docs: remove stray tags that broke Dream page MDX parsing

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
docs: note Synthesis only considers user_id-scoped memories
2026-08-04 18:14:50 +05:30 · 2026-08-04 15:08:29 +05:30 · 2026-08-04 14:06:47 +05:30 · 2026-07-30 19:43:38 +05:30 · 2026-07-30 19:38:05 +05:30 · 2026-07-29 21:23:30 +05:30
250 changed files with 2992 additions and 21977 deletions
@@ -17,10 +17,6 @@
      "claude code", "opencode", "pi agent", "mem0-plugin",
      "cursor plugin", "codex plugin", "editor plugin"
    ],
-    "openmemory": [
-      "openmemory", "open memory", "localhost:8765", "localhost:3000",
-      "openmemory ui", "openmemory/api", "openmemory/ui"
-    ],
    "cli": ["mem0-cli", "@mem0/cli", "npx mem0", "command line"],
    "vector-store": [
      "pgvector", "pinecone", "chroma", "chromadb", "weaviate",
@@ -23,10 +23,6 @@ rest-api:
  - changed-files:
      - any-glob-to-any-file: 'server/**'

-openmemory:
-  - changed-files:
-      - any-glob-to-any-file: 'openmemory/**'
-
 integrations:
  - changed-files:
      - any-glob-to-any-file: 'integrations/**'
@@ -35,12 +35,6 @@ const cases = [
    body: "### 🐛 Describe the bug\n\nI'm using docker compose to deploy a REST API server. When adding memory, I'm unable to set the expiration_date. Is this feature not supported?",
    expected: ["rest-api"],
  },
-  {
-    number: 3444,
-    title: "Fix: Openmemory run.sh non-existent vector-store route",
-    body: "### 🐛 Describe the bug\n\n# Vector_store not implemented\nThere is many references to ` ${NEXT_PUBLIC_API_URL}/api/v1/config/mem0/vector_store` in lines 280, 293, 306, 319,  332, 345, 358, and 371. \n```bash\ncurl -fsS -X PUT \"${NEXT_PUBLIC_API_URL}/api/v1/config/mem0/vector_store\" # Line 280 and for each vector store\n```\nBut the api route is not implemented in `api/app/routers/config.py`.\n# Suggested solution\nI would implement `vector_store` route or remove and use `update_configuration` for all config updates. Also Create class with all config keys for vector_store",
-    expected: ["openmemory"],
-  },
  {
    number: 6252,
    title: "cursor: on_file_read_cursor.sh ignores auto_search / MEM0_AUTO_SEARCH",
@@ -106,7 +106,7 @@ jobs:
        run: |
          pip install --upgrade pip
          pip install -e ".[test,graph,vector_stores,llms,extras]"
-          pip install ruff
+          pip install ruff==0.16.0
      - name: Run Linting
        if: needs.check_changes.outputs.mem0_changed == 'true'
        run: make lint
@@ -27,7 +27,7 @@ jobs:
          script: |
            const allowed = new Set([
              'sdk-python', 'sdk-typescript', 'vector-store', 'plugin',
-              'rest-api', 'openmemory', 'documentation', 'ci', 'cli', 'integrations',
+              'rest-api', 'documentation', 'ci', 'cli', 'integrations',
            ]);
            const umbrella = { plugin: 'integrations' };
            const { repository } = await github.graphql(
@@ -28,7 +28,6 @@ This is a **polyglot monorepo** containing Python and TypeScript packages, CLIs,
 | `integrations/pi-agent-plugin/` | `@mem0/pi-agent-plugin` — Pi Agent plugin |
 | `integrations/vercel-ai-sdk/` | `@mem0/vercel-ai-provider` — Vercel AI SDK memory provider |
 | `server/` | FastAPI REST server for self-hosted Mem0 (Docker: FastAPI + PostgreSQL/pgvector + Neo4j) |
-| `openmemory/` | Self-hosted memory platform — `api/` (FastAPI + Alembic + MCP server) and `ui/` (Next.js 15 + React 19) |
 | `skills/` | Claude Code skill definitions. Reference skills (SDK knowledge, always-on): `mem0/`, `mem0-cli/`, `mem0-vercel-ai-sdk/`. Pipeline skills (run on demand): `mem0-integrate/`, `mem0-test-integration/`, `mem0-oss-to-platform/` |
 | `docs/` | Documentation site (Mintlify) |
 | `tests/` | Python SDK tests (pytest) |
@@ -62,7 +61,7 @@ integrations/openclaw/ ──▶ mem0ai (npm)
 - **Node.js**: v18+ (v20 or v22 recommended)
 - **pnpm**: v10+ (`npm install -g pnpm@10`) — used for all TypeScript packages
 - **Hatch**: Python build/environment tool (`pip install hatch`)
- **Docker**: Required for `server/` and `openmemory/` development
+- **Docker**: Required for `server/` development

 ### Initial Setup

@@ -214,28 +213,6 @@ docker-compose up                  # starts all 3 services
 - **Services:** PostgreSQL with pgvector, Neo4j 5.x with APOC plugin
 - **Hot reload:** Dev Dockerfile mounts `server/` and `mem0/` for live changes

-### OpenMemory (`openmemory/`)
-
-```bash
-# Full stack via Docker Compose
-cd openmemory
-docker-compose up
-# Qdrant: localhost:6333
-# API (MCP): localhost:8765
-# UI: localhost:3000
-
-# Individual development
-cd openmemory/api && uvicorn main:app --reload       # FastAPI backend
-cd openmemory/ui && npm run dev                       # Next.js frontend
-
-# Tests
-cd openmemory/api && pytest tests/                   # API tests (e.g., test_mcp_server.py)
-```
-
- **API:** FastAPI + Alembic (DB migrations) + MCP server (Model Context Protocol)
- **UI:** Next.js 15, React 19, Radix UI, Redux Toolkit, TailwindCSS, Recharts
- **Vector store:** Qdrant
-
 ### Documentation (`docs/`)

 ```bash
@@ -331,7 +308,6 @@ python -m benchmarks.beam.run --project-name my-test --backend cloud --mem0-api-
  - Root SDK: line length **120**
  - Python CLI: line length **100** with extended rule set (UP, B, SIM, RUF)
 - **isort** with `profile = "black"` for import sorting.
- Ruff excludes `openmemory/` from root config.

 ### TypeScript Conventions

@@ -382,7 +358,6 @@ Optional layer on top of vector memory for relationship-aware retrieval. Configu
 Model Context Protocol support in multiple places:

 - **Remote:** MCP server at `mcp.mem0.ai`
- **Local:** MCP server in `openmemory/api/` (FastAPI-based)
 - **Plugin:** MCP tools in `integrations/mem0-plugin/` — 9 tools: `add_memory`, `search_memories`, `get_memories`, `get_memory`, `update_memory`, `delete_memory`, `delete_all_memories`, `delete_entities`, `list_entities`

 ### Plugin & Skills System
@@ -585,7 +560,7 @@ N/A

 - Follow existing code patterns — don't introduce new frameworks or abstractions without discussion.
 - Version bumps go in `pyproject.toml` (Python) or `package.json` (TypeScript).
- For `server/` and `openmemory/` work, use Docker Compose for local development.
+- For `server/` work, use Docker Compose for local development.
 - Do NOT use `pip` or `conda` for dependency management — use `hatch` (see `docs/contributing/development.mdx`).

 ### Contributing Guides
@@ -608,5 +583,4 @@ N/A
 - Use npm or yarn in TypeScript packages — this repo uses pnpm exclusively.
 - Use `require()` for imports in TypeScript — use ES module `import` syntax.
 - Mix up linter configs: root Python SDK uses line-length 120, Python CLI uses 100, Node CLI uses Biome (not ESLint/Ruff).
- Modify `openmemory/` database migrations without understanding the Alembic migration chain.
 - Change public APIs without updating documentation in `docs/`.
@@ -45,7 +45,7 @@ The two most common contribution targets are the SDKs:
 | TypeScript SDK (`mem0ai`) | `mem0-ts/` | TypeScript | `pnpm`        |

 Other packages include the CLIs (`cli/python/`, `cli/node/`), integrations
-(`integrations/`), the self-hosted `server/`, `openmemory/`, and the docs site
+(`integrations/`), the self-hosted `server/`, and the docs site
 (`docs/`). See [AGENTS.md](./AGENTS.md) for a full map of the repository.

 ## Development Workflow
@@ -11,7 +11,7 @@ install:
 	hatch env create

 install_all:
-	pip install ruff==0.6.9 groq together boto3 litellm ollama chromadb weaviate weaviate-client sentence_transformers vertexai \
+	pip install ruff==0.16.0 groq together boto3 litellm ollama chromadb weaviate weaviate-client sentence_transformers vertexai \
 	            google-generativeai elasticsearch opensearch-py vecs "pinecone<7.0.0" pinecone-text faiss-cpu langchain-community \
 							upstash-vector azure-search-documents langchain-memgraph langchain-neo4j langchain-aws rank-bm25 pymochow pymongo psycopg kuzu databricks-sdk valkey

@@ -21,7 +21,7 @@ privately through one of the following channels:
 To help us triage and resolve the issue quickly, please include as much of the
 following as you can:

- Affected component or package (e.g. Python SDK, TypeScript SDK, server, OpenMemory)
+- Affected component or package (e.g. Python SDK, TypeScript SDK, server, CLI)
 - Affected version, tag, or commit
 - Clear, step-by-step reproduction instructions
 - The security impact and a proof of concept, if available
@@ -7,6 +7,18 @@ mode: "wide"
 <Tabs>
 <Tab title="Python">

+<Update label="2026-07-25" description="v2.0.14">
+
+**New Features:**
+- **Vector Stores:** Add an Oracle AI Vector Search provider (`oracledb`) with connection pooling, `HNSW`/`IVF` indexes, JSON metadata filtering, and six selectable distance metrics ([#5358](https://github.com/mem0ai/mem0/pull/5358))
+
+**Bug Fixes:**
+- **Vector Stores:** Translate a `"*"` filter value in OpenSearch into an `exists` query for every key, not just identity keys. It was previously ignored or matched literally against the string `"*"`, so a wildcard filter returned nothing ([#6522](https://github.com/mem0ai/mem0/pull/6522))
+- **Vector Stores:** Re-raise errors from OpenSearch `search()` instead of returning `[]`, so a transport, auth, or index misconfiguration surfaces instead of looking like zero matches. `keyword_search()` still degrades on failure, since it is a best-effort BM25 signal ([#6519](https://github.com/mem0ai/mem0/pull/6519))
+- **Vector Stores:** Guard the `text` field in Milvus `update()` behind the `_has_bm25_schema` check, matching `insert()`, so updating a memory in a collection without the BM25 `text`/`sparse` schema no longer fails ([#5705](https://github.com/mem0ai/mem0/pull/5705))
+
+</Update>
+
 <Update label="2026-07-22" description="v2.0.13">

 **Bug Fixes:**
@@ -1145,6 +1157,18 @@ See the [OSS v2 to v3 migration guide](https://docs.mem0.ai/migration/oss-v2-to-

 <Tab title="TypeScript">

+<Update label="2026-07-25" description="v3.1.2">
+
+**Bug Fixes:**
+- **Vector Stores:** Apply every operator in a Cassandra compound field filter (e.g. `{ age: { gte: 10, lte: 20 } }`) instead of stopping after the first, so the remaining bounds are no longer silently ignored ([#6511](https://github.com/mem0ai/mem0/pull/6511))
+- **Vector Stores:** Stop the Chroma where-clause translator from dropping filter conditions. Same-field ranges (`gte` + `lte`), multi-field conditions inside `$or`, and negated `contains`/`icontains` under `$not` each collapsed to a single clause or vanished, widening the search instead of narrowing it ([#6521](https://github.com/mem0ai/mem0/pull/6521))
+- **Vector Stores:** Skip `"*"` wildcard filter values in Milvus instead of matching them literally, so a filter like `{ user_id: "*" }` no longer returns zero memories ([#6508](https://github.com/mem0ai/mem0/pull/6508))
+- **Vector Stores:** Read `textLemmatized` for BM25 keyword search on Milvus, OpenSearch, and MongoDB, matching the field the memory layer actually writes, so hybrid search on those backends no longer loses the keyword signal ([#6497](https://github.com/mem0ai/mem0/pull/6497))
+- **LLMs:** Forward `responseFormat` to Gemini's `responseMimeType` in `generateResponse()`, so requesting `json_object` returns JSON instead of free-form text ([#6468](https://github.com/mem0ai/mem0/pull/6468))
+- **LLMs:** Find the Anthropic text block by type instead of indexing `content[0]`, so a thinking-enabled model whose `thinking` block comes first no longer throws `Unexpected response type from Anthropic API` ([#6506](https://github.com/mem0ai/mem0/pull/6506))
+
+</Update>
+
 <Update label="2026-07-22" description="v3.1.1">

 **New Features:**
@@ -7,7 +7,7 @@ description: "Reference for vector database configuration options in Mem0, inclu

 The `config` is defined as an object with two main keys:
 - `vector_store`: Specifies the vector database provider and its configuration
-  - `provider`: The name of the vector database (e.g., "chroma", "pgvector", "qdrant", "milvus", "upstash_vector", "azure_ai_search", "vertex_ai_vector_search", "valkey")
+  - `provider`: The name of the vector database (e.g., "chroma", "pgvector", "qdrant", "milvus", "upstash_vector", "azure_ai_search", "vertex_ai_vector_search", "valkey", "oracledb")
  - `config`: A nested dictionary containing provider-specific settings


@@ -95,6 +95,11 @@ Here's a comprehensive list of all parameters that can be used across different
 | `connection_string` | PostgreSQL connection string (for Supabase/PGVector) |
 | `index_method` | Vector index method (for Supabase) |
 | `index_measure` | Distance measure for similarity search (for Supabase) |
+| `connection_params` | Connection settings for Oracle AI Vector Search |
+| `use_connection_pool` | Create an Oracle connection pool from `connection_params` |
+| `distance_metric` | Distance metric for Oracle vector indexing and search |
+| `index_type` | Oracle vector index type: `HNSW` or `IVF` |
+| `index_parameters` | Oracle vector-index parameters for the selected index type |
 </Tab>
 <Tab title="TypeScript">
 | Parameter | Description |
@@ -0,0 +1,134 @@
+---
+title: "Oracle AI Vector Search"
+description: "Use Oracle Database AI Vector Search as a vector store in Mem0 for semantic and relational queries."
+---
+
+[Oracle AI Vector Search](https://www.oracle.com/database/ai-vector-search/) stores embeddings in an Oracle table using the native `VECTOR` data type, so you can combine semantic search over unstructured data with relational queries over business data in a single database.
+
+### Requirements
+
+- Oracle Database 23.4 or later, with a user that can create tables and vector indexes
+- The `python-oracledb` driver. In thick mode, Oracle Client 23.4 or later is also required.
+
+```bash
+pip install oracledb
+```
+
+### Usage
+
+<CodeGroup>
+```python Python
+import os
+from mem0 import Memory
+
+os.environ["OPENAI_API_KEY"] = "sk-xx"
+
+config = {
+    "vector_store": {
+        "provider": "oracledb",
+        "config": {
+            "collection_name": "mem0",
+            "embedding_model_dims": 1536,
+            "connection_params": {
+                "user": "mem0_user",
+                "password": "your-password",
+                "dsn": "localhost:1521/FREEPDB1",
+            },
+        }
+    }
+}
+
+m = Memory.from_config(config)
+messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+m.add(messages, user_id="alice", metadata={"category": "movies"})
+```
+</CodeGroup>
+
+To reuse a connection or pool you already manage, pass it as `client` instead of `connection_params`:
+
+```python
+import oracledb
+
+pool = oracledb.create_pool(user="mem0_user", password="your-password", dsn="localhost:1521/FREEPDB1")
+
+config = {
+    "vector_store": {
+        "provider": "oracledb",
+        "config": {"client": pool},
+    }
+}
+```
+
+### Config
+
+Here are the parameters available for configuring Oracle AI Vector Search:
+
+| Parameter | Description | Default Value |
+| --- | --- | --- |
+| `connection_params` | Connection settings passed to `python-oracledb`, such as `user`, `password` and `dsn`. See the [connection handling guide](https://python-oracledb.readthedocs.io/en/latest/user_guide/connection_handling.html). | `None` |
+| `use_connection_pool` | Create a connection pool from `connection_params` instead of a single connection | `True` |
+| `client` | An existing `oracledb.Connection` or `oracledb.ConnectionPool` to use instead of building one from `connection_params` | `None` |
+| `collection_name` | Name of the Oracle table that stores vectors and payloads | `mem0` |
+| `embedding_model_dims` | Dimension of your embedding vectors, must be greater than 0 | `1536` |
+| `distance_metric` | Distance function used for indexing and search: `COSINE`, `EUCLIDEAN`, `EUCLIDEAN_SQUARED`, `DOT`, `HAMMING` or `MANHATTAN` | `COSINE` |
+| `do_create_index` | Whether to create a vector index on the collection | `True` |
+| `index_type` | Vector index type: `HNSW` or `IVF` | `HNSW` |
+| `index_name` | Name of the vector index | `<collection_name>_VEC_IDX` |
+| `index_parameters` | Index tuning parameters. For `HNSW`: `neighbors`, `efconstruction`. For `IVF`: `neighbor partitions`, `samples_per_partition`, `min_vectors_per_partition`. | `None` |
+| `index_accuracy` | Target index accuracy from 1 to 100, applied as `WITH TARGET ACCURACY <n>` | `None` |
+
+<Note>
+  When you pass a pre-built `client`, Mem0 uses it as-is and ignores `connection_params` and `use_connection_pool`. Mem0 does not close a client it did not create.
+</Note>
+
+### Vector indexes
+
+Set the index type with `index_type` and tune it with `index_parameters`:
+
+```python
+config = {
+    "vector_store": {
+        "provider": "oracledb",
+        "config": {
+            "connection_params": {"user": "mem0_user", "password": "your-password", "dsn": "localhost:1521/FREEPDB1"},
+            "index_type": "HNSW",
+            "index_parameters": {"neighbors": 32, "efconstruction": 200},
+            "index_accuracy": 95,
+        }
+    }
+}
+```
+
+For the full list of supported options, see the Oracle [`CREATE VECTOR INDEX`](https://docs.oracle.com/en/database/oracle/oracle-database/26/sqlrf/create-vector-index.html) reference.
+
+### Search scores
+
+Oracle returns a distance from `VECTOR_DISTANCE`, which Mem0 converts to a `score` where higher means more similar. `COSINE` and the other non-negative metrics produce scores in the range `[0, 1]`. `DOT` returns the inner product, which can fall outside that range.
+
+### Metadata filters
+
+Filters run against the JSON `payload` column and support:
+
+| Filter type | Examples |
+| --- | --- |
+| Scalar equality | `{"user_id": "alice"}` |
+| Field existence | `{"agent_id": "*"}` |
+| Comparison | `{"score": {"gte": 0.5}}`, also `eq`, `ne`, `gt`, `lt`, `lte` |
+| Membership | `{"category": {"in": ["movies", "books"]}}`, also `nin` |
+| String matching | `{"title": {"contains": "sci-fi"}}`, also `icontains` for case-insensitive |
+| Logical groups | `{"AND": [...]}`, `{"OR": [...]}`, `{"NOT": [...]}` |
+
+Multiple fields at the top level are combined with `AND`:
+
+```python
+m.search(
+    "movie recommendations",
+    user_id="alice",
+    filters={"category": {"in": ["movies", "books"]}, "rating": {"gte": 4}},
+)
+```
@@ -1,6 +1,6 @@
 ---
 title: Overview
-description: "Overview of all supported vector databases in Mem0, including Qdrant, Chroma, PGVector, Pinecone, and more."
+description: "Overview of all supported vector databases in Mem0, including Qdrant, Chroma, PGVector, Pinecone, Oracle, and more."
 ---

 Mem0 includes built-in support for various popular databases. Memory can utilize the database provided by the user, ensuring efficient use for specific needs.
@@ -21,6 +21,7 @@ See the list of supported vector databases below.
  <Card title="Milvus" icon="/images/provider-icons/milvus.svg" href="/components/vectordbs/dbs/milvus"></Card>
  <Card title="Pinecone" icon="/images/provider-icons/pinecone.svg" href="/components/vectordbs/dbs/pinecone"></Card>
  <Card title="MongoDB" icon="/images/provider-icons/mongodb.svg" href="/components/vectordbs/dbs/mongodb"></Card>
+  <Card title="Oracle AI Vector Search" icon="/images/provider-icons/oracle.svg" href="/components/vectordbs/dbs/oracledb"></Card>
  <Card title="Azure" icon="/images/provider-icons/azure-color.svg" href="/components/vectordbs/dbs/azure"></Card>
  <Card title="Redis" icon="/images/provider-icons/redis.svg" href="/components/vectordbs/dbs/redis"></Card>
  <Card title="Valkey" icon="/images/provider-icons/valkey.svg" href="/components/vectordbs/dbs/valkey"></Card>
@@ -85,7 +85,8 @@
                          "platform/features/advanced-retrieval",
                          "platform/advanced-memory-operations",
                          "platform/features/custom-instructions",
-                          "platform/features/memory-decay"
+                          "platform/features/memory-decay",
+                          "platform/features/dream"
                        ]
                      },
                      {
@@ -207,6 +208,7 @@
                              "components/vectordbs/dbs/milvus",
                              "components/vectordbs/dbs/pinecone",
                              "components/vectordbs/dbs/mongodb",
+                              "components/vectordbs/dbs/oracledb",
                              "components/vectordbs/dbs/azure",
                              "components/vectordbs/dbs/azure_mysql",
                              "components/vectordbs/dbs/redis",
@@ -633,7 +635,7 @@
    },
    {
      "source": "/platform/features/expiration-date",
-      "destination": "/"
+      "destination": "/platform/features/memory-expiration"
    },
    {
      "source": "/cookbooks/essentials/memory-expiration-short-and-long-term",
@@ -1234,6 +1236,10 @@
    {
      "source": "/platform/features/criteria-retrieval",
      "destination": "/platform/features/advanced-retrieval"
+    },
+    {
+      "source": "/integrations/keywords",
+      "destination": "/integrations/respan"
    }
  ]
 }
@@ -0,0 +1 @@
+<svg fill="#8F74E0" role="img" viewBox="0 0 93.9 59.4" xmlns="http://www.w3.org/2000/svg"><title>Oracle</title><path d="M30.5,59.4H65c16.4-0.4,29.3-14.1,28.9-30.4C93.5,13.1,80.7,0.4,65,0H30.5C14.1-0.4,0.4,12.5,0,28.9s12.5,30,28.9,30.4C29.4,59.4,29.9,59.4,30.5,59.4 M64.2,48.9h-33c-10.6-0.3-18.9-9.2-18.6-19.8C13,19,21.1,10.8,31.2,10.5h33c10.6-0.3,19.5,8,19.8,18.6c0.3,10.6-8,19.5-18.6,19.8C65,48.9,64.6,48.9,64.2,48.9"/></svg>
@@ -207,6 +207,7 @@ If the user is on a pre-current major (Python < 2, TS < 3, or Platform `output_f
 - [Temporal Reasoning](https://docs.mem0.ai/platform/features/temporal-reasoning) [Platform]: Use when time-aware searches like last week, upcoming, or right now need better result ordering.
 - [Custom Instructions](https://docs.mem0.ai/platform/features/custom-instructions) [Platform]: Use when tailoring what Mem0 extracts and stores on Platform.
 - [Memory Decay](https://docs.mem0.ai/platform/features/memory-decay) [Platform]: Use when search results should boost recently-reinforced memories and dampen stale ones. Opt in per project; applies at search time and never filters candidates out.
+- [Dream](https://docs.mem0.ai/platform/features/dream) [Platform]: Use when long-lived user memory should stay coherent on its own - synthesizing recurring patterns, superseding outdated facts, and merging duplicates in the background. Synthesis is opt-in (Pro+); Supersede and Merge are always on.
 - [Advanced Memory Operations](https://docs.mem0.ai/platform/advanced-memory-operations) [Platform]: Use when basic CRUD is not enough - batch ops, complex filters, workflows.

 ### Features - Data Management
@@ -416,7 +417,6 @@ Editor-specific setup docs (already listed above under `## Integrations > AI Cod
 ### MCP Endpoints

 - Hosted MCP server: `https://mcp.mem0.ai` - requires Platform API key. See `platform/mem0-mcp`.
- Self-hosted MCP server: ships with `openmemory/api/` (FastAPI) - runs against your own Qdrant + LLM stack.

 ## Community & Support

@@ -472,6 +472,7 @@ Everything below is OSS-only provider configuration. Skip this entire section wh
 - [Milvus](https://docs.mem0.ai/components/vectordbs/dbs/milvus) [OSS]: Use for large-scale Milvus deployments.
 - [Pinecone](https://docs.mem0.ai/components/vectordbs/dbs/pinecone) [OSS]: Use when the user is on Pinecone managed.
 - [MongoDB](https://docs.mem0.ai/components/vectordbs/dbs/mongodb) [OSS]: Use when Mongo Atlas Vector Search is the backing store.
+- [Oracle AI Vector Search](https://docs.mem0.ai/components/vectordbs/dbs/oracledb) [OSS]: Use when Oracle Database AI Vector Search is the backing store.
 - [Azure AI Search](https://docs.mem0.ai/components/vectordbs/dbs/azure) [OSS]: Use when the user is on Azure AI Search.
 - [Azure MySQL](https://docs.mem0.ai/components/vectordbs/dbs/azure_mysql) [OSS]: Use when vector search runs on Azure Database for MySQL.
 - [Redis](https://docs.mem0.ai/components/vectordbs/dbs/redis) [OSS]: Use when Redis Stack is the backing store.
@@ -1,19 +0,0 @@
-<svg width="307" height="307" viewBox="0 0 307 307" fill="none" xmlns="http://www.w3.org/2000/svg">
-<path d="M162.496 25.3505C165.003 25.3505 167.453 24.6071 169.538 23.2144C171.622 21.8216 173.247 19.8419 174.206 17.5258C175.165 15.2097 175.416 12.6612 174.927 10.2024C174.438 7.74365 173.231 5.48516 171.458 3.71249C169.686 1.93983 167.427 0.73263 164.968 0.243552C162.51 -0.245525 159.961 0.00550576 157.645 0.964866C155.329 1.92423 153.349 3.54885 151.956 5.63328C150.564 7.71772 149.82 10.1683 149.82 12.6753C149.818 14.3404 150.145 15.9895 150.781 17.5283C151.417 19.0671 152.351 20.4653 153.528 21.6427C154.706 22.8201 156.104 23.7537 157.643 24.39C159.181 25.0262 160.83 25.3526 162.496 25.3505Z" fill="#9C58FA"/>
-<path d="M69.3342 56.559C71.1066 54.7862 72.3135 52.5277 72.8024 50.069C73.2913 47.6103 73.0401 45.0619 72.0807 42.7459C71.1213 40.43 69.4967 38.4505 67.4123 37.0579C65.3279 35.6652 62.8774 34.9219 60.3706 34.9219C57.8637 34.9219 55.4132 35.6652 53.3288 37.0579C51.2444 38.4505 49.6198 40.43 48.6604 42.7459C47.701 45.0619 47.4498 47.6103 47.9387 50.069C48.4276 52.5277 49.6345 54.7862 51.4069 56.559C52.5839 57.7363 53.9813 58.6701 55.5193 59.3073C57.0573 59.9444 58.7058 60.2724 60.3706 60.2724C62.0353 60.2724 63.6838 59.9444 65.2218 59.3073C66.7598 58.6701 68.1572 57.7363 69.3342 56.559Z" fill="#9C58FA"/>
-<path d="M25.3505 144.504C25.3505 141.997 24.6071 139.547 23.2143 137.462C21.8216 135.378 19.842 133.753 17.5259 132.794C15.2098 131.835 12.6612 131.584 10.2024 132.073C7.74368 132.562 5.48513 133.769 3.71247 135.542C1.9398 137.314 0.732655 139.573 0.243578 142.032C-0.2455 144.49 0.00543354 147.039 0.964793 149.355C1.92415 151.671 3.54877 153.651 5.63321 155.044C7.71764 156.436 10.1683 157.18 12.6752 157.18C16.0369 157.18 19.261 155.844 21.638 153.467C24.0151 151.09 25.3505 147.866 25.3505 144.504Z" fill="#9C58FA"/>
-<path d="M56.5589 237.749C54.7862 235.976 52.5277 234.769 50.069 234.28C47.6103 233.792 45.0619 234.043 42.7459 235.002C40.43 235.962 38.4505 237.586 37.0579 239.671C35.6652 241.755 34.9219 244.206 34.9219 246.712C34.9219 249.219 35.6652 251.67 37.0579 253.754C38.4505 255.838 40.43 257.463 42.7459 258.423C45.0619 259.382 47.6103 259.633 50.069 259.144C52.5277 258.655 54.7862 257.448 56.5589 255.676C57.7362 254.499 58.6701 253.102 59.3073 251.564C59.9444 250.026 60.2724 248.377 60.2724 246.712C60.2724 245.048 59.9444 243.399 59.3073 241.861C58.6701 240.323 57.7362 238.926 56.5589 237.749Z" fill="#9C58FA"/>
-<path d="M144.488 281.648C141.981 281.648 139.53 282.392 137.446 283.785C135.361 285.177 133.737 287.157 132.777 289.473C131.818 291.789 131.567 294.338 132.056 296.797C132.545 299.255 133.752 301.514 135.525 303.286C137.298 305.059 139.556 306.266 142.015 306.755C144.474 307.244 147.022 306.993 149.338 306.034C151.655 305.075 153.634 303.45 155.027 301.366C156.42 299.281 157.163 296.831 157.163 294.324C157.159 290.963 155.822 287.742 153.446 285.366C151.07 282.989 147.848 281.653 144.488 281.648Z" fill="#9C58FA"/>
-<path d="M237.751 250.487C235.978 252.26 234.771 254.518 234.282 256.977C233.794 259.435 234.045 261.984 235.004 264.3C235.964 266.616 237.588 268.595 239.673 269.988C241.757 271.381 244.207 272.124 246.714 272.124C249.221 272.124 251.672 271.381 253.756 269.988C255.84 268.595 257.465 266.616 258.424 264.3C259.384 261.984 259.635 259.435 259.146 256.977C258.657 254.518 257.45 252.26 255.678 250.487C254.501 249.31 253.104 248.376 251.566 247.739C250.028 247.101 248.379 246.773 246.714 246.773C245.05 246.773 243.401 247.101 241.863 247.739C240.325 248.376 238.928 249.31 237.751 250.487Z" fill="#9C58FA"/>
-<path d="M281.648 162.512C281.648 165.019 282.392 167.469 283.785 169.554C285.177 171.638 287.157 173.263 289.473 174.222C291.789 175.181 294.338 175.432 296.797 174.943C299.255 174.454 301.514 173.247 303.286 171.474C305.059 169.702 306.266 167.443 306.755 164.984C307.244 162.526 306.993 159.977 306.034 157.661C305.075 155.345 303.45 153.365 301.366 151.973C299.281 150.58 296.831 149.836 294.324 149.836C290.962 149.836 287.738 151.172 285.361 153.549C282.984 155.926 281.648 159.15 281.648 162.512Z" fill="#9C58FA"/>
-<path d="M250.471 69.3303C252.244 71.1027 254.503 72.3097 256.961 72.7985C259.42 73.2874 261.968 73.0363 264.284 72.0768C266.6 71.1174 268.58 69.4928 269.972 67.4084C271.365 65.324 272.108 62.8735 272.108 60.3667C272.108 57.8599 271.365 55.4093 269.972 53.3249C268.58 51.2406 266.6 49.616 264.284 48.6565C261.968 47.6971 259.42 47.4459 256.961 47.9348C254.503 48.4236 252.244 49.6306 250.471 51.403C249.294 52.58 248.36 53.9775 247.723 55.5155C247.086 57.0535 246.758 58.7019 246.758 60.3667C246.758 62.0314 247.086 63.6799 247.723 65.2179C248.36 66.7559 249.294 68.1533 250.471 69.3303Z" fill="#9C58FA"/>
-<path d="M184.782 60.8054C180.168 63.4713 178.3 69.0427 177.63 74.3267C177.047 78.9358 175.033 83.2457 171.87 86.6488C168.707 90.052 164.556 92.3766 160.002 93.2951C155.448 94.2136 150.721 93.6796 146.487 91.7683C142.252 89.857 138.724 86.6649 136.401 82.642C134.077 78.6192 133.075 73.9684 133.535 69.3455C133.995 64.7226 135.895 60.3607 138.966 56.8748C142.037 53.389 146.125 50.9549 150.653 49.9159C155.181 48.8768 159.921 49.2852 164.204 51.0834C169.121 53.1428 174.884 54.2762 179.514 51.6422C184.143 49.0082 185.995 43.4049 186.665 38.1208C187.245 33.5107 189.257 29.1987 192.418 25.7931C195.579 22.3876 199.73 20.0603 204.284 19.1394C208.838 18.2185 213.567 18.7505 217.803 20.6605C222.039 22.5704 225.568 25.7618 227.893 29.7846C230.218 33.8075 231.222 38.4587 230.763 43.0824C230.303 47.7062 228.404 52.0691 225.333 55.5559C222.262 59.0426 218.173 61.4773 213.645 62.5165C209.116 63.5557 204.375 63.147 200.091 61.3481C195.174 59.3048 189.411 58.1554 184.782 60.8054Z" fill="#9C58FA"/>
-<path d="M110.073 65.8178C108.7 70.9742 111.318 76.2422 114.575 80.4567C117.417 84.1261 119.036 88.595 119.204 93.2335C119.372 97.872 118.08 102.446 115.51 106.311C112.941 110.177 109.223 113.138 104.881 114.778C100.538 116.419 95.7912 116.655 91.3077 115.454C86.8242 114.253 82.8306 111.675 79.8898 108.084C76.9489 104.493 75.2091 100.07 74.9155 95.4379C74.6219 90.8057 75.7894 86.1981 78.2533 82.2645C80.7173 78.331 84.3534 75.2698 88.6494 73.5124C93.5822 71.485 98.4991 68.2444 99.8241 63.0881C101.149 57.9317 98.579 52.6637 95.3224 48.4493C92.4827 44.7781 90.8665 40.3083 90.7018 35.6699C90.537 31.0315 91.8319 26.4583 94.4039 22.5949C96.976 18.7314 100.695 15.7724 105.038 14.1349C109.381 12.4974 114.128 12.2639 118.611 13.4673C123.094 14.6708 127.085 17.2505 130.024 20.8429C132.963 24.4354 134.7 28.8594 134.991 33.4916C135.283 38.1237 134.113 42.7305 131.647 46.6627C129.182 50.5948 125.544 53.6541 121.248 55.4095C116.363 57.4209 111.462 60.6775 110.073 65.8178Z" fill="#9C58FA"/>
-<path d="M60.7892 122.218C63.4552 126.831 69.0425 128.699 74.3265 129.37C78.9361 129.955 83.2455 131.973 86.6471 135.138C90.0487 138.304 92.3707 142.457 93.2857 147.013C94.2006 151.569 93.6625 156.296 91.747 160.53C89.8314 164.763 86.6353 168.288 82.6093 170.608C78.5833 172.928 73.9305 173.926 69.3073 173.46C64.6841 172.995 60.3236 171.09 56.841 168.014C53.3583 164.938 50.9292 160.846 49.8962 156.316C48.8631 151.785 49.2783 147.045 51.0832 142.763C53.1426 137.846 54.2759 132.083 51.6419 127.454C49.0079 122.824 43.4046 120.973 38.1047 120.302C33.4951 119.717 29.1856 117.699 25.7841 114.533C22.3825 111.368 20.0604 107.214 19.1454 102.659C18.2304 98.1032 18.7687 93.3752 20.6842 89.1418C22.5997 84.9084 25.7959 81.3832 29.8219 79.0632C33.8479 76.7433 38.5006 75.7457 43.1238 76.2113C47.7471 76.6768 52.1075 78.582 55.5902 81.658C59.0728 84.7341 61.502 88.8258 62.535 93.3561C63.568 97.8865 63.1528 102.627 61.3479 106.908C59.2886 111.825 58.1552 117.588 60.7892 122.218Z" fill="#9C58FA"/>
-<path d="M65.8204 196.93C70.9767 198.303 76.2287 195.685 80.4592 192.428C84.1286 189.586 88.5975 187.967 93.236 187.799C97.8745 187.631 102.449 188.923 106.314 191.493C110.179 194.062 113.141 197.78 114.781 202.122C116.421 206.464 116.657 211.212 115.457 215.695C114.256 220.179 111.678 224.172 108.087 227.113C104.496 230.054 100.073 231.794 95.4404 232.087C90.8082 232.381 86.2006 231.214 82.2671 228.75C78.3335 226.286 75.2723 222.649 73.5149 218.353C71.4875 213.421 68.231 208.504 63.0906 207.179C57.9503 205.854 52.6662 208.424 48.4518 211.681C44.7804 214.528 40.308 216.151 35.6652 216.32C31.0224 216.49 26.4435 215.199 22.5738 212.628C18.7042 210.057 15.7391 206.336 14.0968 201.99C12.4544 197.644 12.2176 192.892 13.4197 188.404C14.6218 183.917 17.2021 179.919 20.7969 176.976C24.3917 174.033 28.8195 172.293 33.4562 172C38.0929 171.708 42.7045 172.878 46.6407 175.345C50.577 177.813 53.6394 181.454 55.3961 185.755C57.4235 190.656 60.6641 195.541 65.8204 196.93Z" fill="#9C58FA"/>
-<path d="M122.205 246.21C126.818 243.544 128.686 237.956 129.373 232.672C129.96 228.068 131.978 223.763 135.142 220.366C138.306 216.969 142.456 214.651 147.008 213.738C151.559 212.825 156.283 213.364 160.512 215.278C164.741 217.192 168.263 220.385 170.58 224.408C172.898 228.43 173.895 233.078 173.43 237.697C172.966 242.316 171.064 246.673 167.991 250.153C164.919 253.633 160.832 256.061 156.306 257.095C151.781 258.129 147.045 257.717 142.766 255.916C137.833 253.856 132.07 252.723 127.457 255.357C122.843 257.991 120.96 263.594 120.289 268.894C119.7 273.498 117.681 277.8 114.517 281.196C111.353 284.591 107.204 286.908 102.653 287.821C98.1027 288.733 93.3808 288.194 89.1525 286.281C84.9243 284.367 81.4031 281.175 79.085 277.154C76.767 273.134 75.7689 268.487 76.2316 263.869C76.6942 259.251 78.5942 254.895 81.6638 251.414C84.7334 247.933 88.8179 245.503 93.3417 244.466C97.8655 243.429 102.601 243.838 106.88 245.635C111.828 247.694 117.591 248.876 122.205 246.21Z" fill="#9C58FA"/>
-<path d="M196.915 241.18C198.304 236.024 195.686 230.756 192.414 226.542C189.567 222.87 187.944 218.398 187.774 213.755C187.604 209.112 188.896 204.533 191.467 200.664C194.038 196.794 197.759 193.829 202.104 192.187C206.45 190.544 211.202 190.307 215.69 191.509C220.178 192.712 224.175 195.292 227.118 198.887C230.061 202.481 231.802 206.909 232.094 211.546C232.387 216.183 231.217 220.794 228.749 224.731C226.281 228.667 222.64 231.729 218.339 233.486C213.406 235.513 208.505 238.77 207.164 243.91C205.823 249.051 208.393 254.335 211.666 258.549C214.513 262.22 216.136 266.693 216.306 271.335C216.476 275.978 215.184 280.557 212.613 284.427C210.042 288.297 206.321 291.262 201.975 292.904C197.629 294.546 192.877 294.783 188.39 293.581C183.902 292.379 179.905 289.799 176.962 286.204C174.019 282.609 172.278 278.181 171.985 273.545C171.693 268.908 172.863 264.296 175.331 260.36C177.799 256.424 181.44 253.361 185.741 251.605C190.658 249.577 195.543 246.337 196.915 241.18Z" fill="#9C58FA"/>
-<path d="M246.195 184.797C243.529 180.184 237.957 178.316 232.673 177.629C228.069 177.045 223.764 175.03 220.365 171.869C216.967 168.708 214.646 164.56 213.729 160.01C212.813 155.46 213.348 150.737 215.258 146.507C217.168 142.277 220.357 138.753 224.376 136.431C228.395 134.11 233.041 133.108 237.66 133.567C242.279 134.026 246.637 135.923 250.12 138.991C253.604 142.058 256.037 146.141 257.077 150.664C258.117 155.188 257.711 159.923 255.917 164.204C253.857 169.137 252.724 174.9 255.342 179.513C257.96 184.127 263.595 186.01 268.879 186.681C273.484 187.267 277.789 189.283 281.186 192.446C284.584 195.608 286.904 199.757 287.819 204.308C288.733 208.859 288.197 213.582 286.285 217.811C284.372 222.041 281.181 225.564 277.16 227.884C273.14 230.203 268.492 231.203 263.874 230.741C259.255 230.279 254.897 228.379 251.416 225.31C247.934 222.24 245.503 218.155 244.466 213.63C243.429 209.106 243.838 204.37 245.636 200.09C247.695 195.173 248.861 189.411 246.195 184.797Z" fill="#9C58FA"/>
-<path d="M241.18 110.07C236.024 108.697 230.756 111.315 226.542 114.588C222.87 117.435 218.398 119.058 213.755 119.228C209.112 119.398 204.533 118.106 200.664 115.535C196.794 112.964 193.829 109.243 192.187 104.897C190.544 100.551 190.307 95.7994 191.509 91.3117C192.712 86.824 195.292 82.8268 198.887 79.8837C202.481 76.9405 206.909 75.2 211.546 74.9073C216.183 74.6147 220.794 75.7849 224.731 78.2527C228.667 80.7206 231.729 84.3617 233.486 88.6627C235.513 93.5955 238.754 98.4964 243.91 99.8374C249.066 101.178 254.335 98.6082 258.549 95.3356C262.22 92.4959 266.69 90.8798 271.328 90.7151C275.967 90.5503 280.54 91.8452 284.403 94.4172C288.267 96.9892 291.226 100.709 292.863 105.052C294.501 109.394 294.734 114.142 293.531 118.624C292.327 123.107 289.748 127.099 286.155 130.037C282.563 132.976 278.139 134.714 273.507 135.005C268.875 135.296 264.268 134.126 260.336 131.661C256.403 129.195 253.344 125.557 251.589 121.261C249.577 116.36 246.321 111.459 241.18 110.07Z" fill="#9C58FA"/>
-<path d="M153.491 191.533C174.501 191.533 191.533 174.501 191.533 153.491C191.533 132.482 174.501 115.45 153.491 115.45C132.481 115.45 115.449 132.482 115.449 153.491C115.449 174.501 132.481 191.533 153.491 191.533Z" fill="#9C58FA"/>
-</svg>
@@ -0,0 +1,164 @@
+---
+title: Dream
+description: "Dream keeps a user's memory clean and insightful over time by distilling recurring patterns, retiring outdated facts, and folding away duplicates, automatically and in the background."
+---
+
+# Dream
+
+As an application talks to the same user over weeks and months, their memory grows. Some of that growth is signal, meaning new facts worth keeping. A lot of it is noise: the same preference stated three different ways, an old fact that a newer one has quietly replaced, or a set of small observations that only mean something when you look at them together.
+
+**Dream** is the background layer that keeps a user's memory coherent as it grows. It continuously reviews each user's memories and does three things. It synthesizes higher-order patterns, supersedes outdated facts, and merges duplicates. The result is that what you read back stays sharp instead of drifting into a pile of overlapping, stale entries.
+
+<Info>
+  **Dream matters when…**
+  - Your users interact with your product over a long period and accumulate a lot of memories.
+  - You want retrieval to return the *current* truth about a user, not a mix of old and new contradictory facts.
+  - You want higher-level insights ("this user consistently prefers X") without writing your own summarization layer.
+</Info>
+
+## The three actions of Dream
+
+Dream is made of three independent actions. Two of them, Supersede and Merge, keep memory clean and run automatically for everyone. The third, Synthesis, produces new insight and is a toggle you turn on per project.
+
+| Action | What it does | When it runs | Availability |
+|---|---|---|---|
+| **Synthesis** | Distills a user's memories into higher-order **pattern memories** | On a schedule, in the background | Opt-in (Pro and above) |
+| **Supersede** | Marks an older fact as outdated when a newer one contradicts it | As memories are added | Always on, all plans |
+| **Merge** | Folds a duplicate into a single canonical memory | As memories are added | Always on, all plans |
+
+### Synthesis
+
+Over time a user's memories often *imply* something larger than any single entry. Ten separate notes about early-morning meetings, workout logs, and coffee orders together say "this user is an early riser." **Synthesis** finds those recurring threads and writes them back as new **pattern memories**: concise, higher-order facts that capture what the individual memories only hint at.
+
+- Pattern memories are added *alongside* your existing memories, never in place of them. The source memories stay exactly where they are.
+- Each pattern memory keeps a link back to the specific memories it was distilled from, so an insight is always traceable to its evidence.
+- Synthesis is additive and idempotent. Re-running it will not create duplicate patterns for the same underlying evidence.
+
+**Example.** These four memories accumulate for the same user over time:
+
+- *"User runs approximately 40 kilometers per week and is currently training for a marathon."*
+- *"User lifts weights at the gym three times a week, primarily focusing on legs and back."*
+- *"User tracks all workouts using a Garmin Forerunner watch."*
+- *"User's goal for 2026 is to run a sub-4-hour marathon."*
+
+Synthesis distills them into one pattern memory, kept alongside the originals:
+
+> *"User follows a structured fitness routine that includes weekly long runs (≈40 km), regular leg-and-back strength training, tracks workouts with a Garmin device, and pursues progressive marathon time goals."*
+
+Each source memory stays exactly where it was, and the new pattern links back to all of them as its evidence.
+
+<Note>
+  Synthesis only considers memories created **after** you enable it for a project. Turning it on sets a forward boundary, so historical memories aren't reprocessed in bulk on day one. Everything added from that point on is eligible.
+</Note>
+
+<Note>
+  Synthesis only looks at memories scoped to a **`user_id` alone**. Memories that also carry another entity (an `agent_id`, `run_id`, or `app_id`) are left out of a user's synthesis run. This keeps each run tied to a single user's own memories and avoids cross-referencing across agents, runs, or apps. So a memory has to be user-scoped, with no other entity attached, to be eligible for a pattern.
+</Note>
+
+### Supersede
+
+When a user tells you something that **contradicts** an earlier memory ("I moved to Berlin" after an earlier "I live in Lisbon"), Dream marks the older memory as **superseded** and links it to the newer fact that replaced it. Superseded memories are not deleted and not hidden by default. A normal `search` or `get` still returns them alongside your active memories, badged as superseded, so you keep the full history. When you want only the current truth, ask for it explicitly with `latest_only=true` (see [How reads change](#how-reads-change-with-dream) below). Supersede runs automatically as part of adding memories, on every plan.
+
+**Example.** The user has an existing memory *"User drives a 2019 Subaru Outback."* Later they mention selling it, producing a new memory *"User sold their 2019 Subaru Outback and bought a Tesla Model 3."* Dream marks the Subaru memory as superseded and links it to the newer one. A default `search` returns both: the Tesla memory as active, and the Subaru one labelled superseded. Passing `latest_only=true` returns only *"User sold their 2019 Subaru Outback and bought a Tesla Model 3."*
+
+### Merge
+
+When a new memory is effectively a **duplicate** of one you already have, Dream keeps a single canonical memory instead of two near-identical copies. When a duplicate is stored as its own memory, Dream marks it **merged** and links it to the canonical one. The merged record is hidden from reads by default (you get the one canonical memory), retained rather than deleted, and surfaced with `include_merged=true`. Merge runs automatically as memories are added, on every plan, and keeps your memory set compact without you deduplicating by hand.
+
+In practice, most exact or near-duplicate restatements of a fact you already have are recognised and deduplicated as the memory is added. No second copy is created, so you simply keep the one memory. A distinct `merged` record appears when a fuller version of an existing fact arrives and folds the barer one in.
+
+**Example.** The user has an existing memory *"User has a dog named Rex."* Later they mention *"My dog Rex is a 3-year-old golden retriever."* The richer statement is stored and Dream marks the barer *"User has a dog named Rex"* as **merged** into it. A default read returns the single canonical memory *"User's dog Rex is a 3-year-old golden retriever"*, and `include_merged=true` also returns the merged original.
+
+<Info>
+  **Nothing Dream does is destructive.** Superseded and merged memories are retained, never erased. Every change is recorded and reviewable, so you always know why a memory was retired or combined.
+</Info>
+
+## How reads change with Dream
+
+Dream doesn't change the shape of your `add`, `search`, or `get` calls, so you don't touch your application code. What it changes is *which* memories a read returns by default, and it gives you two flags to widen or narrow that set:
+
+| Read mode | Active | Superseded | Merged |
+|---|:---:|:---:|:---:|
+| **Default** (`search` / `get`) | ✓ | ✓ | ✗ |
+| **`latest_only=true`** | ✓ | — | — |
+| **`include_merged=true`** | ✓ | ✓ | ✓ |
+
+- **By default**, a read returns active plus superseded memories (superseded ones are still there, labelled as history) and hides merged duplicates. Synthesized pattern memories are returned alongside these too.
+- **`latest_only=true`** narrows the result to active memories only, meaning the current truth, with superseded and merged both excluded. Use this when you want the cleanest possible snapshot of the user right now.
+- **`include_merged=true`** returns everything, including the merged duplicates, when you need the complete picture.
+
+## Enabling Dream
+
+Supersede and Merge require no setup. They're always on for every project on every plan.
+
+Synthesis is opt-in per project:
+
+1. Open the **[Dream settings for your project](https://app.mem0.ai/dashboard/dream)** in the Mem0 dashboard.
+2. Toggle **Synthesis** on.
+
+Synthesis is a per-project setting, so you can enable it for one project and compare against another with it off. You can turn it off at any time. Doing so is fully reversible and leaves every existing memory (including already-synthesized patterns) untouched.
+
+From the [Dream page](https://app.mem0.ai/dashboard/dream) you can also review what Dream has done: recent synthesis runs, the patterns produced and their source memories, and the memories that were superseded or merged.
+
+## Plan availability
+
+| Capability | Free | Starter | Pro | Enterprise |
+|---|:---:|:---:|:---:|:---:|
+| **Supersede** (outdated facts flagged) | ✓ | ✓ | ✓ | ✓ |
+| **Merge** (duplicates folded, hidden by default) | ✓ | ✓ | ✓ | ✓ |
+| **Synthesis** (pattern memories written) | — | — | ✓ | ✓ |
+| **Dream dashboard** (runs, activity) | — | — | ✓ | ✓ |
+
+Synthesis requires a **Pro plan or higher**. Enterprise plans also get a faster, configurable schedule (see below).
+
+## How often Dream runs, and what delay to expect
+
+Different actions run on different clocks, so the delay you should expect depends on which action.
+
+### Supersede & Merge, as memories are added
+
+Supersede and Merge are part of the memory-addition pipeline. They're evaluated when a memory is added, so an outdated fact is superseded or a duplicate is merged as part of that add being processed, on the same timescale as the memory becoming searchable. There's no separate schedule to wait for.
+
+### Synthesis, on a schedule in the background
+
+Synthesis runs as a scheduled background job per user, not on every add. Two conditions gate it:
+
+- **Enough to work with:** a user must have at least **20** memories before Synthesis considers them. Below that threshold there isn't a meaningful pattern to distill yet.
+- **Cadence elapsed:** each user is re-synthesized at most once per cadence window.
+
+| Plan | Synthesis cadence (per user) |
+|---|---|
+| Pro | Every **7 days** |
+| Enterprise | **Daily** (and configurable) |
+
+Because Synthesis is processed in batches in the background, **expect new pattern memories to appear within roughly 24 hours of a scheduled run**, not instantly. In practice, the end-to-end delay from crossing a cadence window to seeing new patterns is up to about a day. This background design is deliberate: it keeps Synthesis from adding any latency to your live `add` and `search` calls.
+
+<Warning>
+  Synthesis is **not** real-time. If you enable it today, the first pattern memories for an eligible user will appear on the next scheduled run for that user (governed by the cadence above), and can take up to ~24 hours to complete once that run starts. Supersede and Merge, by contrast, keep pace with your adds.
+</Warning>
+
+## FAQ
+
+**Does Dream delete any of my memories?**
+No. Nothing Dream does is destructive. Superseded memories stay visible in default reads (labelled as history), merged duplicates are hidden by default but retained, and synthesized patterns are added alongside your existing memories, never in place of them. Every change is reviewable from the dashboard.
+
+**How do I get only the current facts, without the superseded ones?**
+Pass `latest_only=true` on your read. Superseded and merged memories are both excluded, leaving only active memories. By default (no flag) superseded memories are included so you keep the full history.
+
+**Do I need to change my code to use Dream?**
+No. Supersede and Merge are always on, and enabling Synthesis is a project setting. Your `add`, `search`, and `get` calls are unchanged. Dream shapes the memory set behind the same API.
+
+**Will Synthesis reprocess all my old memories when I turn it on?**
+No. Enabling Synthesis sets a forward boundary, so only memories created after you turn it on are eligible. This avoids a bulk reprocess of your entire history on day one.
+
+**Why don't I see pattern memories immediately after enabling Synthesis?**
+Synthesis runs on a schedule (every 7 days on Pro, daily on Enterprise) and only for users with at least 20 memories. Patterns appear on the next scheduled run for an eligible user and can take up to ~24 hours to complete once that run starts.
+
+**Which memories does Synthesis include?**
+Only memories scoped to a `user_id` on its own. If a memory also carries an `agent_id`, `run_id`, or `app_id`, it's excluded from that user's synthesis run. This keeps each run confined to a single user's memories and prevents any cross-referencing across agents, runs, or apps. Supersede and Merge are not affected by this and run across your memories as usual.
+
+**Are synthesized pattern memories traceable?**
+Yes. Every pattern memory links back to the specific source memories it was distilled from, so you can always see the evidence behind an insight from the Dream dashboard.
+
+**Can I turn Synthesis off?**
+Yes, at any time, per project. Turning it off is fully reversible and leaves all existing memories, including already-synthesized patterns, untouched.
@@ -1,9 +1,10 @@
 ---
-title: Memory Expiration
-description: "Give a memory a shelf life: set an expiration date and it stops surfacing in search once that date passes, without deleting the record."
+title: "Memory Expiration in Mem0"
+sidebarTitle: "Memory Expiration"
+description: "Set an expiration date on a Mem0 memory and it stops surfacing in search once that date passes. Nothing is deleted. Works on Platform and Open Source."
 ---

-# Memory Expiration
+## Why Use Memory Expiration?

 Some facts are only true for a while. A trial plan ends, a seasonal preference goes stale, a support ticket ages past its retention window. Set an `expiration_date` on a memory and Mem0 stops surfacing it once that date passes, so you don't need a cleanup job hunting for rows to delete.

@@ -18,7 +19,7 @@ Some facts are only true for a while. A trial plan ends, a seasonal preference g
 - **No expiration date means never expires.** That is the default for every memory.
 - **Malformed dates fail open**: a stored value Mem0 can't parse is treated as *not* expired. A bad date never makes a memory silently vanish.

-## Set an expiration date
+## How do you set an expiration date on a memory?

 Set it when you add the memory:

@@ -97,7 +98,7 @@ The same parameter and spelling work on the OSS `Memory` class. See <Link href="
  Expired memories are dropped *before* your `top_k` is applied, so Mem0 widens the internal candidate pool first and short result sets are rare. They are not impossible: if nearly every memory in a scope has expired, a call can still return fewer than `top_k` results. Pass `show_expired: true` to get the full set back.
 </Note>

-## Clear an expiration date
+## How do you clear or remove an expiration date?

 Pass an explicit `None` (Python) or `null` (TypeScript) to make the memory permanent again. The SDKs deliberately preserve that null instead of treating it as "argument not supplied".

@@ -62,10 +62,6 @@ SECTION_MAP = {
        "/open-source/features/rest-api",
        "/open-source/configure-components",
    ],
-    "openmemory": [
-        "/openmemory/overview",
-        "/openmemory/quickstart",
-    ],
    "sdks": [
        "/sdks/python",
        "/sdks/js",
@@ -1,6 +1,6 @@
 {
  "name": "mem0ai",
-  "version": "3.1.1",
+  "version": "3.1.2",
  "description": "The Memory Layer For Your AI Apps",
  "main": "./dist/index.js",
  "module": "./dist/index.mjs",
@@ -100,12 +100,16 @@ export class AnthropicLLM implements LLM {
      return { content, role: "assistant", toolCalls };
    }

-    const firstBlock = response.content[0];
-    if (firstBlock.type === "text") {
-      return firstBlock.text;
-    } else {
-      throw new Error("Unexpected response type from Anthropic API");
+    // Thinking-enabled responses put a thinking block before the text block,
+    // and a response can carry no text block at all, so find the text block
+    // like the tools branch above instead of indexing content[0]. Mirrors the
+    // Python provider (#6481).
+    for (const block of response.content) {
+      if (block.type === "text") {
+        return block.text;
+      }
    }
+    return "";
  }

  async generateChat(messages: Message[]): Promise<LLMResponse> {
@@ -59,6 +59,15 @@ export class GoogleLLM implements LLM {
      ];
    }

+    // Honor a requested JSON response format (parity with the Python SDK's
+    // mem0/llms/gemini.py). Gemini's structured output is opt-in via
+    // responseMimeType — without it the model is never told to emit JSON, so
+    // callers passing json_object silently get free-form text and depend on a
+    // fragile markdown-fence strip downstream.
+    if (responseFormat?.type === "json_object") {
+      config.responseMimeType = "application/json";
+    }
+
    const completion = await this.google.models.generateContent({
      contents,
      model: this.model,
@@ -440,4 +440,52 @@ describe("generateWhereClause", () => {
      ChromaDB.generateWhereClause({ $not: [{ age: { gt: 18 } }] }),
    ).toEqual({ age: { $lte: 18 } });
  });
+
+  // Regression tests for the three where-clause translation bugs fixed in
+  // Python by #6452 and tracked for the TS SDK in #6513. ChromaDB allows
+  // exactly one operator or field per dict level.
+  it("keeps both bounds of a same-field range as $and-combined clauses", () => {
+    expect(ChromaDB.generateWhereClause({ age: { gte: 18, lte: 65 } })).toEqual(
+      { $and: [{ age: { $gte: 18 } }, { age: { $lte: 65 } }] },
+    );
+  });
+
+  it("keeps same-field ranges inside $or branches", () => {
+    expect(
+      ChromaDB.generateWhereClause({
+        $or: [{ age: { gte: 18, lte: 65 } }, { vip: true }],
+      }),
+    ).toEqual({
+      $or: [
+        { $and: [{ age: { $gte: 18 } }, { age: { $lte: 65 } }] },
+        { vip: { $eq: true } },
+      ],
+    });
+  });
+
+  it("wraps multi-field conditions inside $or in $and", () => {
+    expect(
+      ChromaDB.generateWhereClause({
+        $or: [{ age: { gte: 18 }, vip: true }, { city: "sh" }],
+      }),
+    ).toEqual({
+      $or: [
+        { $and: [{ age: { $gte: 18 } }, { vip: { $eq: true } }] },
+        { city: { $eq: "sh" } },
+      ],
+    });
+  });
+
+  it("negates $not contains/icontains instead of dropping the clause", () => {
+    expect(
+      ChromaDB.generateWhereClause({
+        $not: [{ title: { contains: "draft" } }],
+      }),
+    ).toEqual({ title: { $ne: "draft" } });
+    expect(
+      ChromaDB.generateWhereClause({
+        $not: [{ title: { icontains: "draft" } }],
+      }),
+    ).toEqual({ title: { $ne: "draft" } });
+  });
 });
@@ -267,6 +267,36 @@ describe("Milvus vector store (TS OSS SDK)", () => {
    });
  });

+  it("skips a wildcard '*' filter value and keeps the rest", async () => {
+    const client = new FakeMilvusClient({ existing: ["mem0"] });
+    client.searchResponse = { results: [] };
+    const store = makeStore(client, { metricType: "COSINE" });
+    await store.initialize();
+
+    // "*" means match-any: it must be dropped, not emitted as `== "*"` (which
+    // matches nothing), leaving only the real agent_id clause.
+    await store.search([0.1, 0.2, 0.3], 5, {
+      user_id: "*",
+      agent_id: "a1",
+    });
+
+    const searchCall = client.calls.find((c) => c.method === "search")!;
+    expect(searchCall.args.filter).toBe('(metadata["agent_id"] == "a1")');
+  });
+
+  it("omits the filter entirely when every value is a wildcard", async () => {
+    const client = new FakeMilvusClient({ existing: ["mem0"] });
+    const store = makeStore(client);
+    await store.initialize();
+
+    await store.list({ user_id: "*" });
+
+    // All clauses dropped, so list() falls back to its match-all "" filter
+    // rather than a literal `(metadata["user_id"] == "*")` that matches nothing.
+    const queryCall = client.calls.filter((c) => c.method === "query").pop()!;
+    expect(queryCall.args.filter).toBe("");
+  });
+
  it("normalises L2 distances into a 0..1 similarity score", async () => {
    const client = new FakeMilvusClient({ existing: ["mem0"] });
    client.searchResponse = {
@@ -432,12 +462,18 @@ describe("Milvus vector store (TS OSS SDK)", () => {
      ["a"],
      [{ data: "hello world", text_lemmatized: "hello world lemma" }],
    );
+    await store.insert(
+      [[0.2, 0.3, 0.4]],
+      ["c"],
+      [{ data: "hello world", textLemmatized: "hello world camel" }],
+    );
    // Falls back to raw data when there is no lemmatized text.
    await store.insert([[0.4, 0.5, 0.6]], ["b"], [{ data: "just data" }]);

    const insertCalls = client.calls.filter((c) => c.method === "insert");
    expect(insertCalls[0].args.data[0].text).toBe("hello world lemma");
-    expect(insertCalls[1].args.data[0].text).toBe("just data");
+    expect(insertCalls[1].args.data[0].text).toBe("hello world camel");
+    expect(insertCalls[2].args.data[0].text).toBe("just data");
  });

  it("writes the BM25 text field on update for a BM25 collection", async () => {
@@ -5,6 +5,7 @@ const mockFindOne = jest.fn();
 const mockUpdateOne = jest.fn();
 const mockListSearchIndexes = jest.fn();
 const mockCreateSearchIndex = jest.fn();
+const mockDropSearchIndex = jest.fn();
 const mockDrop = jest.fn();
 const mockToArray = jest.fn();
 const mockLimit = jest.fn().mockReturnThis();
@@ -26,6 +27,7 @@ const mockCollection = {
  updateOne: mockUpdateOne,
  listSearchIndexes: mockListSearchIndexes,
  createSearchIndex: mockCreateSearchIndex,
+  dropSearchIndex: mockDropSearchIndex,
  drop: mockDrop,
  find: mockFind,
  aggregate: mockAggregate,
@@ -74,6 +76,25 @@ describe("MongoDB Vector Store", () => {
    await store.close();
  });

+  const expectedTextSearchIndexDefinition = {
+    name: "test_col_text_search_index",
+    definition: {
+      mappings: {
+        dynamic: false,
+        fields: {
+          payload: {
+            type: "document",
+            fields: {
+              data: { type: "string" },
+              textLemmatized: { type: "string" },
+              text_lemmatized: { type: "string" },
+            },
+          },
+        },
+      },
+    },
+  };
+
  it("should initialize client and check/create collection and indexes", async () => {
    await store.initialize();

@@ -84,6 +105,83 @@ describe("MongoDB Vector Store", () => {
    });
    expect(mockCollection.deleteOne).toHaveBeenCalledWith({ _id: 0 });
    expect(mockCreateSearchIndex).toHaveBeenCalledTimes(2);
+    expect(mockCreateSearchIndex).toHaveBeenCalledWith(
+      expectedTextSearchIndexDefinition,
+    );
+  });
+
+  it("should drop and recreate a stale text search index on upgrade", async () => {
+    mockListCollections.mockReturnValue({
+      toArray: jest.fn().mockResolvedValue([{ name: "test_col" }]),
+    });
+    mockListSearchIndexes.mockReturnValue({
+      toArray: jest.fn().mockResolvedValue([
+        { name: "test_col_vector_index" },
+        {
+          name: "test_col_text_search_index",
+          definition: {
+            mappings: {
+              dynamic: false,
+              fields: {
+                payload: {
+                  type: "document",
+                  fields: {
+                    data: { type: "string" },
+                    text_lemmatized: { type: "string" },
+                  },
+                },
+              },
+            },
+          },
+        },
+      ]),
+    });
+
+    await store.initialize();
+
+    expect(mockDropSearchIndex).toHaveBeenCalledWith(
+      "test_col_text_search_index",
+    );
+    expect(mockCreateSearchIndex).toHaveBeenCalledTimes(1);
+    expect(mockCreateSearchIndex).toHaveBeenCalledWith(
+      expectedTextSearchIndexDefinition,
+    );
+  });
+
+  it("should not recreate a text search index that already has textLemmatized", async () => {
+    mockListCollections.mockReturnValue({
+      toArray: jest.fn().mockResolvedValue([{ name: "test_col" }]),
+    });
+    mockListSearchIndexes.mockReturnValue({
+      toArray: jest.fn().mockResolvedValue([
+        { name: "test_col_vector_index" },
+        {
+          name: "test_col_text_search_index",
+          latestDefinition: expectedTextSearchIndexDefinition.definition,
+        },
+      ]),
+    });
+
+    await store.initialize();
+
+    expect(mockDropSearchIndex).not.toHaveBeenCalled();
+    expect(mockCreateSearchIndex).not.toHaveBeenCalled();
+  });
+
+  it("should map payload.textLemmatized in the text search index", async () => {
+    await store.initialize();
+
+    const textIndexCall = mockCreateSearchIndex.mock.calls.find(
+      ([arg]: any[]) => arg.name === "test_col_text_search_index",
+    );
+    expect(textIndexCall).toBeDefined();
+    expect(textIndexCall![0].definition.mappings.fields.payload.fields).toEqual(
+      {
+        data: { type: "string" },
+        text_lemmatized: { type: "string" },
+        textLemmatized: { type: "string" },
+      },
+    );
  });

  it("should insert documents correctly", async () => {
@@ -197,7 +295,11 @@ describe("MongoDB Vector Store", () => {
          index: "test_col_text_search_index",
          text: {
            query: "test",
-            path: ["payload.data", "payload.text_lemmatized"],
+            path: [
+              "payload.data",
+              "payload.text_lemmatized",
+              "payload.textLemmatized",
+            ],
          },
        },
      },
@@ -455,44 +455,64 @@ export class CassandraDB implements VectorStore {
      return value.includes(payloadValue);
    }

+    // Every operator present in a compound condition must hold (AND), so check
+    // them all instead of returning on the first match. Returning early meant a
+    // range like { gte: 10, lte: 20 } only applied `gte`. Mirrors the databricks
+    // store's matcher.
+    let sawOperator = false;
+
    if ("eq" in value) {
-      return payloadValue === value.eq;
+      sawOperator = true;
+      if (payloadValue !== value.eq) return false;
    }
    if ("ne" in value) {
-      return payloadValue !== value.ne;
+      sawOperator = true;
+      if (payloadValue === value.ne) return false;
    }
    if ("gt" in value) {
-      return payloadValue > value.gt;
+      sawOperator = true;
+      if (!(payloadValue > value.gt)) return false;
    }
    if ("gte" in value) {
-      return payloadValue >= value.gte;
+      sawOperator = true;
+      if (!(payloadValue >= value.gte)) return false;
    }
    if ("lt" in value) {
-      return payloadValue < value.lt;
+      sawOperator = true;
+      if (!(payloadValue < value.lt)) return false;
    }
    if ("lte" in value) {
-      return payloadValue <= value.lte;
+      sawOperator = true;
+      if (!(payloadValue <= value.lte)) return false;
    }
    if ("in" in value) {
-      return Array.isArray(value.in) && value.in.includes(payloadValue);
+      sawOperator = true;
+      if (!Array.isArray(value.in) || !value.in.includes(payloadValue))
+        return false;
    }
    if ("nin" in value) {
-      return !Array.isArray(value.nin) || !value.nin.includes(payloadValue);
+      sawOperator = true;
+      if (Array.isArray(value.nin) && value.nin.includes(payloadValue))
+        return false;
    }
    if ("contains" in value) {
-      return (
-        typeof payloadValue === "string" &&
-        payloadValue.includes(value.contains)
-      );
+      sawOperator = true;
+      if (
+        typeof payloadValue !== "string" ||
+        !payloadValue.includes(value.contains)
+      )
+        return false;
    }
    if ("icontains" in value) {
-      return (
-        typeof payloadValue === "string" &&
-        payloadValue.toLowerCase().includes(value.icontains.toLowerCase())
-      );
+      sawOperator = true;
+      if (
+        typeof payloadValue !== "string" ||
+        !payloadValue.toLowerCase().includes(value.icontains.toLowerCase())
+      )
+        return false;
    }

-    return payloadValue === value;
+    return sawOperator ? true : payloadValue === value;
  }

  private filterVector(
@@ -273,14 +273,14 @@ export class ChromaDB implements VectorStore {
  private static convertCondition(
    key: string,
    value: any,
-  ): Record<string, any> | null {
+  ): Array<Record<string, any>> {
    // Wildcard - ChromaDB has no direct wildcard, so skip this filter.
    if (value === "*") {
-      return null;
+      return [];
    }

    if (Array.isArray(value)) {
-      return { [key]: { $in: value } };
+      return [{ [key]: { $in: value } }];
    }

    if (value !== null && typeof value === "object") {
@@ -294,19 +294,31 @@ export class ChromaDB implements VectorStore {
        in: "$in",
        nin: "$nin",
      };
-      const condition: Record<string, any> = {};
-      for (const [op, val] of Object.entries(value)) {
-        if (op in opMap) {
-          condition[key] = { [opMap[op]]: val };
-        } else {
-          // contains/icontains and unknown operators fall back to equality.
-          condition[key] = { $eq: val };
-        }
-      }
-      return condition;
+      // ChromaDB allows exactly one operator per field expression, so each
+      // operator becomes its own clause (combined with $and by the caller).
+      // Previously each operator overwrote the last, silently dropping range
+      // bounds. contains/icontains and unknown operators fall back to
+      // equality.
+      return Object.entries(value).map(([op, val]) => ({
+        [key]: { [opMap[op] ?? "$eq"]: val },
+      }));
    }

-    return { [key]: { $eq: value } };
+    return [{ [key]: { $eq: value } }];
+  }
+
+  /** Combine clauses under a logical operator, unwrapping singletons. */
+  private static combineClauses(
+    clauses: Array<Record<string, any>>,
+    operator: "$and" | "$or",
+  ): Record<string, any> | null {
+    if (clauses.length === 0) {
+      return null;
+    }
+    if (clauses.length === 1) {
+      return clauses[0];
+    }
+    return { [operator]: clauses };
  }

  /**
@@ -337,66 +349,55 @@ export class ChromaDB implements VectorStore {
      if (key === "$or" || key === "OR") {
        const orConditions: any[] = [];
        for (const condition of value as any[]) {
-          const built: Record<string, any> = {};
+          const subClauses: Array<Record<string, any>> = [];
          for (const [subKey, subValue] of Object.entries(condition)) {
-            const converted = ChromaDB.convertCondition(subKey, subValue);
-            if (converted) Object.assign(built, converted);
+            subClauses.push(...ChromaDB.convertCondition(subKey, subValue));
          }
-          if (Object.keys(built).length > 0) orConditions.push(built);
-        }
-        if (orConditions.length > 1) {
-          processed.push({ $or: orConditions });
-        } else if (orConditions.length === 1) {
-          processed.push(orConditions[0]);
+          // Multi-field conditions must be wrapped in $and — ChromaDB rejects
+          // flat objects with more than one field per level.
+          const combined = ChromaDB.combineClauses(subClauses, "$and");
+          if (combined) orConditions.push(combined);
        }
+        const combinedOr = ChromaDB.combineClauses(orConditions, "$or");
+        if (combinedOr) processed.push(combinedOr);
      } else if (key === "$not" || key === "NOT") {
        // De Morgan: NOT(a AND b) is (NOT a) OR (NOT b), so the negated fields
        // within one condition are combined with $or, and separate conditions
        // are combined with $and. This mirrors the Python SDK's ChromaDB port.
        const negatedPerGroup: any[] = [];
        for (const condition of value as any[]) {
-          const negatedFields: any[] = [];
+          const negatedFields: Array<Record<string, any>> = [];
          for (const [subKey, subValue] of Object.entries(condition)) {
            if (subValue !== null && typeof subValue === "object") {
              for (const [op, val] of Object.entries(subValue as any)) {
-                const neg = negateOp[op];
-                if (neg) {
-                  const converted = ChromaDB.convertCondition(subKey, {
-                    [neg]: val,
-                  });
-                  if (converted) negatedFields.push(converted);
-                }
+                // Unknown operators mirror the positive-path equality
+                // fallback as inequality (previously they were silently
+                // dropped, which could erase the entire NOT clause).
+                const neg = negateOp[op] ?? "ne";
+                negatedFields.push(
+                  ...ChromaDB.convertCondition(subKey, { [neg]: val }),
+                );
              }
            } else {
-              const converted = ChromaDB.convertCondition(subKey, {
-                ne: subValue,
-              });
-              if (converted) negatedFields.push(converted);
+              negatedFields.push(
+                ...ChromaDB.convertCondition(subKey, { ne: subValue }),
+              );
            }
          }
-          if (negatedFields.length > 1) {
-            negatedPerGroup.push({ $or: negatedFields });
-          } else if (negatedFields.length === 1) {
-            negatedPerGroup.push(negatedFields[0]);
-          }
-        }
-        if (negatedPerGroup.length > 1) {
-          processed.push({ $and: negatedPerGroup });
-        } else if (negatedPerGroup.length === 1) {
-          processed.push(negatedPerGroup[0]);
+          const combined = ChromaDB.combineClauses(negatedFields, "$or");
+          if (combined) negatedPerGroup.push(combined);
        }
+        const combinedNot = ChromaDB.combineClauses(negatedPerGroup, "$and");
+        if (combinedNot) processed.push(combinedNot);
      } else {
-        const converted = ChromaDB.convertCondition(key, value);
-        if (converted) processed.push(converted);
+        const combined = ChromaDB.combineClauses(
+          ChromaDB.convertCondition(key, value),
+          "$and",
+        );
+        if (combined) processed.push(combined);
      }
    }

-    if (processed.length === 0) {
-      return undefined;
-    }
-    if (processed.length === 1) {
-      return processed[0];
-    }
-    return { $and: processed };
+    return ChromaDB.combineClauses(processed, "$and") ?? undefined;
  }
 }
@@ -235,6 +235,13 @@ export class Milvus implements VectorStore {
      if (!Milvus.SAFE_FILTER_KEY.test(key)) {
        throw new Error(`Invalid filter key: ${JSON.stringify(key)}`);
      }
+      if (value === "*") {
+        // Wildcard - match any value. Milvus has no direct wildcard, so skip
+        // the clause rather than emitting a literal `== "*"` that matches
+        // nothing. Mirrors the Python provider (#6187) and the chroma/pinecone
+        // stores.
+        continue;
+      }
      if (typeof value === "string") {
        // Escape backslashes before quotes so a value can't break out of the
        // string literal (order matters, exactly as in the Python provider).
@@ -252,13 +259,13 @@ export class Milvus implements VectorStore {
  }

  /**
-   * Text fed to the BM25 sparse index for a payload. Prefers the lemmatized
-   * text, falls back to the raw memory `data`, and truncates to the VarChar
-   * limit (mirrors the Python provider).
+   * Text fed to the BM25 sparse index for a payload. Prefers `textLemmatized`,
+   * then `text_lemmatized`, then raw `data`; truncates to the VarChar limit.
   */
  private bm25Text(payload?: Record<string, any>): string {
    if (!payload) return "";
-    const raw = payload.text_lemmatized || payload.data || "";
+    const raw =
+      payload.textLemmatized || payload.text_lemmatized || payload.data || "";
    return String(raw).slice(0, 65535);
  }

@@ -62,6 +62,46 @@ export class MongoDB implements VectorStore {
    return this._initPromise;
  }

+  private textSearchIndexDefinition(textIndexName: string) {
+    return {
+      name: textIndexName,
+      definition: {
+        mappings: {
+          dynamic: false,
+          fields: {
+            payload: {
+              type: "document",
+              fields: {
+                data: { type: "string" },
+                textLemmatized: { type: "string" },
+                text_lemmatized: { type: "string" },
+              },
+            },
+          },
+        },
+      },
+    };
+  }
+
+  private textSearchIndexMappingIsCurrent(
+    index: Record<string, unknown>,
+  ): boolean {
+    const definition =
+      (index.latestDefinition as Record<string, unknown> | undefined) ??
+      (index.definition as Record<string, unknown> | undefined);
+    const payloadFields = (
+      (definition?.mappings as Record<string, unknown> | undefined)?.fields as
+        | Record<string, unknown>
+        | undefined
+    )?.payload as Record<string, unknown> | undefined;
+    const fields =
+      (payloadFields?.fields as Record<string, unknown> | undefined) ?? {};
+    const textLemmatized = fields.textLemmatized as
+      | { type?: string }
+      | undefined;
+    return textLemmatized?.type === "string";
+  }
+
  private async _doInitialize(): Promise<void> {
    await this.ensureClient();
    try {
@@ -111,32 +151,24 @@ export class MongoDB implements VectorStore {
      // Create Text Search Index for keywordSearch
      const textIndexName = `${this.collectionName}_text_search_index`;
      try {
-        let foundTextIndex = false;
+        let existingTextIndex: Record<string, unknown> | null = null;
        try {
          const indexes = await this.collection.listSearchIndexes().toArray();
-          foundTextIndex = indexes.some((idx) => idx.name === textIndexName);
+          existingTextIndex =
+            (indexes.find((idx) => idx.name === textIndexName) as
+              | Record<string, unknown>
+              | undefined) ?? null;
        } catch (e) {
          // ignore
        }

-        if (!foundTextIndex) {
-          await this.collection.createSearchIndex({
-            name: textIndexName,
-            definition: {
-              mappings: {
-                dynamic: false,
-                fields: {
-                  payload: {
-                    type: "document",
-                    fields: {
-                      data: { type: "string" },
-                      text_lemmatized: { type: "string" },
-                    },
-                  },
-                },
-              },
-            },
-          });
+        const textSearchIndex = this.textSearchIndexDefinition(textIndexName);
+
+        if (!existingTextIndex) {
+          await this.collection.createSearchIndex(textSearchIndex);
+        } else if (!this.textSearchIndexMappingIsCurrent(existingTextIndex)) {
+          await this.collection.dropSearchIndex(textIndexName);
+          await this.collection.createSearchIndex(textSearchIndex);
        }
      } catch (e: any) {
        console.warn(
@@ -286,7 +318,11 @@ export class MongoDB implements VectorStore {
            index: textIndexName,
            text: {
              query: query,
-              path: ["payload.data", "payload.text_lemmatized"],
+              path: [
+                "payload.data",
+                "payload.text_lemmatized",
+                "payload.textLemmatized",
+              ],
            },
          },
        },
@@ -276,6 +276,7 @@ export class OpenSearchDB implements VectorStore {
      should: [
        { match: { "payload.data": query } },
        { match: { "payload.text_lemmatized": query } },
+        { match: { "payload.textLemmatized": query } },
      ],
      minimum_should_match: 1,
    };
@@ -72,6 +72,37 @@ describe("AnthropicLLM (unit)", () => {
    expect(callArgs.tool_choice).toBeUndefined();
  });

+  // Regression: thinking-enabled models emit a thinking block before the text
+  // block. Indexing content[0] threw "Unexpected response type"; the text block
+  // must be found by type instead (TS parity with #6481).
+  it("returns the text block when a thinking block precedes it (no tools)", async () => {
+    mockCreate.mockResolvedValueOnce({
+      content: [
+        { type: "thinking", thinking: "Let me reason about this." },
+        { type: "text", text: '{"facts": ["fact1"]}' },
+      ],
+    });
+
+    const llm = new AnthropicLLM({ apiKey: "test-key" });
+    const result = await llm.generateResponse([
+      { role: "user", content: "Hello" },
+    ]);
+
+    expect(result).toBe('{"facts": ["fact1"]}');
+  });
+
+  // A response carrying no text block at all must resolve to "" rather than throw.
+  it("returns an empty string when no text block is present (no tools)", async () => {
+    mockCreate.mockResolvedValueOnce({
+      content: [{ type: "thinking", thinking: "Thinking only." }],
+    });
+
+    const llm = new AnthropicLLM({ apiKey: "test-key" });
+    await expect(
+      llm.generateResponse([{ role: "user", content: "Hello" }]),
+    ).resolves.toBe("");
+  });
+
  // Bug #1 regression: bare string "auto" must NOT be sent; object form required
  it("forwards tool_choice as { type: 'auto' } (not bare string) when tools are provided", async () => {
    mockCreate.mockResolvedValueOnce({
@@ -0,0 +1,63 @@
+/// <reference types="jest" />
+/**
+ * Cassandra vector store — filter matching unit tests.
+ *
+ * Cassandra has no server-side metadata filter, so search()/list() scan rows
+ * and apply filters in-app via matchFieldCondition(). These tests drive that
+ * matcher through the public list() API with an injected fake client.
+ */
+import { CassandraDB } from "../src/vector_stores/cassandra";
+
+type Row = { id: string; payload: Record<string, any> };
+
+// Minimal fake driver: CREATE statements during initialize() return nothing;
+// a SELECT returns the seeded rows in one page (pageState undefined => stop).
+function fakeClient(rows: Row[]) {
+  return {
+    async connect() {},
+    async execute(query: string) {
+      if (/^\s*SELECT/i.test(query)) {
+        return { rows, pageState: undefined };
+      }
+      return { rows: [], pageState: undefined };
+    },
+    async shutdown() {},
+  };
+}
+
+function makeStore(rows: Row[]) {
+  return new CassandraDB({
+    keyspace: "mem0",
+    collectionName: "mem0",
+    dimension: 3,
+    client: fakeClient(rows) as any,
+  } as any);
+}
+
+describe("CassandraDB filter matching", () => {
+  const rows: Row[] = [
+    { id: "a", payload: { data: "a", age: 5 } },
+    { id: "b", payload: { data: "b", age: 15 } },
+    { id: "c", payload: { data: "c", age: 25 } },
+  ];
+
+  it("applies every operator in a compound range filter (not just the first)", async () => {
+    const store = makeStore(rows);
+    // age in [10, 20]: only "b" (15) qualifies. The old matcher returned on the
+    // first operator (gte), so "c" (25) leaked through because lte was ignored.
+    const [results] = await store.list({ age: { gte: 10, lte: 20 } });
+    expect(results.map((r) => r.id)).toEqual(["b"]);
+  });
+
+  it("still matches a single-operator filter", async () => {
+    const store = makeStore(rows);
+    const [results] = await store.list({ age: { gte: 15 } });
+    expect(results.map((r) => r.id).sort()).toEqual(["b", "c"]);
+  });
+
+  it("treats a plain equality filter as before", async () => {
+    const store = makeStore(rows);
+    const [results] = await store.list({ age: 15 });
+    expect(results.map((r) => r.id)).toEqual(["b"]);
+  });
+});
@@ -185,6 +185,37 @@ describe("GoogleLLM (unit)", () => {
    expect(response.toolCalls[1].name).toBe("add_graph_memory");
  });

+  // Regression: generateResponse accepted a responseFormat argument but never
+  // forwarded it, so Gemini was never told to emit JSON (parity with the Python
+  // SDK's mem0/llms/gemini.py, which sets response_mime_type/response_schema).
+  it("forwards json_object responseFormat as responseMimeType", async () => {
+    mockGenerateContent.mockResolvedValueOnce({
+      text: '{"facts": ["fact1"]}',
+      functionCalls: null,
+    });
+
+    const llm = new GoogleLLM({ apiKey: "test-key" });
+    await llm.generateResponse([{ role: "user", content: "Extract facts" }], {
+      type: "json_object",
+    });
+
+    const callArgs = mockGenerateContent.mock.calls[0][0];
+    expect(callArgs.config.responseMimeType).toBe("application/json");
+  });
+
+  it("does not set responseMimeType when no responseFormat is given", async () => {
+    mockGenerateContent.mockResolvedValueOnce({
+      text: "plain text",
+      functionCalls: null,
+    });
+
+    const llm = new GoogleLLM({ apiKey: "test-key" });
+    await llm.generateResponse([{ role: "user", content: "Hello" }]);
+
+    const callArgs = mockGenerateContent.mock.calls[0][0];
+    expect(callArgs.config.responseMimeType).toBeUndefined();
+  });
+
  it("formats generateChat messages and joins Gemini response parts", async () => {
    mockGenerateContent.mockResolvedValueOnce({
      candidates: [
@@ -153,4 +153,26 @@ describe("OpenSearchDB", () => {

    await expect(store.get("missing")).resolves.toBeNull();
  });
+
+  it("keywordSearch queries lemmatized payload fields", async () => {
+    const client = createClient();
+    const store = await createStore(client);
+
+    await store.keywordSearch("stud french", 5, { user_id: "alice" });
+
+    const searchCall = client.search.mock.calls.find(
+      ([arg]: any[]) => arg.index === collectionName,
+    );
+    expect(searchCall).toBeDefined();
+    const should = searchCall![0].body.query.bool.should;
+    expect(should).toContainEqual({
+      match: { "payload.textLemmatized": "stud french" },
+    });
+    expect(should).toContainEqual({
+      match: { "payload.text_lemmatized": "stud french" },
+    });
+    expect(should).toContainEqual({
+      match: { "payload.data": "stud french" },
+    });
+  });
 });
@@ -0,0 +1,113 @@
+"""Pydantic configuration for the Oracle AI Vector Search integration."""
+
+import re
+from typing import Any, Dict, Literal, Optional
+
+from pydantic import BaseModel, ConfigDict, Field, field_validator, model_validator
+
+
+def _quote_identifier(name: str) -> str:
+    name = name.strip()
+    reg = r'^(?:"[^"]+"|[^".]+)(?:\.(?:"[^"]+"|[^".]+))*$'
+    pattern_validate = re.compile(reg)
+
+    if not pattern_validate.match(name):
+        raise ValueError(f"Identifier name {name} is not valid.")
+
+    pattern_match = r'"([^"]+)"|([^".]+)'
+    groups = re.findall(pattern_match, name)
+    groups = [m[0] or m[1] for m in groups]
+    groups = [f'"{g}"' for g in groups]
+
+    return ".".join(groups)
+
+
+class HnswParams(BaseModel):
+    model_config = ConfigDict(extra="forbid", strict=True)
+
+    neighbors: Optional[int] = Field(None, ge=2, le=2048)
+    efconstruction: Optional[int] = Field(None, ge=1, le=65535)
+
+
+class IvfParams(BaseModel):
+    model_config = ConfigDict(extra="forbid", strict=True)
+
+    neighbor_partitions: Optional[int] = Field(None, alias="neighbor partitions", ge=1, le=10_000_000)
+    samples_per_partition: Optional[int] = Field(None, ge=1)
+    min_vectors_per_partition: Optional[int] = Field(None, ge=0)
+
+
+class OracleAIVectorSearchConfig(BaseModel):
+    """Configuration required to connect to an Oracle database with vector search enabled."""
+
+    connection_params: Optional[dict] = Field(None, description="Database connection parameters, including auth.")
+    use_connection_pool: bool = Field(
+        True,
+        description="Create a ConnectionPool instead of a single Connection when no client is provided",
+    )
+
+    client: Optional[Any] = Field(
+        None, description="Oracle Connection or ConnectionPool (overrides connection string and individual parameters)"
+    )
+
+    collection_name: str = Field("mem0", description="Default name for the collection")
+    embedding_model_dims: int = Field(1536, description="Dimension of the embedding vectors")
+    distance_metric: Literal["EUCLIDEAN", "EUCLIDEAN_SQUARED", "COSINE", "DOT", "HAMMING", "MANHATTAN"] = Field(
+        "COSINE",
+        description="Similarity metric: EUCLIDEAN, EUCLIDEAN_SQUARED, COSINE, DOT, HAMMING or MANHATTAN. Defaults to COSINE",
+    )
+
+    do_create_index: Optional[bool] = Field(True, description="Optional whether to create index")
+    index_type: Literal["HNSW", "IVF"] = Field("HNSW", description="Optional index type, HNSW or IVF")
+    index_name: Optional[str] = Field(None, description="Optional custom name for the vector index")
+    index_parameters: Optional[dict] = Field(
+        None,
+        description="Optional structured CREATE VECTOR INDEX parameters",
+    )
+    index_accuracy: Optional[int] = Field(None, description="Optional index accuracy")
+
+    @field_validator("distance_metric", "index_type", mode="before")
+    @classmethod
+    def _normalize_uppercase(cls, value: Any) -> Any:
+        return value.upper() if isinstance(value, str) else value
+
+    @model_validator(mode="after")
+    def _validate_model(self):
+        """Normalise attributes and validate identifiers/metrics."""
+
+        if not self.connection_params and not self.client:
+            raise ValueError("Must provide at least one of `connection_params` and `client`")
+
+        if self.index_name is None:
+            self.index_name = f"{self.collection_name}_VEC_IDX"
+
+        self.index_name = _quote_identifier(self.index_name)
+        self.collection_name = _quote_identifier(self.collection_name)
+
+        if self.index_parameters is not None:
+            parameter_model = HnswParams if self.index_type == "HNSW" else IvfParams
+            self.index_parameters = parameter_model.model_validate(self.index_parameters).model_dump(
+                by_alias=True,
+                exclude_none=True,
+            )
+
+        if self.index_accuracy and not (0 < self.index_accuracy <= 100):
+            raise ValueError("`index_accuracy` must be between 1 and 100")
+
+        if not (0 < self.embedding_model_dims):
+            raise ValueError("`embedding_model_dims` must be bigger than 0")
+
+        return self
+
+    @model_validator(mode="before")
+    @classmethod
+    def validate_extra_fields(cls, values: Dict[str, Any]) -> Dict[str, Any]:
+        allowed_fields = set(cls.model_fields.keys())
+        extra_fields = set(values.keys()) - allowed_fields
+        if extra_fields:
+            raise ValueError(
+                "Extra fields not allowed: {}. Please input only the following fields: {}".format(
+                    ", ".join(sorted(extra_fields)), ", ".join(sorted(allowed_fields))
+                )
+            )
+        return values
@@ -201,6 +201,7 @@ class VectorStoreFactory:
        "cassandra": "mem0.vector_stores.cassandra.CassandraDB",
        "neptune": "mem0.vector_stores.neptune_analytics.NeptuneAnalyticsVector",
        "turbopuffer": "mem0.vector_stores.turbopuffer.TurbopufferDB",
+        "oracledb": "mem0.vector_stores.oracledb.OracleAIVectorSearch",
    }

    @classmethod
@@ -254,110 +254,111 @@ class ChromaDB(VectorStoreBase):
    def _generate_where_clause(where: dict[str, any]) -> dict[str, any]:
        """
        Generate a properly formatted where clause for ChromaDB.
-        
+
+        ChromaDB's where grammar allows exactly one field or one logical
+        operator per dict level, so multiple operators on the same field and
+        multi-field conditions must be combined with an explicit ``$and``.
+
        Args:
            where (dict[str, any]): The filter conditions.
-            
+
        Returns:
            dict[str, any]: Properly formatted where clause for ChromaDB.
        """
        if where is None:
            return None
-        
-        def convert_condition(key: str, value: any) -> dict:
-            """Convert universal filter format to ChromaDB format."""
+
+        op_map = {
+            "eq": "$eq",
+            "ne": "$ne",
+            "gt": "$gt",
+            "gte": "$gte",
+            "lt": "$lt",
+            "lte": "$lte",
+            "in": "$in",
+            "nin": "$nin",
+        }
+        # Negation of each operator. contains/icontains fall back to equality
+        # on the positive path (ChromaDB has no substring match), so their
+        # negation falls back to inequality for consistency.
+        negate_map = {
+            "eq": "$ne",
+            "ne": "$eq",
+            "gt": "$lte",
+            "gte": "$lt",
+            "lt": "$gte",
+            "lte": "$gt",
+            "in": "$nin",
+            "nin": "$in",
+        }
+
+        def convert_condition(key: str, value: any) -> list:
+            """Convert one field condition to a list of single-field ChromaDB clauses."""
            if value == "*":
                # Wildcard - match any value (ChromaDB doesn't have direct wildcard, so we skip this filter)
+                return []
+            if isinstance(value, dict):
+                # One clause per operator: ChromaDB rejects field expressions
+                # with more than one operator, so a range like
+                # {"gte": 18, "lte": 65} must become two clauses combined
+                # with $and by the caller (previously each operator
+                # overwrote the last, silently dropping bounds).
+                # contains/icontains and unknown operators fall back to equality.
+                return [{key: {op_map.get(op, "$eq"): val}} for op, val in value.items()]
+            # Simple equality
+            return [{key: {"$eq": value}}]
+
+        def combine(clauses: list, operator: str):
+            """Combine clauses under a logical operator, unwrapping singletons."""
+            if not clauses:
                return None
-            elif isinstance(value, dict):
-                # Handle comparison operators
-                chroma_condition = {}
-                for op, val in value.items():
-                    if op == "eq":
-                        chroma_condition[key] = {"$eq": val}
-                    elif op == "ne":
-                        chroma_condition[key] = {"$ne": val}
-                    elif op == "gt":
-                        chroma_condition[key] = {"$gt": val}
-                    elif op == "gte":
-                        chroma_condition[key] = {"$gte": val}
-                    elif op == "lt":
-                        chroma_condition[key] = {"$lt": val}
-                    elif op == "lte":
-                        chroma_condition[key] = {"$lte": val}
-                    elif op == "in":
-                        chroma_condition[key] = {"$in": val}
-                    elif op == "nin":
-                        chroma_condition[key] = {"$nin": val}
-                    elif op in ["contains", "icontains"]:
-                        # ChromaDB doesn't support contains, fallback to equality
-                        chroma_condition[key] = {"$eq": val}
-                    else:
-                        # Unknown operator, treat as equality
-                        chroma_condition[key] = {"$eq": val}
-                return chroma_condition
-            else:
-                # Simple equality
-                return {key: {"$eq": value}}
-        
+            if len(clauses) == 1:
+                return clauses[0]
+            return {operator: clauses}
+
        processed_filters = []
-        
+
        for key, value in where.items():
            if key == "$or":
-                # Handle OR conditions
                or_conditions = []
                for condition in value:
-                    or_condition = {}
+                    sub_clauses = []
                    for sub_key, sub_value in condition.items():
-                        converted = convert_condition(sub_key, sub_value)
-                        if converted:
-                            or_condition.update(converted)
-                    if or_condition:
-                        or_conditions.append(or_condition)
-                
-                if len(or_conditions) > 1:
-                    processed_filters.append({"$or": or_conditions})
-                elif len(or_conditions) == 1:
-                    processed_filters.append(or_conditions[0])
-            
+                        sub_clauses.extend(convert_condition(sub_key, sub_value))
+                    combined = combine(sub_clauses, "$and")
+                    if combined:
+                        or_conditions.append(combined)
+                combined_or = combine(or_conditions, "$or")
+                if combined_or:
+                    processed_filters.append(combined_or)
+
            elif key == "$not":
-                negate_op = {
-                    "eq": "$ne", "ne": "$eq",
-                    "gt": "$lte", "gte": "$lt",
-                    "lt": "$gte", "lte": "$gt",
-                    "in": "$nin", "nin": "$in",
-                }
                negated_per_group = []
                for condition in value:
                    negated_fields = []
                    for sub_key, sub_value in condition.items():
                        if isinstance(sub_value, dict):
                            for op, val in sub_value.items():
-                                neg = negate_op.get(op)
-                                if neg:
-                                    negated_fields.append({sub_key: {neg: val}})
+                                # Unknown operators mirror the positive-path
+                                # equality fallback as inequality (previously
+                                # they were silently dropped, which could
+                                # erase the entire NOT clause).
+                                negated_fields.append({sub_key: {negate_map.get(op, "$ne"): val}})
                        else:
                            negated_fields.append({sub_key: {"$ne": sub_value}})
-                    if len(negated_fields) > 1:
-                        negated_per_group.append({"$or": negated_fields})
-                    elif len(negated_fields) == 1:
-                        negated_per_group.append(negated_fields[0])
+                    # NOT(a AND b) == (NOT a) OR (NOT b)
+                    combined = combine(negated_fields, "$or")
+                    if combined:
+                        negated_per_group.append(combined)
+                combined_not = combine(negated_per_group, "$and")
+                if combined_not:
+                    processed_filters.append(combined_not)

-                if len(negated_per_group) > 1:
-                    processed_filters.append({"$and": negated_per_group})
-                elif len(negated_per_group) == 1:
-                    processed_filters.append(negated_per_group[0])
-                
            else:
                # Regular condition
-                converted = convert_condition(key, value)
-                if converted:
-                    processed_filters.append(converted)
-        
+                combined = combine(convert_condition(key, value), "$and")
+                if combined:
+                    processed_filters.append(combined)
+
        # Return appropriate format based on number of conditions
-        if len(processed_filters) == 0:
-            return None
-        elif len(processed_filters) == 1:
-            return processed_filters[0]
-        else:
-            return {"$and": processed_filters}
+        return combine(processed_filters, "$and")
@@ -35,6 +35,7 @@ class VectorStoreConfig(BaseModel):
        "langchain": "LangchainConfig",
        "s3_vectors": "S3VectorsConfig",
        "turbopuffer": "TurbopufferConfig",
+        "oracledb": "OracleAIVectorSearchConfig",
    }

    @model_validator(mode="after")
@@ -298,10 +298,12 @@ class MilvusDB(VectorStoreBase):
            if payload is None:
                payload = existing[0].get("metadata")

-        text = ""
-        if payload:
-            text = (payload.get("text_lemmatized") or payload.get("data", ""))[:65535]
-        schema = {"id": vector_id, "vectors": vector, "metadata": payload, "text": text}
+        schema = {"id": vector_id, "vectors": vector, "metadata": payload}
+        if self._has_bm25_schema:
+            text = ""
+            if payload:
+                text = (payload.get("text_lemmatized") or payload.get("data", ""))[:65535]
+            schema["text"] = text
        self.client.upsert(collection_name=self.collection_name, data=schema)

    def get(self, vector_id) -> Optional[OutputData]:
@@ -16,6 +16,7 @@ from mem0.vector_stores.base import VectorStoreBase
 logger = logging.getLogger(__name__)

 _SAFE_FILTER_KEY = re.compile(r"^[a-zA-Z_][a-zA-Z0-9_.]*$")
+_IDENTITY_FILTER_KEYS = ("user_id", "agent_id", "run_id")


 def _validate_filter(key: str, value) -> None:
@@ -28,6 +29,29 @@ def _validate_filter(key: str, value) -> None:
        )


+def _build_filter_clauses(filters):
+    """Build term clauses from every filter key, not just the identity keys."""
+    filter_clauses = []
+    for key, value in (filters or {}).items():
+        if value is None:
+            continue
+        if value == "*":
+            # "Any value" wildcard (a documented Platform pattern): match
+            # documents where the field exists — as opensearch.ts already
+            # does for every key — instead of a literal, near-always-empty
+            # term match on the string "*".
+            _validate_filter(key, value)
+            filter_clauses.append({"exists": {"field": f"payload.{key}"}})
+            continue
+        if key not in _IDENTITY_FILTER_KEYS and not isinstance(value, (str, int, float, bool)):
+            logger.debug(f"Ignoring non-scalar filter value for key {key!r}")
+            continue
+        _validate_filter(key, value)
+        field = f"payload.{key}.keyword" if isinstance(value, str) else f"payload.{key}"
+        filter_clauses.append({"term": {field: value}})
+    return filter_clauses
+
+
 class OutputData(BaseModel):
    id: str
    score: float
@@ -204,13 +228,7 @@ class OpenSearchDB(VectorStoreBase):
        query_body = {"size": top_k * 2, "query": None}

        # Prepare filter conditions if applicable
-        filter_clauses = []
-        if filters:
-            for key in ["user_id", "run_id", "agent_id"]:
-                value = filters.get(key)
-                if value:
-                    _validate_filter(key, value)
-                    filter_clauses.append({"term": {f"payload.{key}.keyword": value}})
+        filter_clauses = _build_filter_clauses(filters)

        # Combine knn with filters if needed
        if filter_clauses:
@@ -230,7 +248,7 @@ class OpenSearchDB(VectorStoreBase):
            return results
        except Exception as e:
            logger.error(f"Error during search: {e}", exc_info=True)
-            return []
+            raise

    def keyword_search(self, query, top_k=5, filters=None):
        """Search for memories using BM25 keyword matching.
@@ -255,13 +273,7 @@ class OpenSearchDB(VectorStoreBase):
        }

        # Apply filters consistently with the existing search() method
-        filter_clauses = []
-        if filters:
-            for key in ["user_id", "run_id", "agent_id"]:
-                value = filters.get(key)
-                if value:
-                    _validate_filter(key, value)
-                    filter_clauses.append({"term": {f"payload.{key}.keyword": value}})
+        filter_clauses = _build_filter_clauses(filters)

        if filter_clauses:
            bool_query["filter"] = filter_clauses
@@ -281,8 +293,12 @@ class OpenSearchDB(VectorStoreBase):
            ]
            return results
        except Exception as e:
-            logger.error(f"Error during keyword search: {e}")
-            return []
+            # Do NOT re-raise here: keyword_search() is a best-effort helper that
+            # search() may call to augment semantic results. Raising would crash
+            # the whole search() call on a keyword-only failure (regression per
+            # maintainer review on #6519). Log with exc_info and degrade to None.
+            logger.error(f"Error during keyword search: {e}", exc_info=True)
+            return None

    def delete(self, vector_id: str) -> None:
        """Delete a vector by custom ID."""
@@ -370,13 +386,7 @@ class OpenSearchDB(VectorStoreBase):
            """List all memories with optional filters."""
            query: Dict = {"query": {"match_all": {}}}

-            filter_clauses = []
-            if filters:
-                for key in ["user_id", "run_id", "agent_id"]:
-                    value = filters.get(key)
-                    if value:
-                        _validate_filter(key, value)
-                        filter_clauses.append({"term": {f"payload.{key}.keyword": value}})
+            filter_clauses = _build_filter_clauses(filters)

            if filter_clauses:
                query["query"] = {"bool": {"filter": filter_clauses}}
@@ -0,0 +1,592 @@
+"""Oracle AI Vector Search vector store integration for mem0."""
+
+import array
+import json
+import logging
+import math
+import re
+import uuid
+from contextlib import contextmanager
+from typing import Any, Dict, List, Optional
+
+try:
+    import oracledb
+except ImportError as exc:  # pragma: no cover - dependency guard
+    raise ImportError("Oracle AI Vector Search requires the 'oracledb' package.") from exc
+
+from pydantic import BaseModel
+
+from mem0.configs.vector_stores.oracledb import OracleAIVectorSearchConfig
+from mem0.vector_stores.base import VectorStoreBase
+
+logger = logging.getLogger(__name__)
+
+
+class OutputData(BaseModel):
+    """Standard output structure returned from vector operations."""
+
+    id: Optional[str]
+    score: Optional[float]
+    payload: Optional[Dict[str, Any]]
+
+
+# Allow letters, digits, underscore, dot, brackets, comma, *, space (for 'to')
+METADATA_PATTERN = re.compile(r"[a-zA-Z0-9_\.\[\],\s\*]+")
+
+
+def _validate_metadata_key(metadata_key: str) -> None:
+    if not METADATA_PATTERN.fullmatch(metadata_key):
+        raise ValueError(
+            f"Invalid metadata key '{metadata_key}'. "
+            "Only letters, numbers, underscores, nesting via '.', "
+            "and array wildcards '[*]' are allowed."
+        )
+
+
+_SCORE_FROM_DISTANCE = {
+    "COSINE": lambda d: max(0.0, min(1.0, 1.0 - d)),
+    "EUCLIDEAN": lambda d: 1.0 / (1.0 + max(0.0, d)),
+    "EUCLIDEAN_SQUARED": lambda d: 1.0 / (1.0 + math.sqrt(max(0.0, d))),
+    "HAMMING": lambda d: 1.0 / (1.0 + max(0.0, d)),
+    "MANHATTAN": lambda d: 1.0 / (1.0 + max(0.0, d)),
+    "DOT": lambda d: -d,
+}
+
+
+def _convert_distance_to_score(distance: float, metric: str) -> float:
+    try:
+        return _SCORE_FROM_DISTANCE[metric.upper()](distance)
+    except KeyError:
+        raise ValueError(f"Unsupported distance metric: {metric}") from None
+
+
+_FIELD_OPERATORS = {"eq", "ne", "gt", "gte", "lt", "lte", "in", "nin", "contains", "icontains"}
+_COMPARISON_OPERATORS = {
+    "eq": "==",
+    "ne": "!=",
+    "gt": ">",
+    "gte": ">=",
+    "lt": "<",
+    "lte": "<=",
+}
+_LOGICAL_OPERATORS = {
+    "$and": "and",
+    "$or": "or",
+    "$not": "not",
+    "AND": "and",
+    "OR": "or",
+    "NOT": "not",
+}
+
+
+def _json_path(metadata_key: str) -> str:
+    _validate_metadata_key(metadata_key)
+
+    path_parts: List[str] = []
+    for part in metadata_key.split("."):
+        if part.endswith("[*]"):
+            path_parts.append(f'."{part[:-3]}"[*]')
+        else:
+            path_parts.append(f'."{part}"')
+    return "".join(path_parts)
+
+
+def _bind_filter_value(value: Any, params: Dict[str, Any]) -> tuple[str, str]:
+    param = f"f_{len(params)}"
+    params[param] = value
+    return f"${param}", f':{param} AS "{param}"'
+
+
+def _json_exists(json_path: str, predicate: str, passings: List[str]) -> str:
+    passing_clause = f" PASSING {', '.join(passings)}" if passings else ""
+    return f"JSON_EXISTS(payload, '${json_path}?({predicate})'{passing_clause})"
+
+
+def _validate_scalar_operand(operator: str, value: Any) -> None:
+    if isinstance(value, (dict, list, tuple, set)):
+        raise ValueError(f"Oracle filter operator {operator!r} requires a scalar value")
+
+
+def _build_field_condition(metadata_key: str, value: Any, params: Dict[str, Any]) -> str:
+    json_path = _json_path(metadata_key)
+
+    if value == "*":
+        return f"JSON_EXISTS(payload, '${json_path}')"
+
+    if not isinstance(value, dict):
+        _validate_scalar_operand("eq", value)
+        if value is None:
+            return _json_exists(json_path, "@ == null", [])
+        variable, passing = _bind_filter_value(value, params)
+        return _json_exists(json_path, f"@ == {variable}", [passing])
+
+    if not value:
+        raise ValueError(f"Operator filter for field {metadata_key!r} must not be empty")
+
+    unsupported = set(value) - _FIELD_OPERATORS
+    if unsupported:
+        raise ValueError(
+            f"Unsupported Oracle filter operator(s) for field {metadata_key!r}: "
+            f"{', '.join(sorted(map(str, unsupported)))}"
+        )
+
+    predicates: List[str] = []
+    passings: List[str] = []
+    additional_clauses: List[str] = []
+
+    for operator, operand in value.items():
+        if operator in _COMPARISON_OPERATORS:
+            _validate_scalar_operand(operator, operand)
+            if operand is None:
+                if operator not in {"eq", "ne"}:
+                    raise ValueError(f"Oracle filter operator {operator!r} does not support null")
+                predicates.append(f"@ {_COMPARISON_OPERATORS[operator]} null")
+                continue
+            variable, passing = _bind_filter_value(operand, params)
+            predicates.append(f"@ {_COMPARISON_OPERATORS[operator]} {variable}")
+            passings.append(passing)
+            continue
+
+        if operator in {"in", "nin"}:
+            if not isinstance(operand, (list, tuple)) or not operand:
+                raise ValueError(f"Oracle filter operator {operator!r} requires a non-empty list")
+
+            variables: List[str] = []
+            list_passings: List[str] = []
+            for item in operand:
+                _validate_scalar_operand(operator, item)
+                if item is None:
+                    variables.append("null")
+                    continue
+                variable, passing = _bind_filter_value(item, params)
+                variables.append(variable)
+                list_passings.append(passing)
+
+            membership = _json_exists(json_path, f"@ in ({', '.join(variables)})", list_passings)
+            if operator == "in":
+                additional_clauses.append(membership)
+            else:
+                additional_clauses.append(f"NOT ({membership})")
+            continue
+
+        if not isinstance(operand, str):
+            raise ValueError(f"Oracle filter operator {operator!r} requires a string value")
+
+        if operator == "contains":
+            variable, passing = _bind_filter_value(operand, params)
+            predicates.append(f"@ has substring {variable}")
+            passings.append(passing)
+        else:
+            variable, passing = _bind_filter_value(operand.lower(), params)
+            predicates.append(f"@.lower() has substring {variable}")
+            passings.append(passing)
+
+    clauses = list(additional_clauses)
+    if predicates:
+        clauses.insert(0, _json_exists(json_path, " && ".join(predicates), passings))
+
+    if len(clauses) == 1:
+        return clauses[0]
+    return "(" + " AND ".join(clauses) + ")"
+
+
+def _build_filter_group(filters: Dict[str, Any], params: Dict[str, Any]) -> str:
+    if not isinstance(filters, dict) or not filters:
+        raise ValueError("Oracle filter groups must be non-empty dictionaries")
+
+    clauses: List[str] = []
+    for key, value in filters.items():
+        if key in _LOGICAL_OPERATORS:
+            if not isinstance(value, list) or not value:
+                raise ValueError(f"Logical filter operator {key!r} requires a non-empty list")
+
+            nested = [_build_filter_group(condition, params) for condition in value]
+            logical_operator = _LOGICAL_OPERATORS[key]
+            if logical_operator == "not":
+                clauses.append(f"NOT ({' OR '.join(nested)})")
+            else:
+                joiner = " AND " if logical_operator == "and" else " OR "
+                clauses.append("(" + joiner.join(nested) + ")")
+            continue
+
+        if key.startswith("$"):
+            raise ValueError(f"Unsupported Oracle logical filter operator: {key}")
+
+        clauses.append(_build_field_condition(key, value, params))
+
+    if len(clauses) == 1:
+        return clauses[0]
+    return "(" + " AND ".join(clauses) + ")"
+
+
+class OracleAIVectorSearch(VectorStoreBase):
+    """Oracle AI Vector Search backend for mem0."""
+
+    def __init__(self, **kwargs: Any) -> None:
+        self.config = OracleAIVectorSearchConfig(**kwargs)
+        self.collection_name = self.config.collection_name
+
+        if self.config.client:
+            logger.debug("Using Oracle connection pool: %s", self.config.client)
+            self.client = self.config.client
+            self._owns_client = False
+        elif self.config.use_connection_pool:
+            pool_kwargs = {
+                "min": 1,
+                "max": 4,
+            }
+            pool_kwargs.update(self.config.connection_params)
+
+            logger.debug("Creating Oracle connection pool")
+            self.client = oracledb.create_pool(**pool_kwargs)
+            self._owns_client = True
+        else:
+            logger.debug("Creating Oracle connection")
+            self.client = oracledb.connect(**self.config.connection_params)
+            self._owns_client = True
+
+        if not (hasattr(self.client, "thin") and self.client.thin):
+            if oracledb.clientversion()[:2] < (23, 4):
+                raise RuntimeError(
+                    f"Oracle DB client driver version {'.'.join(map(str, oracledb.clientversion()))} "
+                    "not supported, must be >=23.4 for vector support"
+                )
+
+        if isinstance(self.client, oracledb.Connection):
+            db_version = tuple([int(v) for v in self.client.version.split(".")])
+        else:
+            with self.client.acquire() as conn:
+                db_version = tuple([int(v) for v in conn.version.split(".")])
+
+        if db_version < (23, 4):
+            raise ValueError(
+                f"Oracle DB version {'.'.join(map(str, db_version))} not supported, must be >=23.4 for vector support"
+            )
+
+        self.create_col()
+
+    @contextmanager
+    def _get_cursor(self, commit: bool = False):
+        if isinstance(self.client, oracledb.ConnectionPool):
+            with self.client.acquire() as connection:
+                with connection.cursor() as cursor:
+                    try:
+                        yield cursor
+                        if commit:
+                            connection.commit()
+                    except Exception:
+                        connection.rollback()
+                        raise
+        else:
+            with self.client.cursor() as cursor:
+                try:
+                    yield cursor
+                    if commit:
+                        self.client.commit()
+                except Exception:
+                    self.client.rollback()
+                    raise
+
+    # Utility helpers --------------------------------------------------
+    @staticmethod
+    def _load_payload(value: Any) -> Dict[str, Any]:
+        if value is None:
+            return {}
+        if isinstance(value, dict):
+            return value
+        if hasattr(value, "read"):
+            value = value.read()
+        if isinstance(value, bytes):
+            value = value.decode("utf-8")
+        try:
+            return json.loads(value)
+        except json.JSONDecodeError:
+            logger.debug("Failed to decode payload JSON")
+            raise
+
+    @staticmethod
+    def _catalog_name(name: str) -> str:
+        return name.replace('"', "")
+
+    def _create_index_ddl(self) -> str:
+        accuracy_str = ""
+        if self.config.index_accuracy:
+            accuracy_str = f"WITH TARGET ACCURACY {self.config.index_accuracy}"
+
+        parameters = self._index_parameters()
+        parameters_str = f"PARAMETERS ({parameters})" if parameters else ""
+
+        distance_metric = self.config.distance_metric
+
+        create_index = (
+            f"CREATE VECTOR INDEX IF NOT EXISTS {self.config.index_name} ON {self.collection_name} (vector) "
+            f"ORGANIZATION {'INMEMORY NEIGHBOR GRAPH' if self.config.index_type == 'HNSW' else 'NEIGHBOR PARTITIONS'}"
+            f" DISTANCE {distance_metric} {accuracy_str} {parameters_str}"
+        )
+
+        return create_index
+
+    def _index_parameters(self) -> str:
+        index_parameters = self.config.index_parameters
+        if not index_parameters:
+            return ""
+
+        parameters = [f"type {self.config.index_type}"]
+        parameters.extend(f"{key} {value}" for key, value in index_parameters.items())
+
+        return ", ".join(parameters)
+
+    # Vector store API -------------------------------------------------
+    def create_col(self) -> None:
+        """
+        Create a new collection (table in Oracle).
+        Will also initialize vector search index if specified.
+        """
+        with self._get_cursor(commit=True) as cursor:
+            cursor.execute(
+                f"""
+                CREATE TABLE IF NOT EXISTS {self.collection_name} (
+                    id VARCHAR2(36) PRIMARY KEY,
+                    vector VECTOR({self.config.embedding_model_dims}),
+                    payload JSON
+                )
+                """
+            )
+
+            if self.config.do_create_index:
+                ddl = self._create_index_ddl()
+                cursor.execute(ddl)
+
+    def insert(
+        self,
+        vectors: List[List[float]],
+        payloads: Optional[List[Dict[str, Any]]] = None,
+        ids: Optional[List[str]] = None,
+    ) -> None:
+        logger.info(f"Inserting {len(vectors)} vectors into collection {self.collection_name}")
+
+        if payloads is not None and len(payloads) != len(vectors):
+            raise ValueError(f"Payload count must match vector count. Expected {len(vectors)} got {len(payloads)}.")
+        if ids is not None and len(ids) != len(vectors):
+            raise ValueError(f"ID count must match vector count. Expected {len(vectors)} got {len(ids)}.")
+
+        ids = ids or [str(uuid.uuid4()) for _ in vectors]
+        data = [
+            {"id": _id, "vector": array.array("f", vector), "payload": payload}
+            for vector, payload, _id in zip(vectors, payloads or [{}] * len(vectors), ids)
+        ]
+
+        with self._get_cursor(commit=True) as cursor:
+            cursor.setinputsizes(
+                vector=oracledb.DB_TYPE_VECTOR,
+                payload=oracledb.DB_TYPE_JSON,
+            )
+            cursor.executemany(
+                f"INSERT INTO {self.collection_name} (id, vector, payload) VALUES (:id, :vector, :payload)", data
+            )
+
+    def search(
+        self,
+        query: str,
+        vectors: List[float],
+        top_k: int = 5,
+        filters: Optional[Dict[str, Any]] = None,
+    ) -> List[OutputData]:
+        """
+        Search for similar vectors using the vector search index.
+
+        Args:
+            query (str): Query string
+            vectors (List[float]): Query vector.
+            top_k (int, optional): Number of results to return. Defaults to 5.
+            filters (Dict, optional): Filters to apply to the search.
+
+        Returns:
+            List[OutputData]: Search results.
+        """
+        filter_clause, params = self._build_filters(filters)
+
+        distance_metric = self.config.distance_metric
+
+        sql = (
+            f"SELECT id, payload, VECTOR_DISTANCE(vector, :query_vec, {distance_metric}) distance "
+            f"FROM {self.collection_name} {filter_clause} ORDER BY distance FETCH APPROX FIRST :limit ROWS ONLY"
+        )
+
+        with self._get_cursor() as cursor:
+            cursor.execute(sql, query_vec=array.array("f", vectors), limit=top_k, **params)
+            rows = cursor.fetchall()
+
+        return [
+            OutputData(
+                id=row[0],
+                payload=self._load_payload(row[1]),
+                score=_convert_distance_to_score(float(row[2]), distance_metric),
+            )
+            for row in rows
+        ]
+
+    def _build_filters(self, filters: Optional[Dict[str, Any]]) -> tuple[str, Dict[str, Any]]:
+        if not filters:
+            return "", {}
+
+        params: Dict[str, Any] = {}
+        return "WHERE " + _build_filter_group(filters, params), params
+
+    def delete(self, vector_id: str) -> None:
+        """
+        Delete a vector by ID.
+
+        Args:
+            vector_id (str): ID of the vector to delete.
+        """
+        with self._get_cursor(commit=True) as cursor:
+            cursor.execute(f"DELETE FROM {self.collection_name} WHERE id = :id", id=vector_id)
+
+    def update(
+        self,
+        vector_id: str,
+        vector: Optional[List[float]] = None,
+        payload: Optional[Dict[str, Any]] = None,
+    ) -> None:
+        """
+        Update a vector and its payload.
+
+        Args:
+            vector_id (str): ID of the vector to update.
+            vector (List[float], optional): Updated vector.
+            payload (Dict, optional): Updated payload.
+        """
+        if vector is None and payload is None:
+            return
+
+        with self._get_cursor(commit=True) as cursor:
+            sets, params = [], {"vector_id": vector_id}
+            if vector is not None:
+                sets.append("vector = :vector")
+                params["vector"] = array.array("f", vector)
+                cursor.setinputsizes(vector=oracledb.DB_TYPE_VECTOR)
+            if payload is not None:
+                sets.append("payload = :payload")
+                params["payload"] = payload
+                cursor.setinputsizes(payload=oracledb.DB_TYPE_JSON)
+            cursor.execute(f"UPDATE {self.collection_name} SET {', '.join(sets)} WHERE id = :vector_id", params)
+
+    def get(self, vector_id: str) -> Optional[OutputData]:
+        """
+        Retrieve a vector by ID.
+
+        Args:
+            vector_id (str): ID of the vector to retrieve.
+
+        Returns:
+            OutputData: Retrieved vector.
+        """
+        with self._get_cursor() as cursor:
+            cursor.execute(
+                f"SELECT id, payload FROM {self.collection_name} WHERE id = :vector_id",
+                vector_id=vector_id,
+            )
+            row = cursor.fetchone()
+        if row is None:
+            return None
+        return OutputData(id=row[0], score=None, payload=self._load_payload(row[1]))
+
+    def list_cols(self) -> List[str]:
+        """
+        List all collections.
+
+        Returns:
+            List[str]: List of collection names.
+        """
+        with self._get_cursor() as cursor:
+            cursor.execute("SELECT table_name FROM user_tables")
+            tables = [row[0] for row in cursor.fetchall()]
+        return tables
+
+    def delete_col(self) -> None:
+        """Delete a collection."""
+        with self._get_cursor(commit=True) as cursor:
+            cursor.execute(f"DROP TABLE {self.collection_name} PURGE")
+
+    def col_info(self) -> Dict[str, Any]:
+        """
+        Get information about a collection.
+
+        Returns:
+            Dict[str, Any]: Collection information.
+        """
+        owner, table_name = self._split_collection_name()
+
+        sql = f"""
+        SELECT
+            table_name,
+            (SELECT COUNT(*) FROM {self.collection_name}) AS row_count,
+            (SELECT
+                ROUND(SUM(bytes) / 1024 / 1024, 2) || ' MB'
+            FROM user_segments
+            WHERE segment_name = :table_name
+            AND segment_type = 'TABLE'
+            ) AS total_size
+        FROM all_tables
+        WHERE table_name = :table_name
+        AND owner = NVL(:owner, USER)
+        """
+
+        with self._get_cursor() as cursor:
+            cursor.execute(sql, table_name=table_name, owner=owner)
+            result = cursor.fetchone()
+
+        if result is None:
+            raise ValueError(f"Collection {self.collection_name} not found")
+
+        return {"name": result[0], "count": result[1], "size": result[2]}
+
+    def _split_collection_name(self) -> tuple[Optional[str], str]:
+        """Split the quoted collection name into its optional owner and table parts."""
+        segments = re.findall(r'"([^"]+)"', self.collection_name)
+        if len(segments) > 1:
+            return segments[-2], segments[-1]
+        return None, segments[-1]
+
+    def list(self, filters: Optional[Dict[str, Any]] = None, top_k: Optional[int] = 100) -> List[List[OutputData]]:
+        """
+        List all vectors in a collection.
+
+        Args:
+            filters (Dict, optional): Filters to apply to the list.
+            top_k (int, optional): Number of vectors to return. Defaults to 100.
+
+        Returns:
+            List[List[OutputData]]: A single-element list holding the list of vectors.
+        """
+        filter_clause, params = self._build_filters(filters)
+
+        limit_clause = ""
+        if top_k is not None:
+            limit_clause = " FETCH FIRST :limit ROWS ONLY"
+            params["limit"] = top_k
+
+        sql = f"SELECT id, payload FROM {self.collection_name} {filter_clause} {limit_clause}"
+
+        with self._get_cursor() as cursor:
+            cursor.execute(sql, **params)
+            rows = cursor.fetchall()
+
+        return [[OutputData(id=row[0], score=None, payload=self._load_payload(row[1])) for row in rows]]
+
+    def reset(self) -> None:
+        """Reset the index by deleting and recreating it."""
+        logger.warning("Resetting collection %s", self.collection_name)
+        self.delete_col()
+        self.create_col()
+
+    def __del__(self) -> None:
+        """
+        Close the database connection pool when the object is deleted.
+        """
+        try:
+            if getattr(self, "_owns_client", False):
+                self.client.close()
+        except Exception:
+            pass
@@ -459,13 +459,13 @@ class PGVector(VectorStoreBase):
        self._ensure_collection()
        with self._get_cursor() as cur:
            cur.execute(
-                sql.SQL("SELECT id, vector, payload FROM {} WHERE id = %s").format(self._col()),
+                sql.SQL("SELECT id, payload FROM {} WHERE id = %s").format(self._col()),
                (vector_id,),
            )
            result = cur.fetchone()
            if not result:
                return None
-            return OutputData(id=str(result[0]), score=None, payload=result[2])
+            return OutputData(id=str(result[0]), score=None, payload=result[1])

    def list_cols(self) -> List[str]:
        """
@@ -528,7 +528,7 @@ class PGVector(VectorStoreBase):
        with self._get_cursor() as cur:
            cur.execute(
                sql.SQL("""
-                SELECT id, vector, payload
+                SELECT id, payload
                FROM {}
                {}
                LIMIT %s
@@ -536,7 +536,7 @@ class PGVector(VectorStoreBase):
                (*filter_params, top_k),
            )
            results = cur.fetchall()
-        return [[OutputData(id=str(r[0]), score=None, payload=r[2]) for r in results]]
+        return [[OutputData(id=str(r[0]), score=None, payload=r[1]) for r in results]]

    def __del__(self) -> None:
        """
@@ -1,14 +0,0 @@
-*.db
-.env*
-!.env.example
-!.env.dev
-!ui/lib
-.venv/
-__pycache__
-.DS_Store
-node_modules/
-*.log
-api/.openmemory*
-**/.next
-.openmemory/
-ui/package-lock.json
@@ -1,70 +0,0 @@
-# Contributing to OpenMemory
-
-We are a team of developers passionate about the future of AI and open-source software. With years of experience in both fields, we believe in the power of community-driven development and are excited to build tools that make AI more accessible and personalized.
-
-## Ways to Contribute
-
-We welcome all forms of contributions:
- Bug reports and feature requests through GitHub Issues
- Documentation improvements
- Code contributions
- Testing and feedback
- Community support and discussions
-
-## Development Workflow
-
-1. Fork the repository
-2. Create your feature branch (`git checkout -b openmemory/feature/amazing-feature`)
-3. Commit your changes (`git commit -m 'Add some amazing feature'`)
-4. Push to the branch (`git push origin openmemory/feature/amazing-feature`)
-5. Open a Pull Request
-
-## Development Setup
-
-### Backend Setup
-
-```bash
-# Copy environment file and edit file to update OPENAI_API_KEY and other secrets
-make env
-
-# Build the containers
-make build
-
-# Start the services
-make up
-```
-
-### Frontend Setup
-
-The frontend is a React application. To start the frontend:
-
-```bash
-# Install dependencies and start the development server
-make ui-dev
-```
-
-### Prerequisites
- Docker and Docker Compose
- Python 3.9+ (for backend development)
- Node.js (for frontend development)
- OpenAI API Key (for LLM interactions)
-
-### Getting Started
-Follow the setup instructions in the README.md file to set up your development environment.
-
-## Code Standards
-
-We value:
- Clean, well-documented code
- Thoughtful discussions about features and improvements
- Respectful and constructive feedback
- A welcoming environment for all contributors
-
-## Pull Request Process
-
-1. Ensure your code follows the project's coding standards
-2. Update documentation as needed
-3. Include tests for new features
-4. Make sure all tests pass before submitting
-
-Join us in building the future of AI memory management! Your contributions help make OpenMemory better for everyone.
@@ -1,52 +0,0 @@
-.PHONY: help up down logs shell migrate test test-clean env ui-install ui-start ui-dev ui-build ui-dev-start
-
-NEXT_PUBLIC_USER_ID=$(USER)
-NEXT_PUBLIC_API_URL=http://localhost:8765
-
-# Default target
-help:
-	@echo "Available commands:"
-	@echo "  make env       - Copy .env.example to .env"
-	@echo "  make up        - Start the containers"
-	@echo "  make down      - Stop the containers"
-	@echo "  make logs      - Show container logs"
-	@echo "  make shell     - Open a shell in the api container"
-	@echo "  make migrate   - Run database migrations"
-	@echo "  make test      - Run tests in a new container"
-	@echo "  make test-clean - Run tests and clean up volumes"
-	@echo "  make ui-install - Install frontend dependencies"
-	@echo "  make ui-start  - Start the frontend development server"
-	@echo "  make ui-dev    - Install dependencies and start the frontend in dev mode"
-	@echo "  make ui        - Install dependencies and start the frontend in production mode"
-
-env:
-	cd api && cp .env.example .env
-	cd ui && cp .env.example .env
-
-build:
-	docker compose build
-
-up:
-	NEXT_PUBLIC_USER_ID=$(USER) NEXT_PUBLIC_API_URL=$(NEXT_PUBLIC_API_URL) docker compose up
-
-down:
-	docker compose down -v
-	rm -f api/openmemory.db
-
-logs:
-	docker compose logs -f
-
-shell:
-	docker compose exec api bash
-
-upgrade:
-	docker compose exec api alembic upgrade head
-
-migrate:
-	docker compose exec api alembic upgrade head
-
-downgrade:
-	docker compose exec api alembic downgrade -1
-
-ui-dev:
-	cd ui && NEXT_PUBLIC_USER_ID=$(USER) NEXT_PUBLIC_API_URL=$(NEXT_PUBLIC_API_URL) pnpm install && pnpm dev
@@ -1,168 +0,0 @@
-# OpenMemory
-
-> **⚠️ Sunsetting Notice:** OpenMemory is being sunset. For local self-hosted memory with a dashboard, please use the [Mem0 self-hosted server](https://docs.mem0.ai/open-source/overview) instead. Get started with `cd server && make bootstrap`. See the [self-hosted docs](https://docs.mem0.ai/open-source/setup) for configuration details.
-
-OpenMemory is your personal memory layer for LLMs - private, portable, and open-source. Your memories live locally, giving you complete control over your data. Build AI applications with personalized memories while keeping your data secure.
-
-![OpenMemory](https://github.com/user-attachments/assets/3c701757-ad82-4afa-bfbe-e049c2b4320b)
-
-## Easy Setup
-
-### Prerequisites
- Docker
- OpenAI API Key
-
-You can quickly run OpenMemory by running the following command:
-
-```bash
-curl -sL https://raw.githubusercontent.com/mem0ai/mem0/main/openmemory/run.sh | bash
-```
-
-You should set the `OPENAI_API_KEY` as a global environment variable:
-
-```bash
-export OPENAI_API_KEY=your_api_key
-```
-
-You can also set the `OPENAI_API_KEY` as a parameter to the script:
-
-```bash
-curl -sL https://raw.githubusercontent.com/mem0ai/mem0/main/openmemory/run.sh | OPENAI_API_KEY=your_api_key bash
-```
-
-## Prerequisites
-
- Docker and Docker Compose
- Python 3.9+ (for backend development)
- Node.js (for frontend development)
- OpenAI API Key (required for LLM interactions, run `cp api/.env.example api/.env` then change **OPENAI_API_KEY** to yours)
-
-## Quickstart
-
-### 1. Set Up Environment Variables
-
-Before running the project, you need to configure environment variables for both the API and the UI.
-
-You can do this in one of the following ways:
-
- **Manually**:  
-  Create a `.env` file in each of the following directories:
-  - `/api/.env`
-  - `/ui/.env`
-
- **Using `.env.example` files**:  
-  Copy and rename the example files:
-
-  ```bash
-  cp api/.env.example api/.env
-  cp ui/.env.example ui/.env
-  ```
-
- - **Using Makefile** (if supported):  
-    Run:
-  
-   ```bash
-   make env
-   ```
- #### Example `/api/.env`
-
-```env
-OPENAI_API_KEY=sk-xxx
-USER=<user-id> # The User Id you want to associate the memories with
-```
-
- #### LLM Configuration (optional)
-
-By default, OpenMemory uses OpenAI (`gpt-4o-mini`) for the LLM and embedder. You can configure a different provider using these environment variables in `/api/.env`:
-
-| Variable | Description | Default |
-|---|---|---|
-| `LLM_PROVIDER` | LLM provider (`openai`, `ollama`, `anthropic`, `groq`, `together`, `deepseek`, etc.) | `openai` |
-| `LLM_MODEL` | Model name for the LLM provider | `gpt-4o-mini` (OpenAI) / `llama3.1:latest` (Ollama) |
-| `LLM_API_KEY` | API key for the LLM provider | `OPENAI_API_KEY` env var |
-| `LLM_BASE_URL` | Custom base URL for the LLM API | Provider default |
-| `OLLAMA_BASE_URL` | Ollama-specific base URL (takes precedence over `LLM_BASE_URL` for Ollama) | `http://localhost:11434` |
-| `EMBEDDER_PROVIDER` | Embedder provider (defaults to `ollama` when LLM is Ollama, otherwise `openai`) | `openai` |
-| `EMBEDDER_MODEL` | Model name for the embedder | `text-embedding-3-small` (OpenAI) / `nomic-embed-text` (Ollama) |
-| `EMBEDDER_API_KEY` | API key for the embedder provider | `OPENAI_API_KEY` env var |
-| `EMBEDDER_BASE_URL` | Custom base URL for the embedder API | Provider default |
-
-**Example: Using Ollama (fully local)**
-```env
-LLM_PROVIDER=ollama
-LLM_MODEL=llama3.1:latest
-EMBEDDER_PROVIDER=ollama
-EMBEDDER_MODEL=nomic-embed-text
-OLLAMA_BASE_URL=http://localhost:11434
-```
-
-**Example: Using Anthropic**
-```env
-LLM_PROVIDER=anthropic
-LLM_MODEL=claude-sonnet-4-20250514
-LLM_API_KEY=sk-ant-xxx
-```
- #### Example `/ui/.env`
-
-```env
-NEXT_PUBLIC_API_URL=http://localhost:8765
-NEXT_PUBLIC_USER_ID=<user-id> # Same as the user id for environment variable in api
-```
-
-### 2. Build and Run the Project
-You can run the project using the following two commands:
-```bash
-make build # builds the mcp server and ui
-make up  # runs openmemory mcp server and ui
-```
-
-After running these commands, you will have:
- OpenMemory MCP server running at: http://localhost:8765 (API documentation available at http://localhost:8765/docs)
- OpenMemory UI running at: http://localhost:3000
-
-#### UI not working on `localhost:3000`?
-
-If the UI does not start properly on [http://localhost:3000](http://localhost:3000), try running it manually:
-
-```bash
-cd ui
-pnpm install
-pnpm dev
-```
-
-### MCP Client Setup
-
-Use the following one step command to configure OpenMemory Local MCP to a client. The general command format is as follows:
-
-```bash
-npx @openmemory/install local http://localhost:8765/mcp/<client-name>/sse/<user-id> --client <client-name>
-```
-
-Replace `<client-name>` with the desired client name and `<user-id>` with the value specified in your environment variables.
-
-
-## Project Structure
-
- `api/` - Backend APIs + MCP server
- `ui/` - Frontend React application
-
-## Contributing
-
-We are a team of developers passionate about the future of AI and open-source software. With years of experience in both fields, we believe in the power of community-driven development and are excited to build tools that make AI more accessible and personalized.
-
-We welcome all forms of contributions:
- Bug reports and feature requests
- Documentation improvements
- Code contributions
- Testing and feedback
- Community support
-
-How to contribute:
-
-1. Fork the repository
-2. Create your feature branch (`git checkout -b openmemory/feature/amazing-feature`)
-3. Commit your changes (`git commit -m 'Add some amazing feature'`)
-4. Push to the branch (`git push origin openmemory/feature/amazing-feature`)
-5. Open a Pull Request
-
-Join us in building the future of AI memory management! Your contributions help make OpenMemory better for everyone.
@@ -1,23 +0,0 @@
-# Ignore all .env files
-**/.env
-**/.env.*
-
-# Ignore all database files
-**/*.db
-**/*.sqlite
-**/*.sqlite3
-
-# Ignore logs
-**/*.log
-
-# Ignore runtime data
-**/node_modules
-**/__pycache__
-**/.pytest_cache
-**/.coverage
-**/coverage
-
-# Ignore Docker runtime files
-**/.dockerignore
-**/Dockerfile
-**/docker-compose*.yml 
@@ -1,15 +0,0 @@
-OPENAI_API_KEY=sk-xxx
-USER=user
-
-# LLM Configuration (optional - defaults to openai/gpt-4o-mini)
-# LLM_PROVIDER=ollama
-# LLM_MODEL=llama3.1:latest
-# LLM_API_KEY=
-# LLM_BASE_URL=
-# OLLAMA_BASE_URL=http://localhost:11434
-
-# Embedder Configuration (optional - defaults to openai/text-embedding-3-small)
-# EMBEDDER_PROVIDER=ollama
-# EMBEDDER_MODEL=nomic-embed-text
-# EMBEDDER_API_KEY=
-# EMBEDDER_BASE_URL=
@@ -1 +0,0 @@
-3.12
@@ -1,14 +0,0 @@
-FROM python:3.12-slim
-
-LABEL org.opencontainers.image.name="mem0/openmemory-mcp"
-
-WORKDIR /usr/src/openmemory
-
-COPY requirements.txt .
-RUN pip install -r requirements.txt
-
-COPY config.json .
-COPY . .
-
-EXPOSE 8765
-CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8765"]
@@ -1,60 +0,0 @@
-# OpenMemory API
-
-This directory contains the backend API for OpenMemory, built with FastAPI and SQLAlchemy. This also runs the Mem0 MCP Server that you can use with MCP clients to remember things.
-
-## Quick Start with Docker (Recommended)
-
-The easiest way to get started is using Docker. Make sure you have Docker and Docker Compose installed.
-
-1. Build the containers:
-```bash
-make build
-```
-
-2. Create `.env` file:
-```bash
-make env
-```
-
-Once you run this command, edit the file `api/.env` and enter the `OPENAI_API_KEY`.
-
-3. Start the services:
-```bash
-make up
-```
-
-The API will be available at `http://localhost:8765`
-
-### Common Docker Commands
-
- View logs: `make logs`
- Open shell in container: `make shell`
- Run database migrations: `make migrate`
- Run tests: `make test`
- Run tests and clean up: `make test-clean`
- Stop containers: `make down`
-
-## API Documentation
-
-Once the server is running, you can access the API documentation at:
- Swagger UI: `http://localhost:8765/docs`
- ReDoc: `http://localhost:8765/redoc`
-
-## Project Structure
-
- `app/`: Main application code
-  - `models.py`: Database models
-  - `database.py`: Database configuration
-  - `routers/`: API route handlers
- `migrations/`: Database migration files
- `tests/`: Test files
- `alembic/`: Alembic migration configuration
- `main.py`: Application entry point
-
-## Development Guidelines
-
- Follow PEP 8 style guide
- Use type hints
- Write tests for new features
- Update documentation when making changes
- Run migrations for database changes
@@ -1,114 +0,0 @@
-# A generic, single database configuration.
-
-[alembic]
-# path to migration scripts
-# Use forward slashes (/) also on windows to provide an os agnostic path
-script_location = alembic
-
-# template used to generate migration file names; The default value is %%(rev)s_%%(slug)s
-# Uncomment the line below if you want the files to be prepended with date and time
-# see https://alembic.sqlalchemy.org/en/latest/tutorial.html#editing-the-ini-file
-# for all available tokens
-# file_template = %%(year)d_%%(month).2d_%%(day).2d_%%(hour).2d%%(minute).2d-%%(rev)s_%%(slug)s
-
-# sys.path path, will be prepended to sys.path if present.
-# defaults to the current working directory.
-prepend_sys_path = .
-
-# timezone to use when rendering the date within the migration file
-# as well as the filename.
-# If specified, requires the python-dateutil library that can be
-# installed by adding `alembic[tz]` to the pip requirements
-# timezone =
-
-# max length of characters to apply to the "slug" field
-# truncate_slug_length = 40
-
-# set to 'true' to run the environment during
-# the 'revision' command, regardless of autogenerate
-# revision_environment = false
-
-# set to 'true' to allow .pyc and .pyo files without
-# a source .py file to be detected as revisions in the
-# versions/ directory
-# sourceless = false
-
-# version location specification; This defaults
-# to alembic/versions.  When using multiple version
-# directories, initial revisions must be specified with --version-path.
-# The path separator used here should be the separator specified by "version_path_separator" below.
-# version_locations = %(here)s/bar:%(here)s/bat:alembic/versions
-
-# version path separator; As mentioned above, this is the character used to split
-# version_locations. The default within new alembic.ini files is "os", which uses os.pathsep.
-# If this key is omitted entirely, it falls back to the legacy behavior of splitting on spaces and/or colons.
-# Valid values for version_path_separator are:
-#
-# version_path_separator = :
-# version_path_separator = ;
-# version_path_separator = space
-version_path_separator = os  # Use os.pathsep. Default configuration used for new projects.
-
-# set to 'true' to search source files recursively
-# in each "version_locations" directory
-# new in Alembic version 1.10
-# recursive_version_locations = false
-
-# the output encoding used when revision files
-# are written from script.py.mako
-# output_encoding = utf-8
-
-sqlalchemy.url = sqlite:///./openmemory.db
-
-
-[post_write_hooks]
-# post_write_hooks defines scripts or Python functions that are run
-# on newly generated revision scripts.  See the documentation for further
-# detail and examples
-
-# format using "black" - use the console_scripts runner, against the "black" entrypoint
-# hooks = black
-# black.type = console_scripts
-# black.entrypoint = black
-# black.options = -l 79 REVISION_SCRIPT_FILENAME
-
-# lint with attempts to fix using "ruff" - use the exec runner, execute a binary
-# hooks = ruff
-# ruff.type = exec
-# ruff.executable = %(here)s/.venv/bin/ruff
-# ruff.options = check --fix REVISION_SCRIPT_FILENAME
-
-# Logging configuration
-[loggers]
-keys = root,sqlalchemy,alembic
-
-[handlers]
-keys = console
-
-[formatters]
-keys = generic
-
-[logger_root]
-level = WARN
-handlers = console
-qualname =
-
-[logger_sqlalchemy]
-level = WARN
-handlers =
-qualname = sqlalchemy.engine
-
-[logger_alembic]
-level = INFO
-handlers =
-qualname = alembic
-
-[handler_console]
-class = StreamHandler
-args = (sys.stderr,)
-level = NOTSET
-formatter = generic
-
-[formatter_generic]
-format = %(levelname)-5.5s [%(name)s] %(message)s
-datefmt = %H:%M:%S
@@ -1 +0,0 @@
-Generic single-database configuration.
@@ -1,88 +0,0 @@
-import os
-import sys
-from logging.config import fileConfig
-
-from alembic import context
-from dotenv import load_dotenv
-from sqlalchemy import engine_from_config, pool
-
-# Add the parent directory to the Python path
-sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-
-# Load environment variables
-load_dotenv()
-
-# Import your models here - moved after path setup
-from app.database import Base  # noqa: E402
-
-# this is the Alembic Config object, which provides
-# access to the values within the .ini file in use.
-config = context.config
-
-# Interpret the config file for Python logging.
-# This line sets up loggers basically.
-if config.config_file_name is not None:
-    fileConfig(config.config_file_name)
-
-# add your model's MetaData object here
-# for 'autogenerate' support
-target_metadata = Base.metadata
-
-# other values from the config, defined by the needs of env.py,
-# can be acquired:
-# my_important_option = config.get_main_option("my_important_option")
-# ... etc.
-
-
-def run_migrations_offline() -> None:
-    """Run migrations in 'offline' mode.
-
-    This configures the context with just a URL
-    and not an Engine, though an Engine is acceptable
-    here as well.  By skipping the Engine creation
-    we don't even need a DBAPI to be available.
-
-    Calls to context.execute() here emit the given string to the
-    script output.
-
-    """
-    url = os.getenv("DATABASE_URL", "sqlite:///./openmemory.db")
-    context.configure(
-        url=url,
-        target_metadata=target_metadata,
-        literal_binds=True,
-        dialect_opts={"paramstyle": "named"},
-    )
-
-    with context.begin_transaction():
-        context.run_migrations()
-
-
-def run_migrations_online() -> None:
-    """Run migrations in 'online' mode.
-
-    In this scenario we need to create an Engine
-    and associate a connection with the context.
-
-    """
-    configuration = config.get_section(config.config_ini_section)
-    configuration["sqlalchemy.url"] = os.getenv("DATABASE_URL", "sqlite:///./openmemory.db")
-    connectable = engine_from_config(
-        configuration,
-        prefix="sqlalchemy.",
-        poolclass=pool.NullPool,
-    )
-
-    with connectable.connect() as connection:
-        context.configure(
-            connection=connection, target_metadata=target_metadata
-        )
-
-        with context.begin_transaction():
-            context.run_migrations()
-
-
-if context.is_offline_mode():
-    run_migrations_offline()
-else:
-    run_migrations_online()
@@ -1,28 +0,0 @@
-"""${message}
-
-Revision ID: ${up_revision}
-Revises: ${down_revision | comma,n}
-Create Date: ${create_date}
-
-"""
-from typing import Sequence, Union
-
-from alembic import op
-import sqlalchemy as sa
-${imports if imports else ""}
-
-# revision identifiers, used by Alembic.
-revision: str = ${repr(up_revision)}
-down_revision: Union[str, None] = ${repr(down_revision)}
-branch_labels: Union[str, Sequence[str], None] = ${repr(branch_labels)}
-depends_on: Union[str, Sequence[str], None] = ${repr(depends_on)}
-
-
-def upgrade() -> None:
-    """Upgrade schema."""
-    ${upgrades if upgrades else "pass"}
-
-
-def downgrade() -> None:
-    """Downgrade schema."""
-    ${downgrades if downgrades else "pass"}
@@ -1,225 +0,0 @@
-"""Initial migration
-
-Revision ID: 0b53c747049a
-Revises: 
-Create Date: 2025-04-19 00:59:56.244203
-
-"""
-from typing import Sequence, Union
-
-import sqlalchemy as sa
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision: str = '0b53c747049a'
-down_revision: Union[str, None] = None
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    """Upgrade schema."""
-    # ### commands auto generated by Alembic - please adjust! ###
-    op.create_table('access_controls',
-    sa.Column('id', sa.UUID(), nullable=False),
-    sa.Column('subject_type', sa.String(), nullable=False),
-    sa.Column('subject_id', sa.UUID(), nullable=True),
-    sa.Column('object_type', sa.String(), nullable=False),
-    sa.Column('object_id', sa.UUID(), nullable=True),
-    sa.Column('effect', sa.String(), nullable=False),
-    sa.Column('created_at', sa.DateTime(), nullable=True),
-    sa.PrimaryKeyConstraint('id')
-    )
-    op.create_index('idx_access_object', 'access_controls', ['object_type', 'object_id'], unique=False)
-    op.create_index('idx_access_subject', 'access_controls', ['subject_type', 'subject_id'], unique=False)
-    op.create_index(op.f('ix_access_controls_created_at'), 'access_controls', ['created_at'], unique=False)
-    op.create_index(op.f('ix_access_controls_effect'), 'access_controls', ['effect'], unique=False)
-    op.create_index(op.f('ix_access_controls_object_id'), 'access_controls', ['object_id'], unique=False)
-    op.create_index(op.f('ix_access_controls_object_type'), 'access_controls', ['object_type'], unique=False)
-    op.create_index(op.f('ix_access_controls_subject_id'), 'access_controls', ['subject_id'], unique=False)
-    op.create_index(op.f('ix_access_controls_subject_type'), 'access_controls', ['subject_type'], unique=False)
-    op.create_table('archive_policies',
-    sa.Column('id', sa.UUID(), nullable=False),
-    sa.Column('criteria_type', sa.String(), nullable=False),
-    sa.Column('criteria_id', sa.UUID(), nullable=True),
-    sa.Column('days_to_archive', sa.Integer(), nullable=False),
-    sa.Column('created_at', sa.DateTime(), nullable=True),
-    sa.PrimaryKeyConstraint('id')
-    )
-    op.create_index('idx_policy_criteria', 'archive_policies', ['criteria_type', 'criteria_id'], unique=False)
-    op.create_index(op.f('ix_archive_policies_created_at'), 'archive_policies', ['created_at'], unique=False)
-    op.create_index(op.f('ix_archive_policies_criteria_id'), 'archive_policies', ['criteria_id'], unique=False)
-    op.create_index(op.f('ix_archive_policies_criteria_type'), 'archive_policies', ['criteria_type'], unique=False)
-    op.create_table('categories',
-    sa.Column('id', sa.UUID(), nullable=False),
-    sa.Column('name', sa.String(), nullable=False),
-    sa.Column('description', sa.String(), nullable=True),
-    sa.Column('created_at', sa.DateTime(), nullable=True),
-    sa.Column('updated_at', sa.DateTime(), nullable=True),
-    sa.PrimaryKeyConstraint('id')
-    )
-    op.create_index(op.f('ix_categories_created_at'), 'categories', ['created_at'], unique=False)
-    op.create_index(op.f('ix_categories_name'), 'categories', ['name'], unique=True)
-    op.create_table('users',
-    sa.Column('id', sa.UUID(), nullable=False),
-    sa.Column('user_id', sa.String(), nullable=False),
-    sa.Column('name', sa.String(), nullable=True),
-    sa.Column('email', sa.String(), nullable=True),
-    sa.Column('metadata', sa.JSON(), nullable=True),
-    sa.Column('created_at', sa.DateTime(), nullable=True),
-    sa.Column('updated_at', sa.DateTime(), nullable=True),
-    sa.PrimaryKeyConstraint('id')
-    )
-    op.create_index(op.f('ix_users_created_at'), 'users', ['created_at'], unique=False)
-    op.create_index(op.f('ix_users_email'), 'users', ['email'], unique=True)
-    op.create_index(op.f('ix_users_name'), 'users', ['name'], unique=False)
-    op.create_index(op.f('ix_users_user_id'), 'users', ['user_id'], unique=True)
-    op.create_table('apps',
-    sa.Column('id', sa.UUID(), nullable=False),
-    sa.Column('owner_id', sa.UUID(), nullable=False),
-    sa.Column('name', sa.String(), nullable=False),
-    sa.Column('description', sa.String(), nullable=True),
-    sa.Column('metadata', sa.JSON(), nullable=True),
-    sa.Column('is_active', sa.Boolean(), nullable=True),
-    sa.Column('created_at', sa.DateTime(), nullable=True),
-    sa.Column('updated_at', sa.DateTime(), nullable=True),
-    sa.ForeignKeyConstraint(['owner_id'], ['users.id'], ),
-    sa.PrimaryKeyConstraint('id')
-    )
-    op.create_index(op.f('ix_apps_created_at'), 'apps', ['created_at'], unique=False)
-    op.create_index(op.f('ix_apps_is_active'), 'apps', ['is_active'], unique=False)
-    op.create_index(op.f('ix_apps_name'), 'apps', ['name'], unique=True)
-    op.create_index(op.f('ix_apps_owner_id'), 'apps', ['owner_id'], unique=False)
-    op.create_table('memories',
-    sa.Column('id', sa.UUID(), nullable=False),
-    sa.Column('user_id', sa.UUID(), nullable=False),
-    sa.Column('app_id', sa.UUID(), nullable=False),
-    sa.Column('content', sa.String(), nullable=False),
-    sa.Column('vector', sa.String(), nullable=True),
-    sa.Column('metadata', sa.JSON(), nullable=True),
-    sa.Column('state', sa.Enum('active', 'paused', 'archived', 'deleted', name='memorystate'), nullable=True),
-    sa.Column('created_at', sa.DateTime(), nullable=True),
-    sa.Column('updated_at', sa.DateTime(), nullable=True),
-    sa.Column('archived_at', sa.DateTime(), nullable=True),
-    sa.Column('deleted_at', sa.DateTime(), nullable=True),
-    sa.ForeignKeyConstraint(['app_id'], ['apps.id'], ),
-    sa.ForeignKeyConstraint(['user_id'], ['users.id'], ),
-    sa.PrimaryKeyConstraint('id')
-    )
-    op.create_index('idx_memory_app_state', 'memories', ['app_id', 'state'], unique=False)
-    op.create_index('idx_memory_user_app', 'memories', ['user_id', 'app_id'], unique=False)
-    op.create_index('idx_memory_user_state', 'memories', ['user_id', 'state'], unique=False)
-    op.create_index(op.f('ix_memories_app_id'), 'memories', ['app_id'], unique=False)
-    op.create_index(op.f('ix_memories_archived_at'), 'memories', ['archived_at'], unique=False)
-    op.create_index(op.f('ix_memories_created_at'), 'memories', ['created_at'], unique=False)
-    op.create_index(op.f('ix_memories_deleted_at'), 'memories', ['deleted_at'], unique=False)
-    op.create_index(op.f('ix_memories_state'), 'memories', ['state'], unique=False)
-    op.create_index(op.f('ix_memories_user_id'), 'memories', ['user_id'], unique=False)
-    op.create_table('memory_access_logs',
-    sa.Column('id', sa.UUID(), nullable=False),
-    sa.Column('memory_id', sa.UUID(), nullable=False),
-    sa.Column('app_id', sa.UUID(), nullable=False),
-    sa.Column('accessed_at', sa.DateTime(), nullable=True),
-    sa.Column('access_type', sa.String(), nullable=False),
-    sa.Column('metadata', sa.JSON(), nullable=True),
-    sa.ForeignKeyConstraint(['app_id'], ['apps.id'], ),
-    sa.ForeignKeyConstraint(['memory_id'], ['memories.id'], ),
-    sa.PrimaryKeyConstraint('id')
-    )
-    op.create_index('idx_access_app_time', 'memory_access_logs', ['app_id', 'accessed_at'], unique=False)
-    op.create_index('idx_access_memory_time', 'memory_access_logs', ['memory_id', 'accessed_at'], unique=False)
-    op.create_index(op.f('ix_memory_access_logs_access_type'), 'memory_access_logs', ['access_type'], unique=False)
-    op.create_index(op.f('ix_memory_access_logs_accessed_at'), 'memory_access_logs', ['accessed_at'], unique=False)
-    op.create_index(op.f('ix_memory_access_logs_app_id'), 'memory_access_logs', ['app_id'], unique=False)
-    op.create_index(op.f('ix_memory_access_logs_memory_id'), 'memory_access_logs', ['memory_id'], unique=False)
-    op.create_table('memory_categories',
-    sa.Column('memory_id', sa.UUID(), nullable=False),
-    sa.Column('category_id', sa.UUID(), nullable=False),
-    sa.ForeignKeyConstraint(['category_id'], ['categories.id'], ),
-    sa.ForeignKeyConstraint(['memory_id'], ['memories.id'], ),
-    sa.PrimaryKeyConstraint('memory_id', 'category_id')
-    )
-    op.create_index('idx_memory_category', 'memory_categories', ['memory_id', 'category_id'], unique=False)
-    op.create_index(op.f('ix_memory_categories_category_id'), 'memory_categories', ['category_id'], unique=False)
-    op.create_index(op.f('ix_memory_categories_memory_id'), 'memory_categories', ['memory_id'], unique=False)
-    op.create_table('memory_status_history',
-    sa.Column('id', sa.UUID(), nullable=False),
-    sa.Column('memory_id', sa.UUID(), nullable=False),
-    sa.Column('changed_by', sa.UUID(), nullable=False),
-    sa.Column('old_state', sa.Enum('active', 'paused', 'archived', 'deleted', name='memorystate'), nullable=False),
-    sa.Column('new_state', sa.Enum('active', 'paused', 'archived', 'deleted', name='memorystate'), nullable=False),
-    sa.Column('changed_at', sa.DateTime(), nullable=True),
-    sa.ForeignKeyConstraint(['changed_by'], ['users.id'], ),
-    sa.ForeignKeyConstraint(['memory_id'], ['memories.id'], ),
-    sa.PrimaryKeyConstraint('id')
-    )
-    op.create_index('idx_history_memory_state', 'memory_status_history', ['memory_id', 'new_state'], unique=False)
-    op.create_index('idx_history_user_time', 'memory_status_history', ['changed_by', 'changed_at'], unique=False)
-    op.create_index(op.f('ix_memory_status_history_changed_at'), 'memory_status_history', ['changed_at'], unique=False)
-    op.create_index(op.f('ix_memory_status_history_changed_by'), 'memory_status_history', ['changed_by'], unique=False)
-    op.create_index(op.f('ix_memory_status_history_memory_id'), 'memory_status_history', ['memory_id'], unique=False)
-    op.create_index(op.f('ix_memory_status_history_new_state'), 'memory_status_history', ['new_state'], unique=False)
-    op.create_index(op.f('ix_memory_status_history_old_state'), 'memory_status_history', ['old_state'], unique=False)
-    # ### end Alembic commands ###
-
-
-def downgrade() -> None:
-    """Downgrade schema."""
-    # ### commands auto generated by Alembic - please adjust! ###
-    op.drop_index(op.f('ix_memory_status_history_old_state'), table_name='memory_status_history')
-    op.drop_index(op.f('ix_memory_status_history_new_state'), table_name='memory_status_history')
-    op.drop_index(op.f('ix_memory_status_history_memory_id'), table_name='memory_status_history')
-    op.drop_index(op.f('ix_memory_status_history_changed_by'), table_name='memory_status_history')
-    op.drop_index(op.f('ix_memory_status_history_changed_at'), table_name='memory_status_history')
-    op.drop_index('idx_history_user_time', table_name='memory_status_history')
-    op.drop_index('idx_history_memory_state', table_name='memory_status_history')
-    op.drop_table('memory_status_history')
-    op.drop_index(op.f('ix_memory_categories_memory_id'), table_name='memory_categories')
-    op.drop_index(op.f('ix_memory_categories_category_id'), table_name='memory_categories')
-    op.drop_index('idx_memory_category', table_name='memory_categories')
-    op.drop_table('memory_categories')
-    op.drop_index(op.f('ix_memory_access_logs_memory_id'), table_name='memory_access_logs')
-    op.drop_index(op.f('ix_memory_access_logs_app_id'), table_name='memory_access_logs')
-    op.drop_index(op.f('ix_memory_access_logs_accessed_at'), table_name='memory_access_logs')
-    op.drop_index(op.f('ix_memory_access_logs_access_type'), table_name='memory_access_logs')
-    op.drop_index('idx_access_memory_time', table_name='memory_access_logs')
-    op.drop_index('idx_access_app_time', table_name='memory_access_logs')
-    op.drop_table('memory_access_logs')
-    op.drop_index(op.f('ix_memories_user_id'), table_name='memories')
-    op.drop_index(op.f('ix_memories_state'), table_name='memories')
-    op.drop_index(op.f('ix_memories_deleted_at'), table_name='memories')
-    op.drop_index(op.f('ix_memories_created_at'), table_name='memories')
-    op.drop_index(op.f('ix_memories_archived_at'), table_name='memories')
-    op.drop_index(op.f('ix_memories_app_id'), table_name='memories')
-    op.drop_index('idx_memory_user_state', table_name='memories')
-    op.drop_index('idx_memory_user_app', table_name='memories')
-    op.drop_index('idx_memory_app_state', table_name='memories')
-    op.drop_table('memories')
-    op.drop_index(op.f('ix_apps_owner_id'), table_name='apps')
-    op.drop_index(op.f('ix_apps_name'), table_name='apps')
-    op.drop_index(op.f('ix_apps_is_active'), table_name='apps')
-    op.drop_index(op.f('ix_apps_created_at'), table_name='apps')
-    op.drop_table('apps')
-    op.drop_index(op.f('ix_users_user_id'), table_name='users')
-    op.drop_index(op.f('ix_users_name'), table_name='users')
-    op.drop_index(op.f('ix_users_email'), table_name='users')
-    op.drop_index(op.f('ix_users_created_at'), table_name='users')
-    op.drop_table('users')
-    op.drop_index(op.f('ix_categories_name'), table_name='categories')
-    op.drop_index(op.f('ix_categories_created_at'), table_name='categories')
-    op.drop_table('categories')
-    op.drop_index(op.f('ix_archive_policies_criteria_type'), table_name='archive_policies')
-    op.drop_index(op.f('ix_archive_policies_criteria_id'), table_name='archive_policies')
-    op.drop_index(op.f('ix_archive_policies_created_at'), table_name='archive_policies')
-    op.drop_index('idx_policy_criteria', table_name='archive_policies')
-    op.drop_table('archive_policies')
-    op.drop_index(op.f('ix_access_controls_subject_type'), table_name='access_controls')
-    op.drop_index(op.f('ix_access_controls_subject_id'), table_name='access_controls')
-    op.drop_index(op.f('ix_access_controls_object_type'), table_name='access_controls')
-    op.drop_index(op.f('ix_access_controls_object_id'), table_name='access_controls')
-    op.drop_index(op.f('ix_access_controls_effect'), table_name='access_controls')
-    op.drop_index(op.f('ix_access_controls_created_at'), table_name='access_controls')
-    op.drop_index('idx_access_subject', table_name='access_controls')
-    op.drop_index('idx_access_object', table_name='access_controls')
-    op.drop_table('access_controls')
-    # ### end Alembic commands ###
@@ -1,40 +0,0 @@
-"""add_config_table
-
-Revision ID: add_config_table
-Revises: 0b53c747049a
-Create Date: 2023-06-01 10:00:00.000000
-
-"""
-import uuid
-
-import sqlalchemy as sa
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision = 'add_config_table'
-down_revision = '0b53c747049a'
-branch_labels = None
-depends_on = None
-
-
-def upgrade():
-    # Create configs table if it doesn't exist
-    op.create_table(
-        'configs',
-        sa.Column('id', sa.UUID(), nullable=False, default=lambda: uuid.uuid4()),
-        sa.Column('key', sa.String(), nullable=False),
-        sa.Column('value', sa.JSON(), nullable=False),
-        sa.Column('created_at', sa.DateTime(), nullable=True),
-        sa.Column('updated_at', sa.DateTime(), nullable=True),
-        sa.PrimaryKeyConstraint('id'),
-        sa.UniqueConstraint('key')
-    )
-    
-    # Create index for key lookups
-    op.create_index('idx_configs_key', 'configs', ['key'])
-
-
-def downgrade():
-    # Drop the configs table
-    op.drop_index('idx_configs_key', 'configs')
-    op.drop_table('configs') 
@@ -1,34 +0,0 @@
-"""remove_global_unique_constraint_on_app_name_add_composite_unique
-
-Revision ID: afd00efbd06b
-Revises: add_config_table
-Create Date: 2025-06-04 01:59:41.637440
-
-"""
-from typing import Sequence, Union
-
-from alembic import op
-
-# revision identifiers, used by Alembic.
-revision: str = 'afd00efbd06b'
-down_revision: Union[str, None] = 'add_config_table'
-branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
-
-
-def upgrade() -> None:
-    """Upgrade schema."""
-    # ### commands auto generated by Alembic - please adjust! ###
-    op.drop_index('ix_apps_name', table_name='apps')
-    op.create_index(op.f('ix_apps_name'), 'apps', ['name'], unique=False)
-    op.create_index('idx_app_owner_name', 'apps', ['owner_id', 'name'], unique=True)
-    # ### end Alembic commands ###
-
-
-def downgrade() -> None:
-    """Downgrade schema."""
-    # ### commands auto generated by Alembic - please adjust! ###
-    op.drop_index('idx_app_owner_name', table_name='apps')
-    op.drop_index(op.f('ix_apps_name'), table_name='apps')
-    op.create_index('ix_apps_name', 'apps', ['name'], unique=True)
-    # ### end Alembic commands ###
@@ -1 +0,0 @@
-# This file makes the app directory a Python package
@@ -1,4 +0,0 @@
-import os
-
-USER_ID = os.getenv("USER", "default_user")
-DEFAULT_APP_ID = "openmemory"
@@ -1,30 +0,0 @@
-import os
-
-from dotenv import load_dotenv
-from sqlalchemy import create_engine
-from sqlalchemy.orm import declarative_base, sessionmaker
-
-# load .env file (make sure you have DATABASE_URL set)
-load_dotenv()
-
-DATABASE_URL = os.getenv("DATABASE_URL", "sqlite:///./openmemory.db")
-if not DATABASE_URL:
-    raise RuntimeError("DATABASE_URL is not set in environment")
-
-# SQLAlchemy engine & session
-engine = create_engine(
-    DATABASE_URL,
-    connect_args={"check_same_thread": False}  # Needed for SQLite
-)
-SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
-
-# Base class for models
-Base = declarative_base()
-
-# Dependency for FastAPI
-def get_db():
-    db = SessionLocal()
-    try:
-        yield db
-    finally:
-        db.close()
@@ -1,574 +0,0 @@
-"""
-MCP Server for OpenMemory with resilient memory client handling.
-
-This module implements an MCP (Model Context Protocol) server that provides
-memory operations for OpenMemory. The memory client is initialized lazily
-to prevent server crashes when external dependencies (like Ollama) are
-unavailable. If the memory client cannot be initialized, the server will
-continue running with limited functionality and appropriate error messages.
-
-Key features:
- Lazy memory client initialization
- Graceful error handling for unavailable dependencies
- Fallback to database-only mode when vector store is unavailable
- Proper logging for debugging connection issues
- Environment variable parsing for API keys
-"""
-
-import contextvars
-import datetime
-import json
-import logging
-import uuid
-
-import anyio
-
-from app.database import SessionLocal
-from app.models import Memory, MemoryAccessLog, MemoryState, MemoryStatusHistory
-from app.utils.db import get_user_and_app
-from app.utils.memory import get_memory_client
-from app.utils.permissions import check_memory_access_permissions
-from dotenv import load_dotenv
-from fastapi import FastAPI, Request
-from fastapi.routing import APIRouter
-from mcp.server.fastmcp import FastMCP
-from mcp.server.sse import SseServerTransport
-from mcp.server.streamable_http import StreamableHTTPServerTransport
-from starlette.responses import Response
-
-# Load environment variables
-load_dotenv()
-
-# Initialize MCP
-mcp = FastMCP("mem0-mcp-server")
-
-# Don't initialize memory client at import time - do it lazily when needed
-def get_memory_client_safe():
-    """Get memory client with error handling. Returns None if client cannot be initialized."""
-    try:
-        return get_memory_client()
-    except Exception as e:
-        logging.warning(f"Failed to get memory client: {e}")
-        return None
-
-# Context variables for user_id and client_name
-user_id_var: contextvars.ContextVar[str] = contextvars.ContextVar("user_id")
-client_name_var: contextvars.ContextVar[str] = contextvars.ContextVar("client_name")
-
-# Create a router for MCP endpoints
-mcp_router = APIRouter(prefix="/mcp")
-
-# Initialize SSE transport
-sse = SseServerTransport("/mcp/messages/")
-
-@mcp.tool(description="Add a new memory. This method is called everytime the user informs anything about themselves, their preferences, or anything that has any relevant information which can be useful in the future conversation. This can also be called when the user asks you to remember something. Set infer to False to store the memory verbatim without LLM fact extraction.")
-async def add_memories(text: str, infer: bool = True) -> str:
-    uid = user_id_var.get(None)
-    client_name = client_name_var.get(None)
-
-    if not uid:
-        return "Error: user_id not provided"
-    if not client_name:
-        return "Error: client_name not provided"
-
-    # Get memory client safely
-    memory_client = get_memory_client_safe()
-    if not memory_client:
-        return "Error: Memory system is currently unavailable. Please try again later."
-
-    try:
-        db = SessionLocal()
-        try:
-            # Get or create user and app
-            user, app = get_user_and_app(db, user_id=uid, app_id=client_name)
-
-            # Check if app is active
-            if not app.is_active:
-                return f"Error: App {app.name} is currently paused on OpenMemory. Cannot create new memories."
-
-            response = memory_client.add(text,
-                                         user_id=uid,
-                                         metadata={
-                                            "source_app": "openmemory",
-                                            "mcp_client": client_name,
-                                         },
-                                         infer=infer)
-
-            # Process the response and update database
-            if isinstance(response, dict) and 'results' in response:
-                for result in response['results']:
-                    memory_id = uuid.UUID(result['id'])
-                    memory = db.query(Memory).filter(Memory.id == memory_id).first()
-
-                    if result['event'] == 'ADD':
-                        if not memory:
-                            memory = Memory(
-                                id=memory_id,
-                                user_id=user.id,
-                                app_id=app.id,
-                                content=result['memory'],
-                                state=MemoryState.active
-                            )
-                            db.add(memory)
-                        else:
-                            memory.state = MemoryState.active
-                            memory.content = result['memory']
-
-                        # Create history entry
-                        history = MemoryStatusHistory(
-                            memory_id=memory_id,
-                            changed_by=user.id,
-                            old_state=MemoryState.deleted if memory else None,
-                            new_state=MemoryState.active
-                        )
-                        db.add(history)
-
-                    elif result['event'] == 'DELETE':
-                        if memory:
-                            memory.state = MemoryState.deleted
-                            memory.deleted_at = datetime.datetime.now(datetime.UTC)
-                            # Create history entry
-                            history = MemoryStatusHistory(
-                                memory_id=memory_id,
-                                changed_by=user.id,
-                                old_state=MemoryState.active,
-                                new_state=MemoryState.deleted
-                            )
-                            db.add(history)
-
-                db.commit()
-
-            return json.dumps(response)
-        finally:
-            db.close()
-    except Exception as e:
-        logging.exception(f"Error adding to memory: {e}")
-        return f"Error adding to memory: {e}"
-
-
-@mcp.tool(description="Search through stored memories. This method is called EVERYTIME the user asks anything.")
-async def search_memory(query: str) -> str:
-    uid = user_id_var.get(None)
-    client_name = client_name_var.get(None)
-    if not uid:
-        return "Error: user_id not provided"
-    if not client_name:
-        return "Error: client_name not provided"
-
-    # Get memory client safely
-    memory_client = get_memory_client_safe()
-    if not memory_client:
-        return "Error: Memory system is currently unavailable. Please try again later."
-
-    try:
-        db = SessionLocal()
-        try:
-            # Get or create user and app
-            user, app = get_user_and_app(db, user_id=uid, app_id=client_name)
-
-            # Get accessible memory IDs based on ACL
-            user_memories = db.query(Memory).filter(Memory.user_id == user.id).all()
-            accessible_memory_ids = [memory.id for memory in user_memories if check_memory_access_permissions(db, memory, app.id)]
-
-            filters = {
-                "user_id": uid
-            }
-
-            embeddings = memory_client.embedding_model.embed(query, "search")
-
-            hits = memory_client.vector_store.search(
-                query=query, 
-                vectors=embeddings, 
-                limit=10, 
-                filters=filters,
-            )
-
-            allowed = set(str(mid) for mid in accessible_memory_ids) if accessible_memory_ids else None
-
-            results = []
-            for h in hits:
-                # All vector db search functions return OutputData class
-                id, score, payload = h.id, h.score, h.payload
-                if allowed and (h.id is None or h.id not in allowed):
-                    continue
-                
-                results.append({
-                    "id": id, 
-                    "memory": payload.get("data"), 
-                    "hash": payload.get("hash"),
-                    "created_at": payload.get("created_at"), 
-                    "updated_at": payload.get("updated_at"), 
-                    "score": score,
-                })
-
-            for r in results: 
-                if r.get("id"): 
-                    access_log = MemoryAccessLog(
-                        memory_id=uuid.UUID(r["id"]),
-                        app_id=app.id,
-                        access_type="search",
-                        metadata_={
-                            "query": query,
-                            "score": r.get("score"),
-                            "hash": r.get("hash"),
-                        },
-                    )
-                    db.add(access_log)
-            db.commit()
-
-            return json.dumps({"results": results}, indent=2)
-        finally:
-            db.close()
-    except Exception as e:
-        logging.exception(e)
-        return f"Error searching memory: {e}"
-
-
-@mcp.tool(description="List all memories in the user's memory")
-async def list_memories() -> str:
-    uid = user_id_var.get(None)
-    client_name = client_name_var.get(None)
-    if not uid:
-        return "Error: user_id not provided"
-    if not client_name:
-        return "Error: client_name not provided"
-
-    # Get memory client safely
-    memory_client = get_memory_client_safe()
-    if not memory_client:
-        return "Error: Memory system is currently unavailable. Please try again later."
-
-    try:
-        db = SessionLocal()
-        try:
-            # Get or create user and app
-            user, app = get_user_and_app(db, user_id=uid, app_id=client_name)
-
-            # Get all memories
-            memories = memory_client.get_all(user_id=uid)
-            filtered_memories = []
-
-            # Filter memories based on permissions
-            user_memories = db.query(Memory).filter(Memory.user_id == user.id).all()
-            accessible_memory_ids = [memory.id for memory in user_memories if check_memory_access_permissions(db, memory, app.id)]
-            if isinstance(memories, dict) and 'results' in memories:
-                for memory_data in memories['results']:
-                    if 'id' in memory_data:
-                        memory_id = uuid.UUID(memory_data['id'])
-                        if memory_id in accessible_memory_ids:
-                            # Create access log entry
-                            access_log = MemoryAccessLog(
-                                memory_id=memory_id,
-                                app_id=app.id,
-                                access_type="list",
-                                metadata_={
-                                    "hash": memory_data.get('hash')
-                                }
-                            )
-                            db.add(access_log)
-                            filtered_memories.append(memory_data)
-                db.commit()
-            else:
-                for memory in memories:
-                    memory_id = uuid.UUID(memory['id'])
-                    memory_obj = db.query(Memory).filter(Memory.id == memory_id).first()
-                    if memory_obj and check_memory_access_permissions(db, memory_obj, app.id):
-                        # Create access log entry
-                        access_log = MemoryAccessLog(
-                            memory_id=memory_id,
-                            app_id=app.id,
-                            access_type="list",
-                            metadata_={
-                                "hash": memory.get('hash')
-                            }
-                        )
-                        db.add(access_log)
-                        filtered_memories.append(memory)
-                db.commit()
-            return json.dumps(filtered_memories, indent=2)
-        finally:
-            db.close()
-    except Exception as e:
-        logging.exception(f"Error getting memories: {e}")
-        return f"Error getting memories: {e}"
-
-
-@mcp.tool(description="Delete specific memories by their IDs")
-async def delete_memories(memory_ids: list[str]) -> str:
-    uid = user_id_var.get(None)
-    client_name = client_name_var.get(None)
-    if not uid:
-        return "Error: user_id not provided"
-    if not client_name:
-        return "Error: client_name not provided"
-
-    # Get memory client safely
-    memory_client = get_memory_client_safe()
-    if not memory_client:
-        return "Error: Memory system is currently unavailable. Please try again later."
-
-    try:
-        db = SessionLocal()
-        try:
-            # Get or create user and app
-            user, app = get_user_and_app(db, user_id=uid, app_id=client_name)
-
-            # Convert string IDs to UUIDs and filter accessible ones
-            requested_ids = [uuid.UUID(mid) for mid in memory_ids]
-            user_memories = db.query(Memory).filter(Memory.user_id == user.id).all()
-            accessible_memory_ids = [memory.id for memory in user_memories if check_memory_access_permissions(db, memory, app.id)]
-
-            # Only delete memories that are both requested and accessible
-            ids_to_delete = [mid for mid in requested_ids if mid in accessible_memory_ids]
-
-            if not ids_to_delete:
-                return "Error: No accessible memories found with provided IDs"
-
-            # Delete from vector store
-            for memory_id in ids_to_delete:
-                try:
-                    memory_client.delete(str(memory_id))
-                except Exception as delete_error:
-                    logging.warning(f"Failed to delete memory {memory_id} from vector store: {delete_error}")
-
-            # Update each memory's state and create history entries
-            now = datetime.datetime.now(datetime.UTC)
-            for memory_id in ids_to_delete:
-                memory = db.query(Memory).filter(Memory.id == memory_id).first()
-                if memory:
-                    # Update memory state
-                    memory.state = MemoryState.deleted
-                    memory.deleted_at = now
-
-                    # Create history entry
-                    history = MemoryStatusHistory(
-                        memory_id=memory_id,
-                        changed_by=user.id,
-                        old_state=MemoryState.active,
-                        new_state=MemoryState.deleted
-                    )
-                    db.add(history)
-
-                    # Create access log entry
-                    access_log = MemoryAccessLog(
-                        memory_id=memory_id,
-                        app_id=app.id,
-                        access_type="delete",
-                        metadata_={"operation": "delete_by_id"}
-                    )
-                    db.add(access_log)
-
-            db.commit()
-            return f"Successfully deleted {len(ids_to_delete)} memories"
-        finally:
-            db.close()
-    except Exception as e:
-        logging.exception(f"Error deleting memories: {e}")
-        return f"Error deleting memories: {e}"
-
-
-@mcp.tool(description="Delete all memories in the user's memory")
-async def delete_all_memories() -> str:
-    uid = user_id_var.get(None)
-    client_name = client_name_var.get(None)
-    if not uid:
-        return "Error: user_id not provided"
-    if not client_name:
-        return "Error: client_name not provided"
-
-    # Get memory client safely
-    memory_client = get_memory_client_safe()
-    if not memory_client:
-        return "Error: Memory system is currently unavailable. Please try again later."
-
-    try:
-        db = SessionLocal()
-        try:
-            # Get or create user and app
-            user, app = get_user_and_app(db, user_id=uid, app_id=client_name)
-
-            user_memories = db.query(Memory).filter(Memory.user_id == user.id).all()
-            accessible_memory_ids = [memory.id for memory in user_memories if check_memory_access_permissions(db, memory, app.id)]
-
-            # delete the accessible memories only
-            for memory_id in accessible_memory_ids:
-                try:
-                    memory_client.delete(str(memory_id))
-                except Exception as delete_error:
-                    logging.warning(f"Failed to delete memory {memory_id} from vector store: {delete_error}")
-
-            # Update each memory's state and create history entries
-            now = datetime.datetime.now(datetime.UTC)
-            for memory_id in accessible_memory_ids:
-                memory = db.query(Memory).filter(Memory.id == memory_id).first()
-                # Update memory state
-                memory.state = MemoryState.deleted
-                memory.deleted_at = now
-
-                # Create history entry
-                history = MemoryStatusHistory(
-                    memory_id=memory_id,
-                    changed_by=user.id,
-                    old_state=MemoryState.active,
-                    new_state=MemoryState.deleted
-                )
-                db.add(history)
-
-                # Create access log entry
-                access_log = MemoryAccessLog(
-                    memory_id=memory_id,
-                    app_id=app.id,
-                    access_type="delete_all",
-                    metadata_={"operation": "bulk_delete"}
-                )
-                db.add(access_log)
-
-            db.commit()
-            return "Successfully deleted all memories"
-        finally:
-            db.close()
-    except Exception as e:
-        logging.exception(f"Error deleting memories: {e}")
-        return f"Error deleting memories: {e}"
-
-
-@mcp_router.get("/{client_name}/sse/{user_id}")
-async def handle_sse(request: Request):
-    """Handle SSE connections for a specific user and client"""
-    # Extract user_id and client_name from path parameters
-    uid = request.path_params.get("user_id")
-    user_token = user_id_var.set(uid or "")
-    client_name = request.path_params.get("client_name")
-    client_token = client_name_var.set(client_name or "")
-
-    try:
-        # NOTE: request._send is the raw ASGI `send` callable. Starlette does not
-        # expose it publicly, but the MCP SDK transports require the raw ASGI
-        # interface (scope, receive, send). This is the standard pattern from the
-        # MCP Python SDK examples.
-        async with sse.connect_sse(
-            request.scope,
-            request.receive,
-            request._send,
-        ) as (read_stream, write_stream):
-            await mcp._mcp_server.run(
-                read_stream,
-                write_stream,
-                mcp._mcp_server.create_initialization_options(),
-            )
-    finally:
-        # Clean up context variables
-        user_id_var.reset(user_token)
-        client_name_var.reset(client_token)
-
-
-@mcp_router.post("/messages/")
-async def handle_get_message(request: Request):
-    return await handle_post_message(request)
-
-
-@mcp_router.post("/{client_name}/sse/{user_id}/messages/")
-async def handle_post_message(request: Request):
-    return await handle_post_message(request)
-
-async def handle_post_message(request: Request):
-    """Handle POST messages for SSE"""
-    try:
-        body = await request.body()
-
-        # Create a simple receive function that returns the body
-        async def receive():
-            return {"type": "http.request", "body": body, "more_body": False}
-
-        # Create a simple send function that does nothing
-        async def send(message):
-            return {}
-
-        # Call handle_post_message with the correct arguments
-        await sse.handle_post_message(request.scope, receive, send)
-
-        # Return a success response
-        return {"status": "ok"}
-    finally:
-        pass
-
-
-@mcp_router.api_route("/{client_name}/http/{user_id}", methods=["POST", "GET", "DELETE"])
-async def handle_streamable_http(request: Request):
-    """Handle Streamable HTTP connections for a specific user and client.
-
-    Uses the Streamable HTTP transport (MCP spec 2025-03-26+) which replaces
-    the deprecated SSE transport. Runs in stateless mode — each request is
-    handled independently with no persistent session.
-
-    The transport writes its response directly to the ASGI ``send`` callable.
-    We intercept it via ``capture_send`` so we can return a proper ``Response``
-    to FastAPI — otherwise FastAPI would also try to send its own response,
-    causing a "double-response" bug.
-    """
-    uid = request.path_params.get("user_id")
-    user_token = user_id_var.set(uid or "")
-    client_name = request.path_params.get("client_name")
-    client_token = client_name_var.set(client_name or "")
-
-    # Intercept the ASGI messages the transport sends so we can return them
-    # as a single Response to FastAPI.  Without this, FastAPI would attempt to
-    # write its own response after the transport already wrote one.
-    response_started = False
-    response_status = 200
-    response_headers: list[tuple[bytes, bytes]] = []
-    response_body = bytearray()
-
-    async def capture_send(message):
-        nonlocal response_started, response_status
-        if message["type"] == "http.response.start":
-            response_started = True
-            response_status = message["status"]
-            response_headers.extend(message.get("headers", []))
-        elif message["type"] == "http.response.body":
-            response_body.extend(message.get("body", b""))
-
-    try:
-        transport = StreamableHTTPServerTransport(
-            mcp_session_id=None,
-            is_json_response_enabled=True,
-        )
-
-        async with anyio.create_task_group() as tg:
-
-            async def run_server(*, task_status=anyio.TASK_STATUS_IGNORED):
-                async with transport.connect() as (read_stream, write_stream):
-                    task_status.started()
-                    await mcp._mcp_server.run(
-                        read_stream,
-                        write_stream,
-                        mcp._mcp_server.create_initialization_options(),
-                        stateless=True,
-                    )
-
-            await tg.start(run_server)
-            await transport.handle_request(request.scope, request.receive, capture_send)
-            await transport.terminate()
-            tg.cancel_scope.cancel()
-    finally:
-        user_id_var.reset(user_token)
-        client_name_var.reset(client_token)
-
-    if not response_started:
-        return Response(status_code=500, content=b"Transport did not produce a response")
-
-    # Header dict conversion is safe here: the MCP transport in stateless JSON
-    # mode only emits single-valued headers (Content-Type, Content-Length).
-    return Response(
-        content=bytes(response_body),
-        status_code=response_status,
-        headers={k.decode(): v.decode() for k, v in response_headers},
-    )
-
-
-def setup_mcp_server(app: FastAPI):
-    """Setup MCP server with the FastAPI application"""
-    mcp._mcp_server.name = "mem0-mcp-server"
-
-    # Include MCP router in the FastAPI app
-    app.include_router(mcp_router)
@@ -1,243 +0,0 @@
-import datetime
-import enum
-import uuid
-
-import sqlalchemy as sa
-from app.database import Base
-from app.utils.categorization import get_categories_for_memory
-from sqlalchemy import (
-    JSON,
-    UUID,
-    Boolean,
-    Column,
-    DateTime,
-    Enum,
-    ForeignKey,
-    Index,
-    Integer,
-    String,
-    Table,
-    event,
-)
-from sqlalchemy.orm import Session, relationship
-
-
-def get_current_utc_time():
-    """Get current UTC time"""
-    return datetime.datetime.now(datetime.UTC)
-
-
-class MemoryState(enum.Enum):
-    active = "active"
-    paused = "paused"
-    archived = "archived"
-    deleted = "deleted"
-
-
-class User(Base):
-    __tablename__ = "users"
-    id = Column(UUID, primary_key=True, default=lambda: uuid.uuid4())
-    user_id = Column(String, nullable=False, unique=True, index=True)
-    name = Column(String, nullable=True, index=True)
-    email = Column(String, unique=True, nullable=True, index=True)
-    metadata_ = Column('metadata', JSON, default=dict)
-    created_at = Column(DateTime, default=get_current_utc_time, index=True)
-    updated_at = Column(DateTime,
-                        default=get_current_utc_time,
-                        onupdate=get_current_utc_time)
-
-    apps = relationship("App", back_populates="owner")
-    memories = relationship("Memory", back_populates="user")
-
-
-class App(Base):
-    __tablename__ = "apps"
-    id = Column(UUID, primary_key=True, default=lambda: uuid.uuid4())
-    owner_id = Column(UUID, ForeignKey("users.id"), nullable=False, index=True)
-    name = Column(String, nullable=False, index=True)
-    description = Column(String)
-    metadata_ = Column('metadata', JSON, default=dict)
-    is_active = Column(Boolean, default=True, index=True)
-    created_at = Column(DateTime, default=get_current_utc_time, index=True)
-    updated_at = Column(DateTime,
-                        default=get_current_utc_time,
-                        onupdate=get_current_utc_time)
-
-    owner = relationship("User", back_populates="apps")
-    memories = relationship("Memory", back_populates="app")
-
-    __table_args__ = (
-        sa.UniqueConstraint('owner_id', 'name', name='idx_app_owner_name'),
-    )
-
-
-class Config(Base):
-    __tablename__ = "configs"
-    id = Column(UUID, primary_key=True, default=lambda: uuid.uuid4())
-    key = Column(String, unique=True, nullable=False, index=True)
-    value = Column(JSON, nullable=False)
-    created_at = Column(DateTime, default=get_current_utc_time)
-    updated_at = Column(DateTime,
-                        default=get_current_utc_time,
-                        onupdate=get_current_utc_time)
-
-
-class Memory(Base):
-    __tablename__ = "memories"
-    id = Column(UUID, primary_key=True, default=lambda: uuid.uuid4())
-    user_id = Column(UUID, ForeignKey("users.id"), nullable=False, index=True)
-    app_id = Column(UUID, ForeignKey("apps.id"), nullable=False, index=True)
-    content = Column(String, nullable=False)
-    vector = Column(String)
-    metadata_ = Column('metadata', JSON, default=dict)
-    state = Column(Enum(MemoryState), default=MemoryState.active, index=True)
-    created_at = Column(DateTime, default=get_current_utc_time, index=True)
-    updated_at = Column(DateTime,
-                        default=get_current_utc_time,
-                        onupdate=get_current_utc_time)
-    archived_at = Column(DateTime, nullable=True, index=True)
-    deleted_at = Column(DateTime, nullable=True, index=True)
-
-    user = relationship("User", back_populates="memories")
-    app = relationship("App", back_populates="memories")
-    categories = relationship("Category", secondary="memory_categories", back_populates="memories")
-
-    __table_args__ = (
-        Index('idx_memory_user_state', 'user_id', 'state'),
-        Index('idx_memory_app_state', 'app_id', 'state'),
-        Index('idx_memory_user_app', 'user_id', 'app_id'),
-    )
-
-
-class Category(Base):
-    __tablename__ = "categories"
-    id = Column(UUID, primary_key=True, default=lambda: uuid.uuid4())
-    name = Column(String, unique=True, nullable=False, index=True)
-    description = Column(String)
-    created_at = Column(DateTime, default=datetime.datetime.now(datetime.UTC), index=True)
-    updated_at = Column(DateTime,
-                        default=get_current_utc_time,
-                        onupdate=get_current_utc_time)
-
-    memories = relationship("Memory", secondary="memory_categories", back_populates="categories")
-
-memory_categories = Table(
-    "memory_categories", Base.metadata,
-    Column("memory_id", UUID, ForeignKey("memories.id"), primary_key=True, index=True),
-    Column("category_id", UUID, ForeignKey("categories.id"), primary_key=True, index=True),
-    Index('idx_memory_category', 'memory_id', 'category_id')
-)
-
-
-class AccessControl(Base):
-    __tablename__ = "access_controls"
-    id = Column(UUID, primary_key=True, default=lambda: uuid.uuid4())
-    subject_type = Column(String, nullable=False, index=True)
-    subject_id = Column(UUID, nullable=True, index=True)
-    object_type = Column(String, nullable=False, index=True)
-    object_id = Column(UUID, nullable=True, index=True)
-    effect = Column(String, nullable=False, index=True)
-    created_at = Column(DateTime, default=get_current_utc_time, index=True)
-
-    __table_args__ = (
-        Index('idx_access_subject', 'subject_type', 'subject_id'),
-        Index('idx_access_object', 'object_type', 'object_id'),
-    )
-
-
-class ArchivePolicy(Base):
-    __tablename__ = "archive_policies"
-    id = Column(UUID, primary_key=True, default=lambda: uuid.uuid4())
-    criteria_type = Column(String, nullable=False, index=True)
-    criteria_id = Column(UUID, nullable=True, index=True)
-    days_to_archive = Column(Integer, nullable=False)
-    created_at = Column(DateTime, default=get_current_utc_time, index=True)
-
-    __table_args__ = (
-        Index('idx_policy_criteria', 'criteria_type', 'criteria_id'),
-    )
-
-
-class MemoryStatusHistory(Base):
-    __tablename__ = "memory_status_history"
-    id = Column(UUID, primary_key=True, default=lambda: uuid.uuid4())
-    memory_id = Column(UUID, ForeignKey("memories.id"), nullable=False, index=True)
-    changed_by = Column(UUID, ForeignKey("users.id"), nullable=False, index=True)
-    old_state = Column(Enum(MemoryState), nullable=False, index=True)
-    new_state = Column(Enum(MemoryState), nullable=False, index=True)
-    changed_at = Column(DateTime, default=get_current_utc_time, index=True)
-
-    __table_args__ = (
-        Index('idx_history_memory_state', 'memory_id', 'new_state'),
-        Index('idx_history_user_time', 'changed_by', 'changed_at'),
-    )
-
-
-class MemoryAccessLog(Base):
-    __tablename__ = "memory_access_logs"
-    id = Column(UUID, primary_key=True, default=lambda: uuid.uuid4())
-    memory_id = Column(UUID, ForeignKey("memories.id"), nullable=False, index=True)
-    app_id = Column(UUID, ForeignKey("apps.id"), nullable=False, index=True)
-    accessed_at = Column(DateTime, default=get_current_utc_time, index=True)
-    access_type = Column(String, nullable=False, index=True)
-    metadata_ = Column('metadata', JSON, default=dict)
-
-    __table_args__ = (
-        Index('idx_access_memory_time', 'memory_id', 'accessed_at'),
-        Index('idx_access_app_time', 'app_id', 'accessed_at'),
-    )
-
-def categorize_memory(memory: Memory, db: Session) -> None:
-    """Categorize a memory using OpenAI and store the categories in the database."""
-    try:
-        # Get categories from OpenAI
-        categories = get_categories_for_memory(memory.content)
-
-        # Get or create categories in the database
-        for category_name in categories:
-            category = db.query(Category).filter(Category.name == category_name).first()
-            if not category:
-                category = Category(
-                    name=category_name,
-                    description=f"Automatically created category for {category_name}"
-                )
-                db.add(category)
-                db.flush()  # Flush to get the category ID
-
-            # Check if the memory-category association already exists
-            existing = db.execute(
-                memory_categories.select().where(
-                    (memory_categories.c.memory_id == memory.id) &
-                    (memory_categories.c.category_id == category.id)
-                )
-            ).first()
-
-            if not existing:
-                # Create the association
-                db.execute(
-                    memory_categories.insert().values(
-                        memory_id=memory.id,
-                        category_id=category.id
-                    )
-                )
-
-        db.commit()
-    except Exception as e:
-        db.rollback()
-        print(f"Error categorizing memory: {e}")
-
-
-@event.listens_for(Memory, 'after_insert')
-def after_memory_insert(mapper, connection, target):
-    """Trigger categorization after a memory is inserted."""
-    db = Session(bind=connection)
-    categorize_memory(target, db)
-    db.close()
-
-
-@event.listens_for(Memory, 'after_update')
-def after_memory_update(mapper, connection, target):
-    """Trigger categorization after a memory is updated."""
-    db = Session(bind=connection)
-    categorize_memory(target, db)
-    db.close()
@@ -1,7 +0,0 @@
-from .apps import router as apps_router
-from .backup import router as backup_router
-from .config import router as config_router
-from .memories import router as memories_router
-from .stats import router as stats_router
-
-__all__ = ["memories_router", "apps_router", "stats_router", "config_router", "backup_router"]
@@ -1,223 +0,0 @@
-from typing import Optional
-from uuid import UUID
-
-from app.database import get_db
-from app.models import App, Memory, MemoryAccessLog, MemoryState
-from fastapi import APIRouter, Depends, HTTPException, Query
-from sqlalchemy import desc, func
-from sqlalchemy.orm import Session, joinedload
-
-router = APIRouter(prefix="/api/v1/apps", tags=["apps"])
-
-# Helper functions
-def get_app_or_404(db: Session, app_id: UUID) -> App:
-    app = db.query(App).filter(App.id == app_id).first()
-    if not app:
-        raise HTTPException(status_code=404, detail="App not found")
-    return app
-
-# List all apps with filtering
-@router.get("/")
-async def list_apps(
-    name: Optional[str] = None,
-    is_active: Optional[bool] = None,
-    sort_by: str = 'name',
-    sort_direction: str = 'asc',
-    page: int = Query(1, ge=1),
-    page_size: int = Query(10, ge=1, le=100),
-    db: Session = Depends(get_db)
-):
-    # Create a subquery for memory counts
-    memory_counts = db.query(
-        Memory.app_id,
-        func.count(Memory.id).label('memory_count')
-    ).filter(
-        Memory.state.in_([MemoryState.active, MemoryState.paused, MemoryState.archived])
-    ).group_by(Memory.app_id).subquery()
-
-    # Create a subquery for access counts
-    access_counts = db.query(
-        MemoryAccessLog.app_id,
-        func.count(func.distinct(MemoryAccessLog.memory_id)).label('access_count')
-    ).group_by(MemoryAccessLog.app_id).subquery()
-
-    # Base query
-    query = db.query(
-        App,
-        func.coalesce(memory_counts.c.memory_count, 0).label('total_memories_created'),
-        func.coalesce(access_counts.c.access_count, 0).label('total_memories_accessed')
-    )
-
-    # Join with subqueries
-    query = query.outerjoin(
-        memory_counts,
-        App.id == memory_counts.c.app_id
-    ).outerjoin(
-        access_counts,
-        App.id == access_counts.c.app_id
-    )
-
-    if name:
-        query = query.filter(App.name.ilike(f"%{name}%"))
-
-    if is_active is not None:
-        query = query.filter(App.is_active == is_active)
-
-    # Apply sorting
-    if sort_by == 'name':
-        sort_field = App.name
-    elif sort_by == 'memories':
-        sort_field = func.coalesce(memory_counts.c.memory_count, 0)
-    elif sort_by == 'memories_accessed':
-        sort_field = func.coalesce(access_counts.c.access_count, 0)
-    else:
-        sort_field = App.name  # default sort
-
-    if sort_direction == 'desc':
-        query = query.order_by(desc(sort_field))
-    else:
-        query = query.order_by(sort_field)
-
-    total = query.count()
-    apps = query.offset((page - 1) * page_size).limit(page_size).all()
-
-    return {
-        "total": total,
-        "page": page,
-        "page_size": page_size,
-        "apps": [
-            {
-                "id": app[0].id,
-                "name": app[0].name,
-                "is_active": app[0].is_active,
-                "total_memories_created": app[1],
-                "total_memories_accessed": app[2]
-            }
-            for app in apps
-        ]
-    }
-
-# Get app details
-@router.get("/{app_id}")
-async def get_app_details(
-    app_id: UUID,
-    db: Session = Depends(get_db)
-):
-    app = get_app_or_404(db, app_id)
-
-    # Get memory access statistics
-    access_stats = db.query(
-        func.count(MemoryAccessLog.id).label("total_memories_accessed"),
-        func.min(MemoryAccessLog.accessed_at).label("first_accessed"),
-        func.max(MemoryAccessLog.accessed_at).label("last_accessed")
-    ).filter(MemoryAccessLog.app_id == app_id).first()
-
-    return {
-        "is_active": app.is_active,
-        "total_memories_created": db.query(Memory)
-            .filter(Memory.app_id == app_id)
-            .count(),
-        "total_memories_accessed": access_stats.total_memories_accessed or 0,
-        "first_accessed": access_stats.first_accessed,
-        "last_accessed": access_stats.last_accessed
-    }
-
-# List memories created by app
-@router.get("/{app_id}/memories")
-async def list_app_memories(
-    app_id: UUID,
-    page: int = Query(1, ge=1),
-    page_size: int = Query(10, ge=1, le=100),
-    db: Session = Depends(get_db)
-):
-    get_app_or_404(db, app_id)
-    query = db.query(Memory).filter(
-        Memory.app_id == app_id,
-        Memory.state.in_([MemoryState.active, MemoryState.paused, MemoryState.archived])
-    )
-    # Add eager loading for categories
-    query = query.options(joinedload(Memory.categories))
-    total = query.count()
-    memories = query.order_by(Memory.created_at.desc()).offset((page - 1) * page_size).limit(page_size).all()
-
-    return {
-        "total": total,
-        "page": page,
-        "page_size": page_size,
-        "memories": [
-            {
-                "id": memory.id,
-                "content": memory.content,
-                "created_at": memory.created_at,
-                "state": memory.state.value,
-                "app_id": memory.app_id,
-                "categories": [category.name for category in memory.categories],
-                "metadata_": memory.metadata_
-            }
-            for memory in memories
-        ]
-    }
-
-# List memories accessed by app
-@router.get("/{app_id}/accessed")
-async def list_app_accessed_memories(
-    app_id: UUID,
-    page: int = Query(1, ge=1),
-    page_size: int = Query(10, ge=1, le=100),
-    db: Session = Depends(get_db)
-):
-    
-    # Get memories with access counts
-    query = db.query(
-        Memory,
-        func.count(MemoryAccessLog.id).label("access_count")
-    ).join(
-        MemoryAccessLog,
-        Memory.id == MemoryAccessLog.memory_id
-    ).filter(
-        MemoryAccessLog.app_id == app_id
-    ).group_by(
-        Memory.id
-    ).order_by(
-        desc("access_count")
-    )
-
-    # Add eager loading for categories
-    query = query.options(joinedload(Memory.categories))
-
-    total = query.count()
-    results = query.offset((page - 1) * page_size).limit(page_size).all()
-
-    return {
-        "total": total,
-        "page": page,
-        "page_size": page_size,
-        "memories": [
-            {
-                "memory": {
-                    "id": memory.id,
-                    "content": memory.content,
-                    "created_at": memory.created_at,
-                    "state": memory.state.value,
-                    "app_id": memory.app_id,
-                    "app_name": memory.app.name if memory.app else None,
-                    "categories": [category.name for category in memory.categories],
-                    "metadata_": memory.metadata_
-                },
-                "access_count": count
-            }
-            for memory, count in results
-        ]
-    }
-
-
-@router.put("/{app_id}")
-async def update_app_details(
-    app_id: UUID,
-    is_active: bool,
-    db: Session = Depends(get_db)
-):
-    app = get_app_or_404(db, app_id)
-    app.is_active = is_active
-    db.commit()
-    return {"status": "success", "message": "Updated app details successfully"}
@@ -1,499 +0,0 @@
-from datetime import UTC, datetime
-import io 
-import json 
-import gzip 
-import zipfile
-from typing import Optional, List, Dict, Any
-from uuid import UUID
-
-from fastapi import APIRouter, Depends, HTTPException, UploadFile, File, Query, Form
-from fastapi.responses import StreamingResponse
-from pydantic import BaseModel
-from sqlalchemy.orm import Session, joinedload
-from sqlalchemy import and_
-
-from app.database import get_db
-from app.models import (
-    User, App, Memory, MemoryState, Category, memory_categories, 
-    MemoryStatusHistory, AccessControl
-)
-from app.utils.memory import get_memory_client
-
-from uuid import uuid4
-
-router = APIRouter(prefix="/api/v1/backup", tags=["backup"])
-
-class ExportRequest(BaseModel):
-    user_id: str
-    app_id: Optional[UUID] = None
-    from_date: Optional[int] = None
-    to_date: Optional[int] = None
-    include_vectors: bool = True
-
-def _iso(dt: Optional[datetime]) -> Optional[str]: 
-    if isinstance(dt, datetime): 
-        try: 
-            return dt.astimezone(UTC).isoformat()
-        except: 
-            return dt.replace(tzinfo=UTC).isoformat()
-    return None
-
-def _parse_iso(dt: Optional[str]) -> Optional[datetime]:
-    if not dt:
-        return None
-    try:
-        return datetime.fromisoformat(dt)
-    except Exception:
-        try:
-            return datetime.fromisoformat(dt.replace("Z", "+00:00"))
-        except Exception:
-            return None
-
-def _export_sqlite(db: Session, req: ExportRequest) -> Dict[str, Any]: 
-    user = db.query(User).filter(User.user_id == req.user_id).first()
-    if not user: 
-        raise HTTPException(status_code=404, detail="User not found")
-    
-    time_filters = []
-    if req.from_date: 
-        time_filters.append(Memory.created_at >= datetime.fromtimestamp(req.from_date, tz=UTC))
-    if req.to_date: 
-        time_filters.append(Memory.created_at <= datetime.fromtimestamp(req.to_date, tz=UTC))
-
-    mem_q = (
-        db.query(Memory)
-        .options(joinedload(Memory.categories), joinedload(Memory.app))
-        .filter(
-            Memory.user_id == user.id, 
-            *(time_filters or []), 
-            * ( [Memory.app_id == req.app_id] if req.app_id else [] ),
-        )
-    )
-
-    memories = mem_q.all()
-    memory_ids = [m.id for m in memories]
-
-    app_ids = sorted({m.app_id for m in memories if m.app_id})
-    apps = db.query(App).filter(App.id.in_(app_ids)).all() if app_ids else []
-
-    cats = sorted({c for m in memories for c in m.categories}, key = lambda c: str(c.id))
-
-    mc_rows = db.execute(
-        memory_categories.select().where(memory_categories.c.memory_id.in_(memory_ids))
-    ).fetchall() if memory_ids else []
-
-    history = db.query(MemoryStatusHistory).filter(MemoryStatusHistory.memory_id.in_(memory_ids)).all() if memory_ids else []
-
-    acls = db.query(AccessControl).filter(
-        AccessControl.subject_type == "app", 
-        AccessControl.subject_id.in_(app_ids) if app_ids else False
-    ).all() if app_ids else []
-
-    return {
-        "user": {
-            "id": str(user.id), 
-            "user_id": user.user_id, 
-            "name": user.name, 
-            "email": user.email, 
-            "metadata": user.metadata_, 
-            "created_at": _iso(user.created_at), 
-            "updated_at": _iso(user.updated_at)
-        }, 
-        "apps": [
-            {
-                "id": str(a.id), 
-                "owner_id": str(a.owner_id), 
-                "name": a.name, 
-                "description": a.description, 
-                "metadata": a.metadata_, 
-                "is_active": a.is_active, 
-                "created_at": _iso(a.created_at), 
-                "updated_at": _iso(a.updated_at),
-            }
-            for a in apps
-        ], 
-        "categories": [
-            {
-                "id": str(c.id), 
-                "name": c.name, 
-                "description": c.description, 
-                "created_at": _iso(c.created_at), 
-                "updated_at": _iso(c.updated_at), 
-            }
-            for c in cats
-        ], 
-        "memories": [
-            {
-                "id": str(m.id), 
-                "user_id": str(m.user_id), 
-                "app_id": str(m.app_id) if m.app_id else None, 
-                "content": m.content, 
-                "metadata": m.metadata_, 
-                "state": m.state.value,
-                "created_at": _iso(m.created_at), 
-                "updated_at": _iso(m.updated_at), 
-                "archived_at": _iso(m.archived_at), 
-                "deleted_at": _iso(m.deleted_at), 
-                "category_ids": [str(c.id) for c in m.categories], #TODO: figure out a way to add category names simply to this
-            }
-            for m in memories
-        ], 
-        "memory_categories": [
-            {"memory_id": str(r.memory_id), "category_id": str(r.category_id)}
-            for r in mc_rows
-        ], 
-        "status_history": [
-            {
-                "id": str(h.id), 
-                "memory_id": str(h.memory_id), 
-                "changed_by": str(h.changed_by), 
-                "old_state": h.old_state.value, 
-                "new_state": h.new_state.value, 
-                "changed_at": _iso(h.changed_at), 
-            }
-            for h in history
-        ], 
-        "access_controls": [
-            {
-                "id": str(ac.id), 
-                "subject_type": ac.subject_type, 
-                "subject_id": str(ac.subject_id) if ac.subject_id else None, 
-                "object_type": ac.object_type, 
-                "object_id": str(ac.object_id) if ac.object_id else None, 
-                "effect": ac.effect, 
-                "created_at": _iso(ac.created_at), 
-            }
-            for ac in acls
-        ], 
-        "export_meta": {
-            "app_id_filter": str(req.app_id) if req.app_id else None,
-            "from_date": req.from_date,
-            "to_date": req.to_date,
-            "version": "1",
-            "generated_at": datetime.now(UTC).isoformat(),
-        },
-    }
-
-def _export_logical_memories_gz(
-        db: Session, 
-        *, 
-        user_id: str, 
-        app_id: Optional[UUID] = None, 
-        from_date: Optional[int] = None, 
-        to_date: Optional[int] = None
-) -> bytes: 
-    """
-    Export a provider-agnostic backup of memories so they can be restored to any vector DB
-    by re-embedding content. One JSON object per line, gzip-compressed.
-
-    Schema (per line):
-    {
-      "id": "<uuid>",
-      "content": "<text>",
-      "metadata": {...},
-      "created_at": "<iso8601 or null>",
-      "updated_at": "<iso8601 or null>",
-      "state": "active|paused|archived|deleted",
-      "app": "<app name or null>",
-      "categories": ["catA", "catB", ...]
-    }
-    """
-
-    user = db.query(User).filter(User.user_id == user_id).first()
-    if not user: 
-        raise HTTPException(status_code=404, detail="User not found")
-    
-    time_filters = []
-    if from_date: 
-        time_filters.append(Memory.created_at >= datetime.fromtimestamp(from_date, tz=UTC))
-    if to_date: 
-        time_filters.append(Memory.created_at <= datetime.fromtimestamp(to_date, tz=UTC))
-    
-    q = (
-        db.query(Memory)
-        .options(joinedload(Memory.categories), joinedload(Memory.app))
-        .filter(
-            Memory.user_id == user.id,
-            *(time_filters or []),
-        )
-    )
-    if app_id:
-        q = q.filter(Memory.app_id == app_id)
-
-    buf = io.BytesIO()
-    with gzip.GzipFile(fileobj=buf, mode="wb") as gz: 
-        for m in q.all(): 
-            record = {
-                "id": str(m.id),
-                "content": m.content,
-                "metadata": m.metadata_ or {},
-                "created_at": _iso(m.created_at),
-                "updated_at": _iso(m.updated_at),
-                "state": m.state.value,
-                "app": m.app.name if m.app else None,
-                "categories": [c.name for c in m.categories],
-            }
-            gz.write((json.dumps(record) + "\n").encode("utf-8"))
-    return buf.getvalue()
-
-@router.post("/export")
-async def export_backup(req: ExportRequest, db: Session = Depends(get_db)): 
-    sqlite_payload = _export_sqlite(db=db, req=req)
-    memories_blob = _export_logical_memories_gz(
-        db=db, 
-        user_id=req.user_id, 
-        app_id=req.app_id, 
-        from_date=req.from_date, 
-        to_date=req.to_date,
-
-    )
-
-    #TODO: add vector store specific exports in future for speed 
-
-    zip_buf = io.BytesIO()
-    with zipfile.ZipFile(zip_buf, "w", compression=zipfile.ZIP_DEFLATED) as zf: 
-        zf.writestr("memories.json", json.dumps(sqlite_payload, indent=2))
-        zf.writestr("memories.jsonl.gz", memories_blob)
-        
-    zip_buf.seek(0)
-    return StreamingResponse(
-        zip_buf, 
-        media_type="application/zip", 
-        headers={"Content-Disposition": f'attachment; filename="memories_export_{req.user_id}.zip"'},
-    )
-
-@router.post("/import")
-async def import_backup(
-    file: UploadFile = File(..., description="Zip with memories.json and memories.jsonl.gz"), 
-    user_id: str = Form(..., description="Import memories into this user_id"),
-    mode: str = Query("overwrite"), 
-    db: Session = Depends(get_db)
-): 
-    if not file.filename.endswith(".zip"): 
-        raise HTTPException(status_code=400, detail="Expected a zip file.")
-    
-    if mode not in {"skip", "overwrite"}:
-        raise HTTPException(status_code=400, detail="Invalid mode. Must be 'skip' or 'overwrite'.")
-    
-    user = db.query(User).filter(User.user_id == user_id).first()
-    if not user: 
-        raise HTTPException(status_code=404, detail="User not found")
-
-    content = await file.read()
-    try:
-        with zipfile.ZipFile(io.BytesIO(content), "r") as zf:
-            names = zf.namelist()
-
-            def find_member(filename: str) -> Optional[str]:
-                for name in names:
-                    # Skip directory entries
-                    if name.endswith('/'):
-                        continue
-                    if name.rsplit('/', 1)[-1] == filename:
-                        return name
-                return None
-
-            sqlite_member = find_member("memories.json")
-            if not sqlite_member:
-                raise HTTPException(status_code=400, detail="memories.json missing in zip")
-
-            memories_member = find_member("memories.jsonl.gz")
-
-            sqlite_data = json.loads(zf.read(sqlite_member))
-            memories_blob = zf.read(memories_member) if memories_member else None
-    except Exception:
-        raise HTTPException(status_code=400, detail="Invalid zip file")
-
-    default_app = db.query(App).filter(App.owner_id == user.id, App.name == "openmemory").first()
-    if not default_app: 
-        default_app = App(owner_id=user.id, name="openmemory", is_active=True, metadata_={})
-        db.add(default_app)
-        db.commit()
-        db.refresh(default_app)
-
-    cat_id_map: Dict[str, UUID] = {}
-    for c in sqlite_data.get("categories", []): 
-        cat = db.query(Category).filter(Category.name == c["name"]).first()
-        if not cat: 
-            cat = Category(name=c["name"], description=c.get("description"))
-            db.add(cat)
-            db.commit()
-            db.refresh(cat)
-        cat_id_map[c["id"]] = cat.id
-
-    old_to_new_id: Dict[str, UUID] = {}
-    for m in sqlite_data.get("memories", []): 
-        incoming_id = UUID(m["id"])
-        existing = db.query(Memory).filter(Memory.id == incoming_id).first()
-
-        # Cross-user collision: always mint a new UUID and import as a new memory
-        if existing and existing.user_id != user.id:
-            target_id = uuid4()
-        else:
-            target_id = incoming_id
-
-        old_to_new_id[m["id"]] = target_id
-
-        # Same-user collision + skip mode: leave existing row untouched
-        if existing and (existing.user_id == user.id) and mode == "skip": 
-            continue 
-        
-        # Same-user collision + overwrite mode: treat import as ground truth
-        if existing and (existing.user_id == user.id) and mode == "overwrite": 
-            incoming_state = m.get("state", "active")
-            existing.user_id = user.id 
-            existing.app_id = default_app.id
-            existing.content = m.get("content") or ""
-            existing.metadata_ = m.get("metadata") or {}
-            try: 
-                existing.state = MemoryState(incoming_state)
-            except Exception: 
-                existing.state = MemoryState.active
-            # Update state-related timestamps from import (ground truth)
-            existing.archived_at = _parse_iso(m.get("archived_at"))
-            existing.deleted_at = _parse_iso(m.get("deleted_at"))
-            existing.created_at = _parse_iso(m.get("created_at")) or existing.created_at
-            existing.updated_at = _parse_iso(m.get("updated_at")) or existing.updated_at
-            db.add(existing)
-            db.commit()
-            continue
-
-        new_mem = Memory(
-            id=target_id,
-            user_id=user.id,
-            app_id=default_app.id,
-            content=m.get("content") or "",
-            metadata_=m.get("metadata") or {},
-            state=MemoryState(m.get("state", "active")) if m.get("state") else MemoryState.active,
-            created_at=_parse_iso(m.get("created_at")) or datetime.now(UTC),
-            updated_at=_parse_iso(m.get("updated_at")) or datetime.now(UTC),
-            archived_at=_parse_iso(m.get("archived_at")),
-            deleted_at=_parse_iso(m.get("deleted_at")),
-        )
-        db.add(new_mem)
-        db.commit()
-
-    for link in sqlite_data.get("memory_categories", []): 
-        mid = old_to_new_id.get(link["memory_id"])
-        cid = cat_id_map.get(link["category_id"])
-        if not (mid and cid): 
-            continue
-        exists = db.execute(
-            memory_categories.select().where(
-                (memory_categories.c.memory_id == mid) & (memory_categories.c.category_id == cid)
-            )
-        ).first()
-
-        if not exists: 
-            db.execute(memory_categories.insert().values(memory_id=mid, category_id=cid))
-            db.commit()
-
-    for h in sqlite_data.get("status_history", []): 
-        hid = UUID(h["id"])
-        mem_id = old_to_new_id.get(h["memory_id"], UUID(h["memory_id"]))
-        exists = db.query(MemoryStatusHistory).filter(MemoryStatusHistory.id == hid).first()
-        if exists and mode == "skip":
-            continue
-        rec = exists if exists else MemoryStatusHistory(id=hid)
-        rec.memory_id = mem_id
-        rec.changed_by = user.id
-        try:
-            rec.old_state = MemoryState(h.get("old_state", "active"))
-            rec.new_state = MemoryState(h.get("new_state", "active"))
-        except Exception:
-            rec.old_state = MemoryState.active
-            rec.new_state = MemoryState.active
-        rec.changed_at = _parse_iso(h.get("changed_at")) or datetime.now(UTC)
-        db.add(rec)
-        db.commit()
-
-    memory_client = get_memory_client()
-    vector_store = getattr(memory_client, "vector_store", None) if memory_client else None
-
-    if vector_store and memory_client and hasattr(memory_client, "embedding_model"):
-        def iter_logical_records():
-            if memories_blob:
-                gz_buf = io.BytesIO(memories_blob)
-                with gzip.GzipFile(fileobj=gz_buf, mode="rb") as gz:
-                    for raw in gz:
-                        yield json.loads(raw.decode("utf-8"))
-            else:
-                for m in sqlite_data.get("memories", []):
-                    yield {
-                        "id": m["id"],
-                        "content": m.get("content"),
-                        "metadata": m.get("metadata") or {},
-                        "created_at": m.get("created_at"),
-                        "updated_at": m.get("updated_at"),
-                    }
-
-        for rec in iter_logical_records():
-            old_id = rec["id"]
-            new_id = old_to_new_id.get(old_id, UUID(old_id))
-            content = rec.get("content") or ""
-            metadata = rec.get("metadata") or {}
-            created_at = rec.get("created_at")
-            updated_at = rec.get("updated_at")
-
-            if mode == "skip":
-                try:
-                    get_fn = getattr(vector_store, "get", None)
-                    if callable(get_fn) and vector_store.get(str(new_id)):
-                        continue
-                except Exception:
-                    pass
-
-            payload = dict(metadata)
-            payload["data"] = content
-            if created_at:
-                payload["created_at"] = created_at
-            if updated_at:
-                payload["updated_at"] = updated_at
-            payload["user_id"] = user_id
-            payload.setdefault("source_app", "openmemory")
-
-            try:
-                vec = memory_client.embedding_model.embed(content, "add")
-                vector_store.insert(vectors=[vec], payloads=[payload], ids=[str(new_id)])
-            except Exception as e:
-                print(f"Vector upsert failed for memory {new_id}: {e}")
-                continue
-
-        return {"message": f'Import completed into user "{user_id}"'}
-
-    return {"message": f'Import completed into user "{user_id}"'}
-
-
-    
-            
-        
- 
-
-
-    
-
-    
-
-
-
-
-
-
-    
-
-    
-
-
-
-
-
-
-
-
-
-
- 
-
-
-
-
@@ -1,291 +0,0 @@
-from typing import Any, Dict, Optional
-
-from app.database import get_db
-from app.models import Config as ConfigModel
-from app.utils.memory import reset_memory_client
-from fastapi import APIRouter, Depends, HTTPException
-from pydantic import BaseModel, Field
-from sqlalchemy.orm import Session
-
-router = APIRouter(prefix="/api/v1/config", tags=["config"])
-
-class LLMConfig(BaseModel):
-    model: str = Field(..., description="LLM model name")
-    temperature: float = Field(..., description="Temperature setting for the model")
-    max_tokens: int = Field(..., description="Maximum tokens to generate")
-    api_key: Optional[str] = Field(None, description="API key or 'env:API_KEY' to use environment variable")
-    ollama_base_url: Optional[str] = Field(None, description="Base URL for Ollama server (e.g., http://host.docker.internal:11434)")
-
-class LLMProvider(BaseModel):
-    provider: str = Field(..., description="LLM provider name")
-    config: LLMConfig
-
-class EmbedderConfig(BaseModel):
-    model: str = Field(..., description="Embedder model name")
-    api_key: Optional[str] = Field(None, description="API key or 'env:API_KEY' to use environment variable")
-    ollama_base_url: Optional[str] = Field(None, description="Base URL for Ollama server (e.g., http://host.docker.internal:11434)")
-
-class EmbedderProvider(BaseModel):
-    provider: str = Field(..., description="Embedder provider name")
-    config: EmbedderConfig
-
-class VectorStoreProvider(BaseModel):
-    provider: str = Field(..., description="Vector store provider name")
-    # Below config can vary widely based on the vector store used. Refer https://docs.mem0.ai/components/vectordbs/config
-    config: Dict[str, Any] = Field(..., description="Vector store-specific configuration")
-
-class OpenMemoryConfig(BaseModel):
-    custom_instructions: Optional[str] = Field(None, description="Custom instructions for memory management and fact extraction")
-
-class Mem0Config(BaseModel):
-    llm: Optional[LLMProvider] = None
-    embedder: Optional[EmbedderProvider] = None
-    vector_store: Optional[VectorStoreProvider] = None
-
-class ConfigSchema(BaseModel):
-    openmemory: Optional[OpenMemoryConfig] = None
-    mem0: Optional[Mem0Config] = None
-
-def get_default_configuration():
-    """Get the default configuration with sensible defaults for LLM and embedder."""
-    return {
-        "openmemory": {
-            "custom_instructions": None
-        },
-        "mem0": {
-            "llm": {
-                "provider": "openai",
-                "config": {
-                    "model": "gpt-4o-mini",
-                    "temperature": 0.1,
-                    "max_tokens": 2000,
-                    "api_key": "env:OPENAI_API_KEY"
-                }
-            },
-            "embedder": {
-                "provider": "openai",
-                "config": {
-                    "model": "text-embedding-3-small",
-                    "api_key": "env:OPENAI_API_KEY"
-                }
-            },
-            "vector_store": None
-        }
-    }
-
-def get_config_from_db(db: Session, key: str = "main"):
-    """Get configuration from database."""
-    config = db.query(ConfigModel).filter(ConfigModel.key == key).first()
-    
-    if not config:
-        # Create default config with proper provider configurations
-        default_config = get_default_configuration()
-        db_config = ConfigModel(key=key, value=default_config)
-        db.add(db_config)
-        db.commit()
-        db.refresh(db_config)
-        return default_config
-    
-    # Ensure the config has all required sections with defaults
-    config_value = config.value
-    default_config = get_default_configuration()
-    
-    # Merge with defaults to ensure all required fields exist
-    if "openmemory" not in config_value:
-        config_value["openmemory"] = default_config["openmemory"]
-    
-    if "mem0" not in config_value:
-        config_value["mem0"] = default_config["mem0"]
-    else:
-        # Ensure LLM config exists with defaults
-        if "llm" not in config_value["mem0"] or config_value["mem0"]["llm"] is None:
-            config_value["mem0"]["llm"] = default_config["mem0"]["llm"]
-        
-        # Ensure embedder config exists with defaults
-        if "embedder" not in config_value["mem0"] or config_value["mem0"]["embedder"] is None:
-            config_value["mem0"]["embedder"] = default_config["mem0"]["embedder"]
-        
-        # Ensure vector_store config exists with defaults
-        if "vector_store" not in config_value["mem0"]:
-            config_value["mem0"]["vector_store"] = default_config["mem0"]["vector_store"]
-
-    # Save the updated config back to database if it was modified
-    if config_value != config.value:
-        config.value = config_value
-        db.commit()
-        db.refresh(config)
-    
-    return config_value
-
-def save_config_to_db(db: Session, config: Dict[str, Any], key: str = "main"):
-    """Save configuration to database."""
-    db_config = db.query(ConfigModel).filter(ConfigModel.key == key).first()
-    
-    if db_config:
-        db_config.value = config
-        db_config.updated_at = None  # Will trigger the onupdate to set current time
-    else:
-        db_config = ConfigModel(key=key, value=config)
-        db.add(db_config)
-        
-    db.commit()
-    db.refresh(db_config)
-    return db_config.value
-
-@router.get("/", response_model=ConfigSchema)
-async def get_configuration(db: Session = Depends(get_db)):
-    """Get the current configuration."""
-    config = get_config_from_db(db)
-    return config
-
-@router.put("/", response_model=ConfigSchema)
-async def update_configuration(config: ConfigSchema, db: Session = Depends(get_db)):
-    """Update the configuration."""
-    current_config = get_config_from_db(db)
-    
-    # Convert to dict for processing
-    updated_config = current_config.copy()
-    
-    # Update openmemory settings if provided
-    if config.openmemory is not None:
-        if "openmemory" not in updated_config:
-            updated_config["openmemory"] = {}
-        updated_config["openmemory"].update(config.openmemory.dict(exclude_none=True))
-    
-    # Update mem0 settings
-    updated_config["mem0"] = config.mem0.dict(exclude_none=True)
-    
-
-@router.patch("/", response_model=ConfigSchema)
-async def patch_configuration(config_update: ConfigSchema, db: Session = Depends(get_db)):
-    """Update parts of the configuration."""
-    current_config = get_config_from_db(db)
-
-    def deep_update(source, overrides):
-        for key, value in overrides.items():
-            if isinstance(value, dict) and key in source and isinstance(source[key], dict):
-                source[key] = deep_update(source[key], value)
-            else:
-                source[key] = value
-        return source
-
-    update_data = config_update.dict(exclude_unset=True)
-    updated_config = deep_update(current_config, update_data)
-
-    save_config_to_db(db, updated_config)
-    reset_memory_client()
-    return updated_config
-
-
-@router.post("/reset", response_model=ConfigSchema)
-async def reset_configuration(db: Session = Depends(get_db)):
-    """Reset the configuration to default values."""
-    try:
-        # Get the default configuration with proper provider setups
-        default_config = get_default_configuration()
-        
-        # Save it as the current configuration in the database
-        save_config_to_db(db, default_config)
-        reset_memory_client()
-        return default_config
-    except Exception as e:
-        raise HTTPException(
-            status_code=500, 
-            detail=f"Failed to reset configuration: {str(e)}"
-        )
-
-@router.get("/mem0/llm", response_model=LLMProvider)
-async def get_llm_configuration(db: Session = Depends(get_db)):
-    """Get only the LLM configuration."""
-    config = get_config_from_db(db)
-    llm_config = config.get("mem0", {}).get("llm", {})
-    return llm_config
-
-@router.put("/mem0/llm", response_model=LLMProvider)
-async def update_llm_configuration(llm_config: LLMProvider, db: Session = Depends(get_db)):
-    """Update only the LLM configuration."""
-    current_config = get_config_from_db(db)
-    
-    # Ensure mem0 key exists
-    if "mem0" not in current_config:
-        current_config["mem0"] = {}
-    
-    # Update the LLM configuration
-    current_config["mem0"]["llm"] = llm_config.dict(exclude_none=True)
-    
-    # Save the configuration to database
-    save_config_to_db(db, current_config)
-    reset_memory_client()
-    return current_config["mem0"]["llm"]
-
-@router.get("/mem0/embedder", response_model=EmbedderProvider)
-async def get_embedder_configuration(db: Session = Depends(get_db)):
-    """Get only the Embedder configuration."""
-    config = get_config_from_db(db)
-    embedder_config = config.get("mem0", {}).get("embedder", {})
-    return embedder_config
-
-@router.put("/mem0/embedder", response_model=EmbedderProvider)
-async def update_embedder_configuration(embedder_config: EmbedderProvider, db: Session = Depends(get_db)):
-    """Update only the Embedder configuration."""
-    current_config = get_config_from_db(db)
-    
-    # Ensure mem0 key exists
-    if "mem0" not in current_config:
-        current_config["mem0"] = {}
-    
-    # Update the Embedder configuration
-    current_config["mem0"]["embedder"] = embedder_config.dict(exclude_none=True)
-    
-    # Save the configuration to database
-    save_config_to_db(db, current_config)
-    reset_memory_client()
-    return current_config["mem0"]["embedder"]
-
-@router.get("/mem0/vector_store", response_model=Optional[VectorStoreProvider])
-async def get_vector_store_configuration(db: Session = Depends(get_db)):
-    """Get only the Vector Store configuration."""
-    config = get_config_from_db(db)
-    vector_store_config = config.get("mem0", {}).get("vector_store", None)
-    return vector_store_config
-
-@router.put("/mem0/vector_store", response_model=VectorStoreProvider)
-async def update_vector_store_configuration(vector_store_config: VectorStoreProvider, db: Session = Depends(get_db)):
-    """Update only the Vector Store configuration."""
-    current_config = get_config_from_db(db)
-    
-    # Ensure mem0 key exists
-    if "mem0" not in current_config:
-        current_config["mem0"] = {}
-    
-    # Update the Vector Store configuration
-    current_config["mem0"]["vector_store"] = vector_store_config.dict(exclude_none=True)
-    
-    # Save the configuration to database
-    save_config_to_db(db, current_config)
-    reset_memory_client()
-    return current_config["mem0"]["vector_store"]
-
-@router.get("/openmemory", response_model=OpenMemoryConfig)
-async def get_openmemory_configuration(db: Session = Depends(get_db)):
-    """Get only the OpenMemory configuration."""
-    config = get_config_from_db(db)
-    openmemory_config = config.get("openmemory", {})
-    return openmemory_config
-
-@router.put("/openmemory", response_model=OpenMemoryConfig)
-async def update_openmemory_configuration(openmemory_config: OpenMemoryConfig, db: Session = Depends(get_db)):
-    """Update only the OpenMemory configuration."""
-    current_config = get_config_from_db(db)
-    
-    # Ensure openmemory key exists
-    if "openmemory" not in current_config:
-        current_config["openmemory"] = {}
-    
-    # Update the OpenMemory configuration
-    current_config["openmemory"].update(openmemory_config.dict(exclude_none=True))
-    
-    # Save the configuration to database
-    save_config_to_db(db, current_config)
-    reset_memory_client()
-    return current_config["openmemory"]
@@ -1,694 +0,0 @@
-import logging
-from datetime import UTC, datetime
-from typing import List, Optional, Set
-from uuid import UUID
-
-from app.database import get_db
-from app.models import (
-    AccessControl,
-    App,
-    Category,
-    Memory,
-    MemoryAccessLog,
-    MemoryState,
-    MemoryStatusHistory,
-    User,
-)
-from app.schemas import MemoryResponse
-from app.utils.memory import get_memory_client
-from app.utils.permissions import check_memory_access_permissions
-from fastapi import APIRouter, Depends, HTTPException, Query
-from fastapi_pagination import Page, Params
-from fastapi_pagination.ext.sqlalchemy import paginate as sqlalchemy_paginate
-from pydantic import BaseModel
-from sqlalchemy import func
-from sqlalchemy.orm import Session, joinedload
-
-router = APIRouter(prefix="/api/v1/memories", tags=["memories"])
-
-
-def get_memory_or_404(db: Session, memory_id: UUID) -> Memory:
-    memory = db.query(Memory).filter(Memory.id == memory_id).first()
-    if not memory:
-        raise HTTPException(status_code=404, detail="Memory not found")
-    return memory
-
-
-def update_memory_state(db: Session, memory_id: UUID, new_state: MemoryState, user_id: UUID):
-    memory = get_memory_or_404(db, memory_id)
-    old_state = memory.state
-
-    # Update memory state
-    memory.state = new_state
-    if new_state == MemoryState.archived:
-        memory.archived_at = datetime.now(UTC)
-    elif new_state == MemoryState.deleted:
-        memory.deleted_at = datetime.now(UTC)
-
-    # Record state change
-    history = MemoryStatusHistory(
-        memory_id=memory_id,
-        changed_by=user_id,
-        old_state=old_state,
-        new_state=new_state
-    )
-    db.add(history)
-    db.commit()
-    return memory
-
-
-def get_accessible_memory_ids(db: Session, app_id: UUID) -> Set[UUID]:
-    """
-    Get the set of memory IDs that the app has access to based on app-level ACL rules.
-    Returns all memory IDs if no specific restrictions are found.
-    """
-    # Get app-level access controls
-    app_access = db.query(AccessControl).filter(
-        AccessControl.subject_type == "app",
-        AccessControl.subject_id == app_id,
-        AccessControl.object_type == "memory"
-    ).all()
-
-    # If no app-level rules exist, return None to indicate all memories are accessible
-    if not app_access:
-        return None
-
-    # Initialize sets for allowed and denied memory IDs
-    allowed_memory_ids = set()
-    denied_memory_ids = set()
-
-    # Process app-level rules
-    for rule in app_access:
-        if rule.effect == "allow":
-            if rule.object_id:  # Specific memory access
-                allowed_memory_ids.add(rule.object_id)
-            else:  # All memories access
-                return None  # All memories allowed
-        elif rule.effect == "deny":
-            if rule.object_id:  # Specific memory denied
-                denied_memory_ids.add(rule.object_id)
-            else:  # All memories denied
-                return set()  # No memories accessible
-
-    # Remove denied memories from allowed set
-    if allowed_memory_ids:
-        allowed_memory_ids -= denied_memory_ids
-
-    return allowed_memory_ids
-
-
-# List all memories with filtering
-@router.get("/", response_model=Page[MemoryResponse])
-async def list_memories(
-    user_id: str,
-    app_id: Optional[UUID] = None,
-    from_date: Optional[int] = Query(
-        None,
-        description="Filter memories created after this date (timestamp)",
-        examples=[1718505600]
-    ),
-    to_date: Optional[int] = Query(
-        None,
-        description="Filter memories created before this date (timestamp)",
-        examples=[1718505600]
-    ),
-    categories: Optional[str] = None,
-    params: Params = Depends(),
-    search_query: Optional[str] = None,
-    sort_column: Optional[str] = Query(None, description="Column to sort by (memory, categories, app_name, created_at)"),
-    sort_direction: Optional[str] = Query(None, description="Sort direction (asc or desc)"),
-    db: Session = Depends(get_db)
-):
-    user = db.query(User).filter(User.user_id == user_id).first()
-    if not user:
-        raise HTTPException(status_code=404, detail="User not found")
-
-    # Build base query
-    query = db.query(Memory).filter(
-        Memory.user_id == user.id,
-        Memory.state != MemoryState.deleted,
-        Memory.state != MemoryState.archived,
-        Memory.content.ilike(f"%{search_query}%") if search_query else True
-    )
-
-    # Apply filters
-    if app_id:
-        query = query.filter(Memory.app_id == app_id)
-
-    if from_date:
-        from_datetime = datetime.fromtimestamp(from_date, tz=UTC)
-        query = query.filter(Memory.created_at >= from_datetime)
-
-    if to_date:
-        to_datetime = datetime.fromtimestamp(to_date, tz=UTC)
-        query = query.filter(Memory.created_at <= to_datetime)
-
-    # Add joins for app and categories after filtering
-    query = query.outerjoin(App, Memory.app_id == App.id)
-    query = query.outerjoin(Memory.categories)
-
-    # Apply category filter if provided
-    if categories:
-        category_list = [c.strip() for c in categories.split(",")]
-        query = query.filter(Category.name.in_(category_list))
-
-    # Apply sorting if specified
-    if sort_column:
-        sort_field = getattr(Memory, sort_column, None)
-        if sort_field:
-            query = query.order_by(sort_field.desc()) if sort_direction == "desc" else query.order_by(sort_field.asc())
-
-    # Add eager loading for app and categories
-    query = query.options(
-        joinedload(Memory.app),
-        joinedload(Memory.categories)
-    ).distinct(Memory.id)
-
-    # Get paginated results with transformer
-    return sqlalchemy_paginate(
-        query,
-        params,
-        transformer=lambda items: [
-            MemoryResponse(
-                id=memory.id,
-                content=memory.content,
-                created_at=memory.created_at,
-                state=memory.state.value,
-                app_id=memory.app_id,
-                app_name=memory.app.name if memory.app else None,
-                categories=[category.name for category in memory.categories],
-                metadata_=memory.metadata_
-            )
-            for memory in items
-            if check_memory_access_permissions(db, memory, app_id)
-        ]
-    )
-
-
-# Get all categories
-@router.get("/categories")
-async def get_categories(
-    user_id: str,
-    db: Session = Depends(get_db)
-):
-    user = db.query(User).filter(User.user_id == user_id).first()
-    if not user:
-        raise HTTPException(status_code=404, detail="User not found")
-
-    # Get unique categories associated with the user's memories
-    # Get all memories
-    memories = db.query(Memory).filter(Memory.user_id == user.id, Memory.state != MemoryState.deleted, Memory.state != MemoryState.archived).all()
-    # Get all categories from memories
-    categories = [category for memory in memories for category in memory.categories]
-    # Get unique categories
-    unique_categories = list(set(categories))
-
-    return {
-        "categories": unique_categories,
-        "total": len(unique_categories)
-    }
-
-
-class CreateMemoryRequest(BaseModel):
-    user_id: str
-    text: str
-    metadata: dict = {}
-    infer: bool = True
-    app: str = "openmemory"
-
-
-# Create new memory
-@router.post("/")
-async def create_memory(
-    request: CreateMemoryRequest,
-    db: Session = Depends(get_db)
-):
-    user = db.query(User).filter(User.user_id == request.user_id).first()
-    if not user:
-        raise HTTPException(status_code=404, detail="User not found")
-    # Get or create app
-    app_obj = db.query(App).filter(App.name == request.app,
-                                   App.owner_id == user.id).first()
-    if not app_obj:
-        app_obj = App(name=request.app, owner_id=user.id)
-        db.add(app_obj)
-        db.commit()
-        db.refresh(app_obj)
-
-    # Check if app is active
-    if not app_obj.is_active:
-        raise HTTPException(status_code=403, detail=f"App {request.app} is currently paused on OpenMemory. Cannot create new memories.")
-
-    # Log what we're about to do
-    logging.info(f"Creating memory for user_id: {request.user_id} with app: {request.app}")
-    
-    # Try to get memory client safely
-    try:
-        memory_client = get_memory_client()
-        if not memory_client:
-            raise Exception("Memory client is not available")
-    except Exception as client_error:
-        logging.warning(f"Memory client unavailable: {client_error}. Creating memory in database only.")
-        # Return a json response with the error
-        return {
-            "error": str(client_error)
-        }
-
-    # Try to save to Qdrant via memory_client
-    try:
-        qdrant_response = memory_client.add(
-            request.text,
-            user_id=request.user_id,  # Use string user_id to match search
-            metadata={
-                "source_app": "openmemory",
-                "mcp_client": request.app,
-            },
-            infer=request.infer
-        )
-        
-        # Log the response for debugging
-        logging.info(f"Qdrant response: {qdrant_response}")
-        
-        # Process Qdrant response
-        if isinstance(qdrant_response, dict) and 'results' in qdrant_response:
-            created_memories = []
-            
-            for result in qdrant_response['results']:
-                if result['event'] == 'ADD':
-                    # Get the Qdrant-generated ID
-                    memory_id = UUID(result['id'])
-                    
-                    # Check if memory already exists
-                    existing_memory = db.query(Memory).filter(Memory.id == memory_id).first()
-                    
-                    if existing_memory:
-                        # Update existing memory
-                        existing_memory.state = MemoryState.active
-                        existing_memory.content = result['memory']
-                        memory = existing_memory
-                    else:
-                        # Create memory with the EXACT SAME ID from Qdrant
-                        memory = Memory(
-                            id=memory_id,  # Use the same ID that Qdrant generated
-                            user_id=user.id,
-                            app_id=app_obj.id,
-                            content=result['memory'],
-                            metadata_=request.metadata,
-                            state=MemoryState.active
-                        )
-                        db.add(memory)
-                    
-                    # Create history entry
-                    history = MemoryStatusHistory(
-                        memory_id=memory_id,
-                        changed_by=user.id,
-                        old_state=MemoryState.deleted if existing_memory else MemoryState.deleted,
-                        new_state=MemoryState.active
-                    )
-                    db.add(history)
-                    
-                    created_memories.append(memory)
-            
-            # Commit all changes at once
-            if created_memories:
-                db.commit()
-                for memory in created_memories:
-                    db.refresh(memory)
-                
-                # Return the first memory (for API compatibility)
-                # but all memories are now saved to the database
-                return created_memories[0]
-    except Exception as qdrant_error:
-        logging.warning(f"Qdrant operation failed: {qdrant_error}.")
-        # Return a json response with the error
-        return {
-            "error": str(qdrant_error)
-        }
-
-
-
-
-# Get memory by ID
-@router.get("/{memory_id}")
-async def get_memory(
-    memory_id: UUID,
-    db: Session = Depends(get_db)
-):
-    memory = get_memory_or_404(db, memory_id)
-    return {
-        "id": memory.id,
-        "text": memory.content,
-        "created_at": int(memory.created_at.timestamp()),
-        "state": memory.state.value,
-        "app_id": memory.app_id,
-        "app_name": memory.app.name if memory.app else None,
-        "categories": [category.name for category in memory.categories],
-        "metadata_": memory.metadata_
-    }
-
-
-class DeleteMemoriesRequest(BaseModel):
-    memory_ids: List[UUID]
-    user_id: str
-
-# Delete multiple memories
-@router.delete("/")
-async def delete_memories(
-    request: DeleteMemoriesRequest,
-    db: Session = Depends(get_db)
-):
-    user = db.query(User).filter(User.user_id == request.user_id).first()
-    if not user:
-        raise HTTPException(status_code=404, detail="User not found")
-
-    # Get memory client to delete from vector store
-    try:
-        memory_client = get_memory_client()
-        if not memory_client:
-            raise HTTPException(
-                status_code=503,
-                detail="Memory client is not available"
-            )
-    except HTTPException:
-        raise
-    except Exception as client_error:
-        logging.error(f"Memory client initialization failed: {client_error}")
-        raise HTTPException(
-            status_code=503,
-            detail=f"Memory service unavailable: {str(client_error)}"
-        )
-
-    # Delete from vector store then mark as deleted in database
-    for memory_id in request.memory_ids:
-        try:
-            memory_client.delete(str(memory_id))
-        except Exception as delete_error:
-            logging.warning(f"Failed to delete memory {memory_id} from vector store: {delete_error}")
-
-        update_memory_state(db, memory_id, MemoryState.deleted, user.id)
-
-    return {"message": f"Successfully deleted {len(request.memory_ids)} memories"}
-
-
-# Archive memories
-@router.post("/actions/archive")
-async def archive_memories(
-    memory_ids: List[UUID],
-    user_id: UUID,
-    db: Session = Depends(get_db)
-):
-    for memory_id in memory_ids:
-        update_memory_state(db, memory_id, MemoryState.archived, user_id)
-    return {"message": f"Successfully archived {len(memory_ids)} memories"}
-
-
-class PauseMemoriesRequest(BaseModel):
-    memory_ids: Optional[List[UUID]] = None
-    category_ids: Optional[List[UUID]] = None
-    app_id: Optional[UUID] = None
-    all_for_app: bool = False
-    global_pause: bool = False
-    state: Optional[MemoryState] = None
-    user_id: str
-
-# Pause access to memories
-@router.post("/actions/pause")
-async def pause_memories(
-    request: PauseMemoriesRequest,
-    db: Session = Depends(get_db)
-):
-    
-    global_pause = request.global_pause
-    all_for_app = request.all_for_app
-    app_id = request.app_id
-    memory_ids = request.memory_ids
-    category_ids = request.category_ids
-    state = request.state or MemoryState.paused
-
-    user = db.query(User).filter(User.user_id == request.user_id).first()
-    if not user:
-        raise HTTPException(status_code=404, detail="User not found")
-    
-    user_id = user.id
-    
-    if global_pause:
-        # Pause all memories
-        memories = db.query(Memory).filter(
-            Memory.state != MemoryState.deleted,
-            Memory.state != MemoryState.archived
-        ).all()
-        for memory in memories:
-            update_memory_state(db, memory.id, state, user_id)
-        return {"message": "Successfully paused all memories"}
-
-    if app_id:
-        # Pause all memories for an app
-        memories = db.query(Memory).filter(
-            Memory.app_id == app_id,
-            Memory.user_id == user.id,
-            Memory.state != MemoryState.deleted,
-            Memory.state != MemoryState.archived
-        ).all()
-        for memory in memories:
-            update_memory_state(db, memory.id, state, user_id)
-        return {"message": f"Successfully paused all memories for app {app_id}"}
-    
-    if all_for_app and memory_ids:
-        # Pause all memories for an app
-        memories = db.query(Memory).filter(
-            Memory.user_id == user.id,
-            Memory.state != MemoryState.deleted,
-            Memory.id.in_(memory_ids)
-        ).all()
-        for memory in memories:
-            update_memory_state(db, memory.id, state, user_id)
-        return {"message": "Successfully paused all memories"}
-
-    if memory_ids:
-        # Pause specific memories
-        for memory_id in memory_ids:
-            update_memory_state(db, memory_id, state, user_id)
-        return {"message": f"Successfully paused {len(memory_ids)} memories"}
-
-    if category_ids:
-        # Pause memories by category
-        memories = db.query(Memory).join(Memory.categories).filter(
-            Category.id.in_(category_ids),
-            Memory.state != MemoryState.deleted,
-            Memory.state != MemoryState.archived
-        ).all()
-        for memory in memories:
-            update_memory_state(db, memory.id, state, user_id)
-        return {"message": f"Successfully paused memories in {len(category_ids)} categories"}
-
-    raise HTTPException(status_code=400, detail="Invalid pause request parameters")
-
-
-# Get memory access logs
-@router.get("/{memory_id}/access-log")
-async def get_memory_access_log(
-    memory_id: UUID,
-    page: int = Query(1, ge=1),
-    page_size: int = Query(10, ge=1, le=100),
-    db: Session = Depends(get_db)
-):
-    query = db.query(MemoryAccessLog).filter(MemoryAccessLog.memory_id == memory_id)
-    total = query.count()
-    logs = query.order_by(MemoryAccessLog.accessed_at.desc()).offset((page - 1) * page_size).limit(page_size).all()
-
-    # Get app name
-    for log in logs:
-        app = db.query(App).filter(App.id == log.app_id).first()
-        log.app_name = app.name if app else None
-
-    return {
-        "total": total,
-        "page": page,
-        "page_size": page_size,
-        "logs": logs
-    }
-
-
-class UpdateMemoryRequest(BaseModel):
-    memory_content: str
-    user_id: str
-
-# Update a memory
-@router.put("/{memory_id}")
-async def update_memory(
-    memory_id: UUID,
-    request: UpdateMemoryRequest,
-    db: Session = Depends(get_db)
-):
-    user = db.query(User).filter(User.user_id == request.user_id).first()
-    if not user:
-        raise HTTPException(status_code=404, detail="User not found")
-    memory = get_memory_or_404(db, memory_id)
-    memory.content = request.memory_content
-    db.commit()
-    db.refresh(memory)
-    return memory
-
-class FilterMemoriesRequest(BaseModel):
-    user_id: str
-    page: int = 1
-    size: int = 10
-    search_query: Optional[str] = None
-    app_ids: Optional[List[UUID]] = None
-    category_ids: Optional[List[UUID]] = None
-    sort_column: Optional[str] = None
-    sort_direction: Optional[str] = None
-    from_date: Optional[int] = None
-    to_date: Optional[int] = None
-    show_archived: Optional[bool] = False
-
-@router.post("/filter", response_model=Page[MemoryResponse])
-async def filter_memories(
-    request: FilterMemoriesRequest,
-    db: Session = Depends(get_db)
-):
-    user = db.query(User).filter(User.user_id == request.user_id).first()
-    if not user:
-        raise HTTPException(status_code=404, detail="User not found")
-
-    # Build base query
-    query = db.query(Memory).filter(
-        Memory.user_id == user.id,
-        Memory.state != MemoryState.deleted,
-    )
-
-    # Filter archived memories based on show_archived parameter
-    if not request.show_archived:
-        query = query.filter(Memory.state != MemoryState.archived)
-
-    # Apply search filter
-    if request.search_query:
-        query = query.filter(Memory.content.ilike(f"%{request.search_query}%"))
-
-    # Apply app filter
-    if request.app_ids:
-        query = query.filter(Memory.app_id.in_(request.app_ids))
-
-    # Add joins for app and categories
-    query = query.outerjoin(App, Memory.app_id == App.id)
-
-    # Apply category filter
-    if request.category_ids:
-        query = query.join(Memory.categories).filter(Category.id.in_(request.category_ids))
-    else:
-        query = query.outerjoin(Memory.categories)
-
-    # Apply date filters
-    if request.from_date:
-        from_datetime = datetime.fromtimestamp(request.from_date, tz=UTC)
-        query = query.filter(Memory.created_at >= from_datetime)
-
-    if request.to_date:
-        to_datetime = datetime.fromtimestamp(request.to_date, tz=UTC)
-        query = query.filter(Memory.created_at <= to_datetime)
-
-    # Apply sorting
-    if request.sort_column and request.sort_direction:
-        sort_direction = request.sort_direction.lower()
-        if sort_direction not in ['asc', 'desc']:
-            raise HTTPException(status_code=400, detail="Invalid sort direction")
-
-        sort_mapping = {
-            'memory': Memory.content,
-            'app_name': App.name,
-            'created_at': Memory.created_at
-        }
-
-        if request.sort_column not in sort_mapping:
-            raise HTTPException(status_code=400, detail="Invalid sort column")
-
-        sort_field = sort_mapping[request.sort_column]
-        if sort_direction == 'desc':
-            query = query.order_by(sort_field.desc())
-        else:
-            query = query.order_by(sort_field.asc())
-    else:
-        # Default sorting
-        query = query.order_by(Memory.created_at.desc())
-
-    # Add eager loading for categories and make the query distinct
-    query = query.options(
-        joinedload(Memory.categories)
-    ).distinct(Memory.id)
-
-    # Use fastapi-pagination's paginate function
-    return sqlalchemy_paginate(
-        query,
-        Params(page=request.page, size=request.size),
-        transformer=lambda items: [
-            MemoryResponse(
-                id=memory.id,
-                content=memory.content,
-                created_at=memory.created_at,
-                state=memory.state.value,
-                app_id=memory.app_id,
-                app_name=memory.app.name if memory.app else None,
-                categories=[category.name for category in memory.categories],
-                metadata_=memory.metadata_
-            )
-            for memory in items
-        ]
-    )
-
-
-@router.get("/{memory_id}/related", response_model=Page[MemoryResponse])
-async def get_related_memories(
-    memory_id: UUID,
-    user_id: str,
-    params: Params = Depends(),
-    db: Session = Depends(get_db)
-):
-    # Validate user
-    user = db.query(User).filter(User.user_id == user_id).first()
-    if not user:
-        raise HTTPException(status_code=404, detail="User not found")
-    
-    # Get the source memory
-    memory = get_memory_or_404(db, memory_id)
-    
-    # Extract category IDs from the source memory
-    category_ids = [category.id for category in memory.categories]
-    
-    if not category_ids:
-        return Page.create([], total=0, params=params)
-    
-    # Build query for related memories
-    query = db.query(Memory).distinct(Memory.id).filter(
-        Memory.user_id == user.id,
-        Memory.id != memory_id,
-        Memory.state != MemoryState.deleted
-    ).join(Memory.categories).filter(
-        Category.id.in_(category_ids)
-    ).options(
-        joinedload(Memory.categories),
-        joinedload(Memory.app)
-    ).order_by(
-        func.count(Category.id).desc(),
-        Memory.created_at.desc()
-    ).group_by(Memory.id)
-    
-    # ⚡ Force page size to be 5
-    params = Params(page=params.page, size=5)
-    
-    return sqlalchemy_paginate(
-        query,
-        params,
-        transformer=lambda items: [
-            MemoryResponse(
-                id=memory.id,
-                content=memory.content,
-                created_at=memory.created_at,
-                state=memory.state.value,
-                app_id=memory.app_id,
-                app_name=memory.app.name if memory.app else None,
-                categories=[category.name for category in memory.categories],
-                metadata_=memory.metadata_
-            )
-            for memory in items
-        ]
-    )
@@ -1,29 +0,0 @@
-from app.database import get_db
-from app.models import App, Memory, MemoryState, User
-from fastapi import APIRouter, Depends, HTTPException
-from sqlalchemy.orm import Session
-
-router = APIRouter(prefix="/api/v1/stats", tags=["stats"])
-
-@router.get("/")
-async def get_profile(
-    user_id: str,
-    db: Session = Depends(get_db)
-):
-    user = db.query(User).filter(User.user_id == user_id).first()
-    if not user:
-        raise HTTPException(status_code=404, detail="User not found")
-    
-    # Get total number of memories
-    total_memories = db.query(Memory).filter(Memory.user_id == user.id, Memory.state != MemoryState.deleted).count()
-
-    # Get total number of apps
-    apps = db.query(App).filter(App.owner == user)
-    total_apps = apps.count()
-
-    return {
-        "total_memories": total_memories,
-        "total_apps": total_apps,
-        "apps": apps.all()
-    }
-
@@ -1,65 +0,0 @@
-from datetime import datetime
-from typing import List, Optional
-from uuid import UUID
-
-from pydantic import BaseModel, ConfigDict, Field, validator
-
-
-class MemoryBase(BaseModel):
-    content: str
-    metadata_: Optional[dict] = Field(default_factory=dict)
-
-class MemoryCreate(MemoryBase):
-    user_id: UUID
-    app_id: UUID
-
-
-class Category(BaseModel):
-    name: str
-
-
-class App(BaseModel):
-    id: UUID
-    name: str
-
-
-class Memory(MemoryBase):
-    id: UUID
-    user_id: UUID
-    app_id: UUID
-    created_at: datetime
-    updated_at: Optional[datetime] = None
-    state: str
-    categories: Optional[List[Category]] = None
-    app: App
-
-    model_config = ConfigDict(from_attributes=True)
-
-class MemoryUpdate(BaseModel):
-    content: Optional[str] = None
-    metadata_: Optional[dict] = None
-    state: Optional[str] = None
-
-
-class MemoryResponse(BaseModel):
-    id: UUID
-    content: str
-    created_at: int
-    state: str
-    app_id: UUID
-    app_name: str
-    categories: List[str]
-    metadata_: Optional[dict] = None
-
-    @validator('created_at', pre=True)
-    def convert_to_epoch(cls, v):
-        if isinstance(v, datetime):
-            return int(v.timestamp())
-        return v
-
-class PaginatedMemoryResponse(BaseModel):
-    items: List[MemoryResponse]
-    total: int
-    page: int
-    size: int
-    pages: int
@@ -1,43 +0,0 @@
-import logging
-from typing import List
-
-from app.utils.prompts import MEMORY_CATEGORIZATION_PROMPT
-from dotenv import load_dotenv
-from openai import OpenAI
-from pydantic import BaseModel
-from tenacity import retry, stop_after_attempt, wait_exponential
-
-load_dotenv()
-openai_client = OpenAI()
-
-
-class MemoryCategories(BaseModel):
-    categories: List[str]
-
-
-@retry(stop=stop_after_attempt(3), wait=wait_exponential(multiplier=1, min=4, max=15))
-def get_categories_for_memory(memory: str) -> List[str]:
-    try:
-        messages = [
-            {"role": "system", "content": MEMORY_CATEGORIZATION_PROMPT},
-            {"role": "user", "content": memory}
-        ]
-
-        # Let OpenAI handle the pydantic parsing directly
-        completion = openai_client.beta.chat.completions.parse(
-            model="gpt-4o-mini",
-            messages=messages,
-            response_format=MemoryCategories,
-            temperature=0
-        )
-
-        parsed: MemoryCategories = completion.choices[0].message.parsed
-        return [cat.strip().lower() for cat in parsed.categories]
-
-    except Exception as e:
-        logging.error(f"[ERROR] Failed to get categories: {e}")
-        try:
-            logging.debug(f"[DEBUG] Raw response: {completion.choices[0].message.content}")
-        except Exception as debug_e:
-            logging.debug(f"[DEBUG] Could not extract raw response: {debug_e}")
-        raise
@@ -1,33 +0,0 @@
-from typing import Tuple
-
-from app.models import App, User
-from sqlalchemy.orm import Session
-
-
-def get_or_create_user(db: Session, user_id: str) -> User:
-    """Get or create a user with the given user_id"""
-    user = db.query(User).filter(User.user_id == user_id).first()
-    if not user:
-        user = User(user_id=user_id)
-        db.add(user)
-        db.commit()
-        db.refresh(user)
-    return user
-
-
-def get_or_create_app(db: Session, user: User, app_id: str) -> App:
-    """Get or create an app for the given user"""
-    app = db.query(App).filter(App.owner_id == user.id, App.name == app_id).first()
-    if not app:
-        app = App(owner_id=user.id, name=app_id)
-        db.add(app)
-        db.commit()
-        db.refresh(app)
-    return app
-
-
-def get_user_and_app(db: Session, user_id: str, app_id: str) -> Tuple[User, App]:
-    """Get or create both user and their app"""
-    user = get_or_create_user(db, user_id)
-    app = get_or_create_app(db, user, app_id)
-    return user, app
@@ -1,504 +0,0 @@
-"""
-Memory client utilities for OpenMemory.
-
-This module provides functionality to initialize and manage the Mem0 memory client
-with automatic configuration management and Docker environment support.
-
-Docker Ollama Configuration:
-When running inside a Docker container and using Ollama as the LLM or embedder provider,
-the system automatically detects the Docker environment and adjusts localhost URLs
-to properly reach the host machine where Ollama is running.
-
-Supported Docker host resolution (in order of preference):
-1. OLLAMA_HOST environment variable (if set)
-2. host.docker.internal (Docker Desktop for Mac/Windows)
-3. Docker bridge gateway IP (typically 172.17.0.1 on Linux)
-4. Fallback to 172.17.0.1
-
-Example configuration that will be automatically adjusted:
-{
-    "llm": {
-        "provider": "ollama",
-        "config": {
-            "model": "llama3.1:latest",
-            "ollama_base_url": "http://localhost:11434"  # Auto-adjusted in Docker
-        }
-    }
-}
-"""
-
-import hashlib
-import json
-import os
-import socket
-
-from app.database import SessionLocal
-from app.models import Config as ConfigModel
-
-from mem0 import Memory
-
-_memory_client = None
-_config_hash = None
-
-
-def _get_config_hash(config_dict):
-    """Generate a hash of the config to detect changes."""
-    config_str = json.dumps(config_dict, sort_keys=True)
-    return hashlib.md5(config_str.encode()).hexdigest()
-
-
-def _get_docker_host_url():
-    """
-    Determine the appropriate host URL to reach host machine from inside Docker container.
-    Returns the best available option for reaching the host from inside a container.
-    """
-    # Check for custom environment variable first
-    custom_host = os.environ.get('OLLAMA_HOST')
-    if custom_host:
-        print(f"Using custom Ollama host from OLLAMA_HOST: {custom_host}")
-        return custom_host.replace('http://', '').replace('https://', '').split(':')[0]
-    
-    # Check if we're running inside Docker
-    if not os.path.exists('/.dockerenv'):
-        # Not in Docker, return localhost as-is
-        return "localhost"
-    
-    print("Detected Docker environment, adjusting host URL for Ollama...")
-    
-    # Try different host resolution strategies
-    host_candidates = []
-    
-    # 1. host.docker.internal (works on Docker Desktop for Mac/Windows)
-    try:
-        socket.gethostbyname('host.docker.internal')
-        host_candidates.append('host.docker.internal')
-        print("Found host.docker.internal")
-    except socket.gaierror:
-        pass
-    
-    # 2. Docker bridge gateway (typically 172.17.0.1 on Linux)
-    try:
-        with open('/proc/net/route', 'r') as f:
-            for line in f:
-                fields = line.strip().split()
-                if fields[1] == '00000000':  # Default route
-                    gateway_hex = fields[2]
-                    gateway_ip = socket.inet_ntoa(bytes.fromhex(gateway_hex)[::-1])
-                    host_candidates.append(gateway_ip)
-                    print(f"Found Docker gateway: {gateway_ip}")
-                    break
-    except (FileNotFoundError, IndexError, ValueError):
-        pass
-    
-    # 3. Fallback to common Docker bridge IP
-    if not host_candidates:
-        host_candidates.append('172.17.0.1')
-        print("Using fallback Docker bridge IP: 172.17.0.1")
-    
-    # Return the first available candidate
-    return host_candidates[0]
-
-
-def _fix_ollama_urls(config_section):
-    """
-    Fix Ollama URLs for Docker environment.
-    Replaces localhost URLs with appropriate Docker host URLs.
-    Sets default ollama_base_url if not provided.
-    """
-    if not config_section or "config" not in config_section:
-        return config_section
-    
-    ollama_config = config_section["config"]
-    
-    # Set default ollama_base_url if not provided
-    if "ollama_base_url" not in ollama_config:
-        ollama_config["ollama_base_url"] = "http://host.docker.internal:11434"
-    else:
-        # Check for ollama_base_url and fix if it's localhost
-        url = ollama_config["ollama_base_url"]
-        if "localhost" in url or "127.0.0.1" in url:
-            docker_host = _get_docker_host_url()
-            if docker_host != "localhost":
-                new_url = url.replace("localhost", docker_host).replace("127.0.0.1", docker_host)
-                ollama_config["ollama_base_url"] = new_url
-                print(f"Adjusted Ollama URL from {url} to {new_url}")
-    
-    return config_section
-
-
-def reset_memory_client():
-    """Reset the global memory client to force reinitialization with new config."""
-    global _memory_client, _config_hash
-    _memory_client = None
-    _config_hash = None
-
-
-# --- LLM provider config factories ---
-
-def _build_ollama_llm_config(model, api_key, base_url, ollama_base_url):
-    config = {"model": model or "llama3.1:latest"}
-    # OLLAMA_BASE_URL takes precedence, then LLM_BASE_URL, then default
-    config["ollama_base_url"] = ollama_base_url or base_url or "http://localhost:11434"
-    return config
-
-
-def _build_openai_llm_config(model, api_key, base_url, ollama_base_url):
-    config = {
-        "model": model or "gpt-4o-mini",
-        "api_key": api_key or "env:OPENAI_API_KEY",
-    }
-    if base_url:
-        config["openai_base_url"] = base_url
-    return config
-
-
-_LLM_CONFIG_FACTORIES = {
-    "ollama": _build_ollama_llm_config,
-    "openai": _build_openai_llm_config,
-}
-
-
-def _create_llm_config(provider, model, api_key, base_url, ollama_base_url):
-    """Build LLM config using registered provider factory or generic fallback."""
-    base_config = {
-        "temperature": 0.1,
-        "max_tokens": 2000,
-    }
-
-    factory = _LLM_CONFIG_FACTORIES.get(provider)
-    if factory:
-        base_config.update(factory(model, api_key, base_url, ollama_base_url))
-    else:
-        # Generic provider (anthropic, groq, together, deepseek, etc.)
-        if not model:
-            raise ValueError(
-                f"LLM_MODEL environment variable is required when using LLM_PROVIDER='{provider}'. "
-                f"Set LLM_MODEL to a valid model name for the '{provider}' provider."
-            )
-        base_config["model"] = model
-        if api_key:
-            base_config["api_key"] = api_key
-
-    return base_config
-
-
-# --- Embedder provider config factories ---
-
-def _build_ollama_embedder_config(model, api_key, base_url, ollama_base_url, llm_base_url):
-    config = {"model": model or "nomic-embed-text"}
-    config["ollama_base_url"] = base_url or ollama_base_url or llm_base_url or "http://localhost:11434"
-    return config
-
-
-def _build_openai_embedder_config(model, api_key, base_url, ollama_base_url, llm_base_url):
-    config = {
-        "model": model or "text-embedding-3-small",
-        "api_key": api_key or "env:OPENAI_API_KEY",
-    }
-    if base_url:
-        config["openai_base_url"] = base_url
-    return config
-
-
-_EMBEDDER_CONFIG_FACTORIES = {
-    "ollama": _build_ollama_embedder_config,
-    "openai": _build_openai_embedder_config,
-}
-
-
-def _create_embedder_config(provider, model, api_key, base_url, ollama_base_url, llm_base_url):
-    """Build embedder config using registered provider factory or generic fallback."""
-    factory = _EMBEDDER_CONFIG_FACTORIES.get(provider)
-    if factory:
-        config = factory(model, api_key, base_url, ollama_base_url, llm_base_url)
-    else:
-        if not model:
-            raise ValueError(
-                f"EMBEDDER_MODEL environment variable is required when using EMBEDDER_PROVIDER='{provider}'. "
-                f"Set EMBEDDER_MODEL to a valid model name for the '{provider}' provider."
-            )
-        config = {"model": model}
-        if api_key:
-            config["api_key"] = api_key
-
-    return config
-
-
-def get_default_memory_config():
-    """Get default memory client configuration with sensible defaults."""
-    # Detect vector store based on environment variables
-    vector_store_config = {
-        "collection_name": "openmemory",
-        "host": "mem0_store",
-    }
-    
-    # Check for different vector store configurations based on environment variables
-    if os.environ.get('CHROMA_HOST') and os.environ.get('CHROMA_PORT'):
-        vector_store_provider = "chroma"
-        vector_store_config.update({
-            "host": os.environ.get('CHROMA_HOST'),
-            "port": int(os.environ.get('CHROMA_PORT'))
-        })
-    elif os.environ.get('QDRANT_HOST') and os.environ.get('QDRANT_PORT'):
-        vector_store_provider = "qdrant"
-        vector_store_config.update({
-            "host": os.environ.get('QDRANT_HOST'),
-            "port": int(os.environ.get('QDRANT_PORT'))
-        })
-    elif os.environ.get('WEAVIATE_CLUSTER_URL') or (os.environ.get('WEAVIATE_HOST') and os.environ.get('WEAVIATE_PORT')):
-        vector_store_provider = "weaviate"
-        # Prefer an explicit cluster URL if provided; otherwise build from host/port
-        cluster_url = os.environ.get('WEAVIATE_CLUSTER_URL')
-        if not cluster_url:
-            weaviate_host = os.environ.get('WEAVIATE_HOST')
-            weaviate_port = int(os.environ.get('WEAVIATE_PORT'))
-            cluster_url = f"http://{weaviate_host}:{weaviate_port}"
-        vector_store_config = {
-            "collection_name": "openmemory",
-            "cluster_url": cluster_url
-        }
-    elif os.environ.get('REDIS_URL'):
-        vector_store_provider = "redis"
-        vector_store_config = {
-            "collection_name": "openmemory",
-            "redis_url": os.environ.get('REDIS_URL')
-        }
-    elif os.environ.get('PG_HOST') and os.environ.get('PG_PORT'):
-        vector_store_provider = "pgvector"
-        vector_store_config.update({
-            "host": os.environ.get('PG_HOST'),
-            "port": int(os.environ.get('PG_PORT')),
-            "dbname": os.environ.get('PG_DB', 'mem0'),
-            "user": os.environ.get('PG_USER', 'mem0'),
-            "password": os.environ.get('PG_PASSWORD', 'mem0')
-        })
-    elif os.environ.get('MILVUS_HOST') and os.environ.get('MILVUS_PORT'):
-        vector_store_provider = "milvus"
-        # Construct the full URL as expected by MilvusDBConfig
-        milvus_host = os.environ.get('MILVUS_HOST')
-        milvus_port = int(os.environ.get('MILVUS_PORT'))
-        milvus_url = f"http://{milvus_host}:{milvus_port}"
-        
-        vector_store_config = {
-            "collection_name": "openmemory",
-            "url": milvus_url,
-            "token": os.environ.get('MILVUS_TOKEN', ''),  # Always include, empty string for local setup
-            "db_name": os.environ.get('MILVUS_DB_NAME', ''),
-            "embedding_model_dims": 1536,
-            "metric_type": "COSINE"  # Using COSINE for better semantic similarity
-        }
-    elif os.environ.get('ELASTICSEARCH_HOST') and os.environ.get('ELASTICSEARCH_PORT'):
-        vector_store_provider = "elasticsearch"
-        # Construct the full URL with scheme since Elasticsearch client expects it
-        elasticsearch_host = os.environ.get('ELASTICSEARCH_HOST')
-        elasticsearch_port = int(os.environ.get('ELASTICSEARCH_PORT'))
-        # Use http:// scheme since we're not using SSL
-        full_host = f"http://{elasticsearch_host}"
-        
-        vector_store_config.update({
-            "host": full_host,
-            "port": elasticsearch_port,
-            "user": os.environ.get('ELASTICSEARCH_USER', 'elastic'),
-            "password": os.environ.get('ELASTICSEARCH_PASSWORD', 'changeme'),
-            "verify_certs": False,
-            "use_ssl": False,
-            "embedding_model_dims": 1536
-        })
-    elif os.environ.get('OPENSEARCH_HOST') and os.environ.get('OPENSEARCH_PORT'):
-        vector_store_provider = "opensearch"
-        vector_store_config.update({
-            "host": os.environ.get('OPENSEARCH_HOST'),
-            "port": int(os.environ.get('OPENSEARCH_PORT'))
-        })
-    elif os.environ.get('FAISS_PATH'):
-        vector_store_provider = "faiss"
-        vector_store_config = {
-            "collection_name": "openmemory",
-            "path": os.environ.get('FAISS_PATH'),
-            "embedding_model_dims": 1536,
-            "distance_strategy": "cosine"
-        }
-    else:
-        # Default fallback to Qdrant
-        vector_store_provider = "qdrant"
-        vector_store_config.update({
-            "port": 6333,
-        })
-    
-    print(f"Auto-detected vector store: {vector_store_provider} with config: {vector_store_config}")
-
-    # Detect LLM provider from environment variables
-    llm_provider = os.environ.get('LLM_PROVIDER', 'openai').lower()
-    llm_model = os.environ.get('LLM_MODEL')
-    llm_api_key = os.environ.get('LLM_API_KEY')
-    llm_base_url = os.environ.get('LLM_BASE_URL')
-    ollama_base_url = os.environ.get('OLLAMA_BASE_URL')
-
-    llm_config = _create_llm_config(
-        provider=llm_provider,
-        model=llm_model,
-        api_key=llm_api_key,
-        base_url=llm_base_url,
-        ollama_base_url=ollama_base_url,
-    )
-    print(f"Auto-detected LLM provider: {llm_provider}")
-
-    # Detect embedder provider from environment variables
-    embedder_provider = os.environ.get('EMBEDDER_PROVIDER', llm_provider if llm_provider == 'ollama' else 'openai').lower()
-    embedder_model = os.environ.get('EMBEDDER_MODEL')
-    embedder_api_key = os.environ.get('EMBEDDER_API_KEY')
-    embedder_base_url = os.environ.get('EMBEDDER_BASE_URL')
-
-    embedder_config = _create_embedder_config(
-        provider=embedder_provider,
-        model=embedder_model,
-        api_key=embedder_api_key,
-        base_url=embedder_base_url,
-        ollama_base_url=ollama_base_url,
-        llm_base_url=llm_base_url,
-    )
-    print(f"Auto-detected embedder provider: {embedder_provider}")
-
-    return {
-        "vector_store": {
-            "provider": vector_store_provider,
-            "config": vector_store_config
-        },
-        "llm": {
-            "provider": llm_provider,
-            "config": llm_config
-        },
-        "embedder": {
-            "provider": embedder_provider,
-            "config": embedder_config
-        },
-        "version": "v1.1"
-    }
-
-
-def _parse_environment_variables(config_dict):
-    """
-    Parse environment variables in config values.
-    Converts 'env:VARIABLE_NAME' to actual environment variable values.
-    """
-    if isinstance(config_dict, dict):
-        parsed_config = {}
-        for key, value in config_dict.items():
-            if isinstance(value, str) and value.startswith("env:"):
-                env_var = value.split(":", 1)[1]
-                env_value = os.environ.get(env_var)
-                if env_value:
-                    parsed_config[key] = env_value
-                    print(f"Loaded {env_var} from environment for {key}")
-                else:
-                    print(f"Warning: Environment variable {env_var} not found, keeping original value")
-                    parsed_config[key] = value
-            elif isinstance(value, dict):
-                parsed_config[key] = _parse_environment_variables(value)
-            else:
-                parsed_config[key] = value
-        return parsed_config
-    return config_dict
-
-
-def get_memory_client(custom_instructions: str = None):
-    """
-    Get or initialize the Mem0 client.
-
-    Args:
-        custom_instructions: Optional instructions for the memory project.
-
-    Returns:
-        Initialized Mem0 client instance or None if initialization fails.
-
-    Raises:
-        Exception: If required API keys are not set or critical configuration is missing.
-    """
-    global _memory_client, _config_hash
-
-    try:
-        # Start with default configuration
-        config = get_default_memory_config()
-        
-        # Variable to track custom instructions
-        db_custom_instructions = None
-        
-        # Load configuration from database
-        try:
-            db = SessionLocal()
-            db_config = db.query(ConfigModel).filter(ConfigModel.key == "main").first()
-            
-            if db_config:
-                json_config = db_config.value
-                
-                # Extract custom instructions from openmemory settings
-                if "openmemory" in json_config and "custom_instructions" in json_config["openmemory"]:
-                    db_custom_instructions = json_config["openmemory"]["custom_instructions"]
-                
-                # Override defaults with configurations from the database
-                if "mem0" in json_config:
-                    mem0_config = json_config["mem0"]
-                    
-                    # Update LLM configuration if available
-                    if "llm" in mem0_config and mem0_config["llm"] is not None:
-                        config["llm"] = mem0_config["llm"]
-
-                    # Update Embedder configuration if available
-                    if "embedder" in mem0_config and mem0_config["embedder"] is not None:
-                        config["embedder"] = mem0_config["embedder"]
-
-                    if "vector_store" in mem0_config and mem0_config["vector_store"] is not None:
-                        config["vector_store"] = mem0_config["vector_store"]
-            else:
-                print("No configuration found in database, using defaults")
-                    
-            db.close()
-                            
-        except Exception as e:
-            print(f"Warning: Error loading configuration from database: {e}")
-            print("Using default configuration")
-            # Continue with default configuration if database config can't be loaded
-
-        # Use custom_instructions parameter first, then fall back to database value
-        instructions_to_use = custom_instructions or db_custom_instructions
-        if instructions_to_use:
-            config["custom_fact_extraction_prompt"] = instructions_to_use
-
-        # Fix Ollama URLs for Docker environment (applies to both env-var defaults and DB overrides)
-        if config.get("llm", {}).get("provider") == "ollama":
-            config["llm"] = _fix_ollama_urls(config["llm"])
-        if config.get("embedder", {}).get("provider") == "ollama":
-            config["embedder"] = _fix_ollama_urls(config["embedder"])
-
-        # ALWAYS parse environment variables in the final config
-        # This ensures that even default config values like "env:OPENAI_API_KEY" get parsed
-        print("Parsing environment variables in final config...")
-        config = _parse_environment_variables(config)
-
-        # Check if config has changed by comparing hashes
-        current_config_hash = _get_config_hash(config)
-        
-        # Only reinitialize if config changed or client doesn't exist
-        if _memory_client is None or _config_hash != current_config_hash:
-            print(f"Initializing memory client with config hash: {current_config_hash}")
-            try:
-                _memory_client = Memory.from_config(config_dict=config)
-                _config_hash = current_config_hash
-                print("Memory client initialized successfully")
-            except Exception as init_error:
-                print(f"Warning: Failed to initialize memory client: {init_error}")
-                print("Server will continue running with limited memory functionality")
-                _memory_client = None
-                _config_hash = None
-                return None
-        
-        return _memory_client
-        
-    except Exception as e:
-        print(f"Warning: Exception occurred while initializing memory client: {e}")
-        print("Server will continue running with limited memory functionality")
-        return None
-
-
-def get_default_user_id():
-    return "default_user"
@@ -1,53 +0,0 @@
-from typing import Optional
-from uuid import UUID
-
-from app.models import App, Memory, MemoryState
-from sqlalchemy.orm import Session
-
-
-def check_memory_access_permissions(
-    db: Session,
-    memory: Memory,
-    app_id: Optional[UUID] = None
-) -> bool:
-    """
-    Check if the given app has permission to access a memory based on:
-    1. Memory state (must be active)
-    2. App state (must not be paused)
-    3. App-specific access controls
-
-    Args:
-        db: Database session
-        memory: Memory object to check access for
-        app_id: Optional app ID to check permissions for
-
-    Returns:
-        bool: True if access is allowed, False otherwise
-    """
-    # Check if memory is active
-    if memory.state != MemoryState.active:
-        return False
-
-    # If no app_id provided, only check memory state
-    if not app_id:
-        return True
-
-    # Check if app exists and is active
-    app = db.query(App).filter(App.id == app_id).first()
-    if not app:
-        return False
-
-    # Check if app is paused/inactive
-    if not app.is_active:
-        return False
-
-    # Check app-specific access controls
-    from app.routers.memories import get_accessible_memory_ids
-    accessible_memory_ids = get_accessible_memory_ids(db, app_id)
-
-    # If accessible_memory_ids is None, all memories are accessible
-    if accessible_memory_ids is None:
-        return True
-
-    # Check if memory is in the accessible set
-    return memory.id in accessible_memory_ids
@@ -1,28 +0,0 @@
-MEMORY_CATEGORIZATION_PROMPT = """Your task is to assign each piece of information (or “memory”) to one or more of the following categories. Feel free to use multiple categories per item when appropriate.
-
- Personal: family, friends, home, hobbies, lifestyle
- Relationships: social network, significant others, colleagues
- Preferences: likes, dislikes, habits, favorite media
- Health: physical fitness, mental health, diet, sleep
- Travel: trips, commutes, favorite places, itineraries
- Work: job roles, companies, projects, promotions
- Education: courses, degrees, certifications, skills development
- Projects: to‑dos, milestones, deadlines, status updates
- AI, ML & Technology: infrastructure, algorithms, tools, research
- Technical Support: bug reports, error logs, fixes
- Finance: income, expenses, investments, billing
- Shopping: purchases, wishlists, returns, deliveries
- Legal: contracts, policies, regulations, privacy
- Entertainment: movies, music, games, books, events
- Messages: emails, SMS, alerts, reminders
- Customer Support: tickets, inquiries, resolutions
- Product Feedback: ratings, bug reports, feature requests
- News: articles, headlines, trending topics
- Organization: meetings, appointments, calendars
- Goals: ambitions, KPIs, long‑term objectives
-
-Guidelines:
- Return only the categories under 'categories' key in the JSON format.
- If you cannot categorize the memory, return an empty list with key 'categories'.
- Don't limit yourself to the categories listed above only. Feel free to create new categories based on the memory. Make sure that it is a single phrase.
-"""
@@ -1,20 +0,0 @@
-{
-    "mem0": {
-        "llm": {
-            "provider": "openai",
-            "config": {
-                "model": "gpt-4o-mini",
-                "temperature": 0.1,
-                "max_tokens": 2000,
-                "api_key": "env:API_KEY"
-            }
-        },
-        "embedder": {
-            "provider": "openai",
-            "config": {
-                "model": "text-embedding-3-small",
-                "api_key": "env:API_KEY"
-            }
-        }
-    }
-}
@@ -1,20 +0,0 @@
-{
-    "mem0": {
-        "llm": {
-            "provider": "openai",
-            "config": {
-                "model": "gpt-4o-mini",
-                "temperature": 0.1,
-                "max_tokens": 2000,
-                "api_key": "env:OPENAI_API_KEY"
-            }
-        },
-        "embedder": {
-            "provider": "openai",
-            "config": {
-                "model": "text-embedding-3-small",
-                "api_key": "env:OPENAI_API_KEY"
-            }
-        }
-    }
-} 
@@ -1,89 +0,0 @@
-import datetime
-from uuid import uuid4
-
-from app.config import DEFAULT_APP_ID, USER_ID
-from app.database import Base, SessionLocal, engine
-from app.mcp_server import setup_mcp_server
-from app.models import App, User
-from app.routers import apps_router, backup_router, config_router, memories_router, stats_router
-from fastapi import FastAPI
-from fastapi.middleware.cors import CORSMiddleware
-from fastapi_pagination import add_pagination
-
-app = FastAPI(title="OpenMemory API")
-
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["*"],
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-
-# Create all tables
-Base.metadata.create_all(bind=engine)
-
-# Check for USER_ID and create default user if needed
-def create_default_user():
-    db = SessionLocal()
-    try:
-        # Check if user exists
-        user = db.query(User).filter(User.user_id == USER_ID).first()
-        if not user:
-            # Create default user
-            user = User(
-                id=uuid4(),
-                user_id=USER_ID,
-                name="Default User",
-                created_at=datetime.datetime.now(datetime.UTC)
-            )
-            db.add(user)
-            db.commit()
-    finally:
-        db.close()
-
-
-def create_default_app():
-    db = SessionLocal()
-    try:
-        user = db.query(User).filter(User.user_id == USER_ID).first()
-        if not user:
-            return
-
-        # Check if app already exists
-        existing_app = db.query(App).filter(
-            App.name == DEFAULT_APP_ID,
-            App.owner_id == user.id
-        ).first()
-
-        if existing_app:
-            return
-
-        app = App(
-            id=uuid4(),
-            name=DEFAULT_APP_ID,
-            owner_id=user.id,
-            created_at=datetime.datetime.now(datetime.UTC),
-            updated_at=datetime.datetime.now(datetime.UTC),
-        )
-        db.add(app)
-        db.commit()
-    finally:
-        db.close()
-
-# Create default user on startup
-create_default_user()
-create_default_app()
-
-# Setup MCP server
-setup_mcp_server(app)
-
-# Include routers
-app.include_router(memories_router)
-app.include_router(apps_router)
-app.include_router(stats_router)
-app.include_router(config_router)
-app.include_router(backup_router)
-
-# Add pagination support
-add_pagination(app)
@@ -1,20 +0,0 @@
-fastapi>=0.68.0
-uvicorn>=0.15.0
-sqlalchemy>=1.4.0
-python-dotenv>=1.2.2
-alembic>=1.7.0
-psycopg2-binary>=2.9.0
-python-multipart>=0.0.27
-urllib3>=2.7.0
-fastapi-pagination>=0.12.0
-mem0ai>=0.1.92
-openai>=1.40.0
-mcp[cli]>=1.25.4
-starlette>=0.40.0
-pytest>=7.0.0
-pytest-asyncio>=0.21.0
-httpx>=0.24.0
-pytest-cov>=4.0.0
-tenacity==9.1.2
-anthropic==0.51.0
-ollama==0.4.8
@@ -1,396 +0,0 @@
-"""Tests for the MCP server endpoints (SSE and Streamable HTTP transports).
-
-Covers the Streamable HTTP transport (MCP spec 2025-03-26+) and the legacy SSE
-transport.  Tests exercise the full JSON-RPC flow — initialize, tools/list,
-tools/call — as well as error handling and context-variable isolation.
-"""
-
-import os
-
-# Set dummy keys before any imports that trigger client initialization
-os.environ.setdefault("OPENAI_API_KEY", "test-key")
-
-import pytest
-import pytest_asyncio
-from httpx import ASGITransport, AsyncClient
-
-from app.mcp_server import client_name_var, mcp, mcp_router, user_id_var
-
-# MCP Streamable HTTP requires the Accept header to include application/json.
-# Including text/event-stream as well satisfies GET (SSE) requests.
-MCP_HEADERS = {"Accept": "application/json, text/event-stream"}
-
-
-# ---------------------------------------------------------------------------
-# Fixtures
-# ---------------------------------------------------------------------------
-
-@pytest.fixture
-def test_app():
-    """Create a minimal FastAPI app with just the MCP router for testing."""
-    from fastapi import FastAPI
-
-    app = FastAPI()
-    app.include_router(mcp_router)
-    return app
-
-
-@pytest_asyncio.fixture
-async def client(test_app):
-    """Async HTTP client wired to the test app via ASGI transport."""
-    transport = ASGITransport(app=test_app)
-    async with AsyncClient(transport=transport, base_url="http://test") as ac:
-        yield ac
-
-
-# ---------------------------------------------------------------------------
-# Helpers
-# ---------------------------------------------------------------------------
-
-def _jsonrpc(method: str, params: dict | None = None, req_id: int = 1) -> dict:
-    """Build a JSON-RPC 2.0 request envelope."""
-    return {
-        "jsonrpc": "2.0",
-        "id": req_id,
-        "method": method,
-        "params": params or {},
-    }
-
-
-def _initialize_payload(req_id: int = 1) -> dict:
-    return _jsonrpc(
-        "initialize",
-        {
-            "protocolVersion": "2025-03-26",
-            "capabilities": {},
-            "clientInfo": {"name": "test-client", "version": "0.1.0"},
-        },
-        req_id=req_id,
-    )
-
-
-# ---------------------------------------------------------------------------
-# Streamable HTTP — route existence & basic protocol
-# ---------------------------------------------------------------------------
-
-class TestStreamableHTTPBasic:
-    """Verify the Streamable HTTP route is registered and responds."""
-
-    @pytest.mark.asyncio
-    async def test_post_initialize(self, client):
-        """POST initialize should return a valid JSON-RPC result."""
-        resp = await client.post(
-            "/mcp/testclient/http/user1",
-            json=_initialize_payload(),
-            headers=MCP_HEADERS,
-        )
-        assert resp.status_code == 200
-        data = resp.json()
-        assert data["jsonrpc"] == "2.0"
-        assert data["id"] == 1
-        assert "result" in data
-        result = data["result"]
-        assert "serverInfo" in result
-        assert "capabilities" in result
-        assert result["protocolVersion"] == "2025-03-26"
-
-    @pytest.mark.asyncio
-    async def test_delete_returns_method_not_allowed(self, client):
-        """DELETE in stateless mode should return 405 (no session to terminate)."""
-        resp = await client.delete(
-            "/mcp/testclient/http/user1",
-            headers=MCP_HEADERS,
-        )
-        assert resp.status_code == 405
-
-    @pytest.mark.asyncio
-    async def test_missing_accept_header_returns_406(self, client):
-        """POST without the required Accept header should return 406."""
-        resp = await client.post(
-            "/mcp/testclient/http/user1",
-            json=_initialize_payload(),
-        )
-        assert resp.status_code == 406
-
-    @pytest.mark.asyncio
-    async def test_invalid_json_returns_400(self, client):
-        """POST with unparseable body should return 400."""
-        resp = await client.post(
-            "/mcp/testclient/http/user1",
-            content=b"not json",
-            headers={**MCP_HEADERS, "Content-Type": "application/json"},
-        )
-        assert resp.status_code == 400
-
-    @pytest.mark.asyncio
-    async def test_route_not_found_for_wrong_path(self, client):
-        """Requests to a non-existent path should 404."""
-        resp = await client.post(
-            "/mcp/testclient/nonexistent/user1",
-            json=_initialize_payload(),
-            headers=MCP_HEADERS,
-        )
-        assert resp.status_code == 404
-
-
-# ---------------------------------------------------------------------------
-# Streamable HTTP — full protocol flow
-# ---------------------------------------------------------------------------
-
-class TestStreamableHTTPProtocol:
-    """End-to-end JSON-RPC flows over Streamable HTTP."""
-
-    @pytest.mark.asyncio
-    async def test_tools_list(self, client):
-        """tools/list should return all registered MCP tools."""
-        init_resp = await client.post(
-            "/mcp/testclient/http/user1",
-            json=_initialize_payload(),
-            headers=MCP_HEADERS,
-        )
-        assert init_resp.status_code == 200
-
-        resp = await client.post(
-            "/mcp/testclient/http/user1",
-            json=_jsonrpc("tools/list", req_id=2),
-            headers=MCP_HEADERS,
-        )
-        assert resp.status_code == 200
-        data = resp.json()
-        assert "result" in data
-        tool_names = {t["name"] for t in data["result"]["tools"]}
-        expected = {"add_memories", "search_memory", "list_memories",
-                    "delete_memories", "delete_all_memories"}
-        assert expected.issubset(tool_names), f"Missing tools: {expected - tool_names}"
-
-    @pytest.mark.asyncio
-    async def test_tools_list_has_descriptions(self, client):
-        """Every tool returned by tools/list should have a non-empty description."""
-        await client.post(
-            "/mcp/testclient/http/user1",
-            json=_initialize_payload(),
-            headers=MCP_HEADERS,
-        )
-        resp = await client.post(
-            "/mcp/testclient/http/user1",
-            json=_jsonrpc("tools/list", req_id=2),
-            headers=MCP_HEADERS,
-        )
-        for tool in resp.json()["result"]["tools"]:
-            assert tool.get("description"), f"Tool {tool['name']} has no description"
-
-    @pytest.mark.asyncio
-    async def test_tools_list_has_input_schemas(self, client):
-        """Every tool should declare an inputSchema."""
-        await client.post(
-            "/mcp/testclient/http/user1",
-            json=_initialize_payload(),
-            headers=MCP_HEADERS,
-        )
-        resp = await client.post(
-            "/mcp/testclient/http/user1",
-            json=_jsonrpc("tools/list", req_id=2),
-            headers=MCP_HEADERS,
-        )
-        for tool in resp.json()["result"]["tools"]:
-            assert "inputSchema" in tool, f"Tool {tool['name']} missing inputSchema"
-
-    @pytest.mark.asyncio
-    async def test_call_unknown_tool_returns_error(self, client):
-        """Calling a non-existent tool should return a JSON-RPC error."""
-        await client.post(
-            "/mcp/testclient/http/user1",
-            json=_initialize_payload(),
-            headers=MCP_HEADERS,
-        )
-        resp = await client.post(
-            "/mcp/testclient/http/user1",
-            json=_jsonrpc("tools/call", {"name": "no_such_tool", "arguments": {}}, req_id=2),
-            headers=MCP_HEADERS,
-        )
-        assert resp.status_code == 200
-        data = resp.json()
-        assert "error" in data or (
-            "result" in data and data["result"].get("isError")
-        )
-
-    @pytest.mark.asyncio
-    async def test_unknown_jsonrpc_method(self, client):
-        """An unknown JSON-RPC method should return an error."""
-        resp = await client.post(
-            "/mcp/testclient/http/user1",
-            json=_jsonrpc("nonexistent/method"),
-            headers=MCP_HEADERS,
-        )
-        assert resp.status_code in (200, 400)
-
-    @pytest.mark.asyncio
-    async def test_response_content_type_is_json(self, client):
-        """Responses should have Content-Type: application/json."""
-        resp = await client.post(
-            "/mcp/testclient/http/user1",
-            json=_initialize_payload(),
-            headers=MCP_HEADERS,
-        )
-        ct = resp.headers.get("content-type", "")
-        assert "application/json" in ct
-
-
-# ---------------------------------------------------------------------------
-# Streamable HTTP — context variable handling
-# ---------------------------------------------------------------------------
-
-class TestStreamableHTTPContext:
-    """Verify that user_id and client_name context variables are set correctly."""
-
-    @pytest.mark.asyncio
-    async def test_context_vars_set_during_tool_call(self, client):
-        """Context vars should reflect the path parameters during tool execution."""
-        captured = {}
-
-        @mcp.tool(name="__test_ctx", description="test only")
-        async def _capture(query: str = "") -> str:
-            captured["user_id"] = user_id_var.get(None)
-            captured["client_name"] = client_name_var.get(None)
-            return "ok"
-
-        try:
-            await client.post(
-                "/mcp/my-app/http/alice",
-                json=_initialize_payload(),
-                headers=MCP_HEADERS,
-            )
-            resp = await client.post(
-                "/mcp/my-app/http/alice",
-                json=_jsonrpc("tools/call", {"name": "__test_ctx", "arguments": {}}, req_id=2),
-                headers=MCP_HEADERS,
-            )
-            assert resp.status_code == 200
-            assert captured.get("user_id") == "alice"
-            assert captured.get("client_name") == "my-app"
-        finally:
-            mcp._tool_manager._tools.pop("__test_ctx", None)
-
-    @pytest.mark.asyncio
-    async def test_different_users_are_isolated(self, client):
-        """Sequential requests with different user_ids must not leak state."""
-        results = []
-
-        @mcp.tool(name="__test_uid_iso", description="test only")
-        async def _capture_uid(query: str = "") -> str:
-            results.append(user_id_var.get(None))
-            return "ok"
-
-        try:
-            for uid in ("userA", "userB", "userC"):
-                await client.post(
-                    f"/mcp/app1/http/{uid}",
-                    json=_initialize_payload(),
-                    headers=MCP_HEADERS,
-                )
-                await client.post(
-                    f"/mcp/app1/http/{uid}",
-                    json=_jsonrpc("tools/call", {"name": "__test_uid_iso", "arguments": {}}, req_id=2),
-                    headers=MCP_HEADERS,
-                )
-
-            assert results == ["userA", "userB", "userC"]
-        finally:
-            mcp._tool_manager._tools.pop("__test_uid_iso", None)
-
-    @pytest.mark.asyncio
-    async def test_different_clients_are_isolated(self, client):
-        """Sequential requests with different client_names must not leak state."""
-        results = []
-
-        @mcp.tool(name="__test_cn_iso", description="test only")
-        async def _capture_cn(query: str = "") -> str:
-            results.append(client_name_var.get(None))
-            return "ok"
-
-        try:
-            for cn in ("cursor", "windsurf", "claude"):
-                await client.post(
-                    f"/mcp/{cn}/http/user1",
-                    json=_initialize_payload(),
-                    headers=MCP_HEADERS,
-                )
-                await client.post(
-                    f"/mcp/{cn}/http/user1",
-                    json=_jsonrpc("tools/call", {"name": "__test_cn_iso", "arguments": {}}, req_id=2),
-                    headers=MCP_HEADERS,
-                )
-
-            assert results == ["cursor", "windsurf", "claude"]
-        finally:
-            mcp._tool_manager._tools.pop("__test_cn_iso", None)
-
-
-# ---------------------------------------------------------------------------
-# Streamable HTTP — response correctness
-# ---------------------------------------------------------------------------
-
-class TestStreamableHTTPResponses:
-    """Verify that captured responses are returned correctly to the caller."""
-
-    @pytest.mark.asyncio
-    async def test_error_status_codes_are_preserved(self, client):
-        """Transport error codes (e.g. 406) must be forwarded, not masked as 200."""
-        resp = await client.post(
-            "/mcp/testclient/http/user1",
-            json=_initialize_payload(),
-        )
-        assert resp.status_code == 406
-
-    @pytest.mark.asyncio
-    async def test_delete_status_code_preserved(self, client):
-        """DELETE 405 from stateless transport must not be masked."""
-        resp = await client.delete(
-            "/mcp/testclient/http/user1",
-            headers=MCP_HEADERS,
-        )
-        assert resp.status_code == 405
-
-    @pytest.mark.asyncio
-    async def test_multiple_sequential_requests(self, client):
-        """Multiple requests in sequence should each get independent responses."""
-        for i in range(5):
-            resp = await client.post(
-                "/mcp/testclient/http/user1",
-                json=_initialize_payload(req_id=i + 1),
-                headers=MCP_HEADERS,
-            )
-            assert resp.status_code == 200
-            data = resp.json()
-            assert data["id"] == i + 1
-            assert "result" in data
-
-    @pytest.mark.asyncio
-    async def test_wrong_content_type_returns_error(self, client):
-        """POST with wrong Content-Type should return an error status."""
-        resp = await client.post(
-            "/mcp/testclient/http/user1",
-            content=b'{"jsonrpc":"2.0","id":1,"method":"initialize","params":{}}',
-            headers={**MCP_HEADERS, "Content-Type": "text/plain"},
-        )
-        assert resp.status_code in (400, 415)
-
-
-# ---------------------------------------------------------------------------
-# Route registration
-# ---------------------------------------------------------------------------
-
-class TestRouteRegistration:
-    """Verify all expected routes are registered in the router."""
-
-    def test_sse_route_is_registered(self, test_app):
-        routes = [r.path for r in test_app.routes if hasattr(r, "path")]
-        assert "/mcp/{client_name}/sse/{user_id}" in routes
-
-    def test_sse_post_messages_route_is_registered(self, test_app):
-        routes = [r.path for r in test_app.routes if hasattr(r, "path")]
-        assert "/mcp/messages/" in routes or "/mcp/{client_name}/sse/{user_id}/messages/" in routes
-
-    def test_streamable_http_route_is_registered(self, test_app):
-        routes = [r.path for r in test_app.routes if hasattr(r, "path")]
-        assert "/mcp/{client_name}/http/{user_id}" in routes
@@ -1,393 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-# Export OpenMemory data from a running Docker container without relying on API endpoints.
-# Produces: memories.json + memories.jsonl.gz zipped as memories_export_<USER_ID>.zip
-#
-# Requirements:
-# - docker available locally
-# - The target container has Python + SQLAlchemy and access to the same DATABASE_URL it uses in prod
-#
-# Usage:
-#   ./export_openmemory.sh --user-id <USER_ID> [--container <NAME_OR_ID>] [--app-id <UUID>] [--from-date <epoch_secs>] [--to-date <epoch_secs>]
-#
-# Notes:
-# - USER_ID is the external user identifier (e.g., "vikramiyer"), not the internal UUID.
-# - If --container is omitted, the script uses container name "openmemory-openmemory-mcp-1".
-# - The script writes intermediate files to /tmp inside the container, then docker cp's them out and zips locally.
-
-usage() {
-  echo "Usage: $0 --user-id <USER_ID> [--container <NAME_OR_ID>] [--app-id <UUID>] [--from-date <epoch_secs>] [--to-date <epoch_secs>]"
-  exit 1
-}
-
-USER_ID=""
-CONTAINER=""
-APP_ID=""
-FROM_DATE=""
-TO_DATE=""
-
-while [[ $# -gt 0 ]]; do
-  case "$1" in
-    --user-id) USER_ID="${2:-}"; shift 2 ;;
-    --container) CONTAINER="${2:-}"; shift 2 ;;
-    --app-id) APP_ID="${2:-}"; shift 2 ;;
-    --from-date) FROM_DATE="${2:-}"; shift 2 ;;
-    --to-date) TO_DATE="${2:-}"; shift 2 ;;
-    -h|--help) usage ;;
-    *) echo "Unknown arg: $1"; usage ;;
-  esac
-done
-
-if [[ -z "${USER_ID}" ]]; then
-  echo "ERROR: --user-id is required"
-  usage
-fi
-
-if [[ -z "${CONTAINER}" ]]; then
-  CONTAINER="openmemory-openmemory-mcp-1"
-fi
-
-# Verify the container exists and is running
-if ! docker ps --format '{{.Names}}' | grep -qx "${CONTAINER}"; then
-  echo "ERROR: Container '${CONTAINER}' not found/running. Pass --container <NAME_OR_ID> if different."
-  exit 1
-fi
-
-# Verify python is available inside the container
-if ! docker exec "${CONTAINER}" sh -lc 'command -v python3 >/dev/null 2>&1 || command -v python >/dev/null 2>&1'; then
-  echo "ERROR: Python is not available in container ${CONTAINER}"
-  exit 1
-fi
-
-PY_BIN="python3"
-if ! docker exec "${CONTAINER}" sh -lc 'command -v python3 >/dev/null 2>&1'; then
-  PY_BIN="python"
-fi
-
-echo "Using container: ${CONTAINER}"
-echo "Exporting data for user_id: ${USER_ID}"
-
-# Run Python inside the container to generate memories.json and memories.jsonl.gz in /tmp
-set +e
-cat <<'PYCODE' | docker exec -i \
-  -e EXPORT_USER_ID="${USER_ID}" \
-  -e EXPORT_APP_ID="${APP_ID}" \
-  -e EXPORT_FROM_DATE="${FROM_DATE}" \
-  -e EXPORT_TO_DATE="${TO_DATE}" \
-  "${CONTAINER}" "${PY_BIN}" -
-import os
-import sys
-import json
-import gzip
-import uuid
-import datetime
-from typing import Any, Dict, List
-
-try:
-    from sqlalchemy import create_engine, text
-except Exception as e:
-    print(f"ERROR: SQLAlchemy not available inside the container: {e}", file=sys.stderr)
-    sys.exit(3)
-
-def _iso(dt):
-    if dt is None:
-        return None
-    try:
-        if isinstance(dt, str):
-            try:
-                dt_obj = datetime.datetime.fromisoformat(dt.replace("Z", "+00:00"))
-            except Exception:
-                return dt
-        else:
-            dt_obj = dt
-        if dt_obj.tzinfo is None:
-            dt_obj = dt_obj.replace(tzinfo=datetime.timezone.utc)
-        else:
-            dt_obj = dt_obj.astimezone(datetime.timezone.utc)
-        return dt_obj.isoformat()
-    except Exception:
-        return None
-
-def _json_load_maybe(val):
-    if isinstance(val, (dict, list)) or val is None:
-        return val
-    if isinstance(val, (bytes, bytearray)):
-        try:
-            return json.loads(val.decode("utf-8"))
-        except Exception:
-            try:
-                return val.decode("utf-8", "ignore")
-            except Exception:
-                return None
-    if isinstance(val, str):
-        try:
-            return json.loads(val)
-        except Exception:
-            return val
-    return val
-
-def _named_in_clause(prefix: str, items: List[Any]):
-    names = [f":{prefix}{i}" for i in range(len(items))]
-    params = {f"{prefix}{i}": items[i] for i in range(len(items))}
-    return ", ".join(names), params
-
-DATABASE_URL = os.getenv("DATABASE_URL", "sqlite:///./openmemory.db")
-user_id_str = os.getenv("EXPORT_USER_ID")
-app_id_filter = os.getenv("EXPORT_APP_ID") or None
-from_date = os.getenv("EXPORT_FROM_DATE")
-to_date = os.getenv("EXPORT_TO_DATE")
-
-if not user_id_str:
-    print("Missing EXPORT_USER_ID", file=sys.stderr)
-    sys.exit(2)
-
-from_ts = None
-to_ts = None
-try:
-    if from_date:
-        from_ts = int(from_date)
-    if to_date:
-        to_ts = int(to_date)
-except Exception:
-    pass
-
-engine = create_engine(DATABASE_URL)
-
-with engine.connect() as conn:
-    user_row = conn.execute(
-        text("SELECT id, user_id, name, email, metadata, created_at, updated_at FROM users WHERE user_id = :uid"),
-        {"uid": user_id_str}
-    ).mappings().first()
-    if not user_row:
-        print(f'User not found for user_id "{user_id_str}"', file=sys.stderr)
-        sys.exit(1)
-
-    user_uuid = user_row["id"]
-
-    # Build memories filter
-    params = {"user_id": user_uuid}
-    conditions = ["user_id = :user_id"]
-    if from_ts is not None:
-        params["from_dt"] = datetime.datetime.fromtimestamp(from_ts, tz=datetime.timezone.utc)
-        conditions.append("created_at >= :from_dt")
-    if to_ts is not None:
-        params["to_dt"] = datetime.datetime.fromtimestamp(to_ts, tz=datetime.timezone.utc)
-        conditions.append("created_at <= :to_dt")
-    if app_id_filter:
-        try:
-            # Accept UUID or raw DB value
-            app_uuid = uuid.UUID(app_id_filter)
-            params["app_id"] = str(app_uuid)
-        except Exception:
-            params["app_id"] = app_id_filter
-        conditions.append("app_id = :app_id")
-
-    mem_sql = f"""
-      SELECT id, user_id, app_id, content, metadata, state, created_at, updated_at, archived_at, deleted_at
-      FROM memories
-      WHERE {' AND '.join(conditions)}
-    """
-    mem_rows = list(conn.execute(text(mem_sql), params).mappings())
-    memory_ids = [r["id"] for r in mem_rows]
-    app_ids = sorted({r["app_id"] for r in mem_rows if r["app_id"] is not None})
-
-    # memory_categories
-    mc_rows = []
-    if memory_ids:
-        names, in_params = _named_in_clause("mid", memory_ids)
-        mc_rows = list(conn.execute(
-            text(f"SELECT memory_id, category_id FROM memory_categories WHERE memory_id IN ({names})"),
-            in_params
-        ).mappings())
-
-    # categories for referenced category_ids
-    cats = []
-    cat_ids = sorted({r["category_id"] for r in mc_rows})
-    if cat_ids:
-        names, in_params = _named_in_clause("cid", cat_ids)
-        cats = list(conn.execute(
-            text(f"SELECT id, name, description, created_at, updated_at FROM categories WHERE id IN ({names})"),
-            in_params
-        ).mappings())
-
-    # apps for referenced app_ids
-    apps = []
-    if app_ids:
-        names, in_params = _named_in_clause("aid", app_ids)
-        apps = list(conn.execute(
-            text(f"SELECT id, owner_id, name, description, metadata, is_active, created_at, updated_at FROM apps WHERE id IN ({names})"),
-            in_params
-        ).mappings())
-
-    # status history for selected memories
-    history = []
-    if memory_ids:
-        names, in_params = _named_in_clause("hid", memory_ids)
-        history = list(conn.execute(
-            text(f"SELECT id, memory_id, changed_by, old_state, new_state, changed_at FROM memory_status_history WHERE memory_id IN ({names})"),
-            in_params
-        ).mappings())
-
-    # access_controls for the apps
-    acls = []
-    if app_ids:
-        names, in_params = _named_in_clause("sid", app_ids)
-        acls = list(conn.execute(
-            text(f"""SELECT id, subject_type, subject_id, object_type, object_id, effect, created_at
-                     FROM access_controls
-                     WHERE subject_type = 'app' AND subject_id IN ({names})"""),
-            in_params
-        ).mappings())
-
-    # Build helper maps
-    app_name_by_id = {r["id"]: r["name"] for r in apps}
-    app_rec_by_id = {r["id"]: r for r in apps}
-    cat_name_by_id = {r["id"]: r["name"] for r in cats}
-    mem_cat_ids_map: Dict[Any, List[Any]] = {}
-    mem_cat_names_map: Dict[Any, List[str]] = {}
-    for r in mc_rows:
-        mem_cat_ids_map.setdefault(r["memory_id"], []).append(r["category_id"])
-        mem_cat_names_map.setdefault(r["memory_id"], []).append(cat_name_by_id.get(r["category_id"], ""))
-
-    # Build sqlite-like payload
-    sqlite_payload = {
-        "user": {
-            "id": str(user_row["id"]),
-            "user_id": user_row["user_id"],
-            "name": user_row.get("name"),
-            "email": user_row.get("email"),
-            "metadata": _json_load_maybe(user_row.get("metadata")),
-            "created_at": _iso(user_row.get("created_at")),
-            "updated_at": _iso(user_row.get("updated_at")),
-        },
-        "apps": [
-            {
-                "id": str(a["id"]),
-                "owner_id": str(a["owner_id"]) if a.get("owner_id") else None,
-                "name": a["name"],
-                "description": a.get("description"),
-                "metadata": _json_load_maybe(a.get("metadata")),
-                "is_active": bool(a.get("is_active")),
-                "created_at": _iso(a.get("created_at")),
-                "updated_at": _iso(a.get("updated_at")),
-            }
-            for a in apps
-        ],
-        "categories": [
-            {
-                "id": str(c["id"]),
-                "name": c["name"],
-                "description": c.get("description"),
-                "created_at": _iso(c.get("created_at")),
-                "updated_at": _iso(c.get("updated_at")),
-            }
-            for c in cats
-        ],
-        "memories": [
-            {
-                "id": str(m["id"]),
-                "user_id": str(m["user_id"]),
-                "app_id": str(m["app_id"]) if m.get("app_id") else None,
-                "content": m.get("content") or "",
-                "metadata": _json_load_maybe(m.get("metadata")) or {},
-                "state": m.get("state"),
-                "created_at": _iso(m.get("created_at")),
-                "updated_at": _iso(m.get("updated_at")),
-                "archived_at": _iso(m.get("archived_at")),
-                "deleted_at": _iso(m.get("deleted_at")),
-                "category_ids": [str(cid) for cid in mem_cat_ids_map.get(m["id"], [])],
-            }
-            for m in mem_rows
-        ],
-        "memory_categories": [
-            {"memory_id": str(r["memory_id"]), "category_id": str(r["category_id"])}
-            for r in mc_rows
-        ],
-        "status_history": [
-            {
-                "id": str(h["id"]),
-                "memory_id": str(h["memory_id"]),
-                "changed_by": str(h["changed_by"]),
-                "old_state": h.get("old_state"),
-                "new_state": h.get("new_state"),
-                "changed_at": _iso(h.get("changed_at")),
-            }
-            for h in history
-        ],
-        "access_controls": [
-            {
-                "id": str(ac["id"]),
-                "subject_type": ac.get("subject_type"),
-                "subject_id": str(ac["subject_id"]) if ac.get("subject_id") else None,
-                "object_type": ac.get("object_type"),
-                "object_id": str(ac["object_id"]) if ac.get("object_id") else None,
-                "effect": ac.get("effect"),
-                "created_at": _iso(ac.get("created_at")),
-            }
-            for ac in acls
-        ],
-        "export_meta": {
-            "app_id_filter": str(app_id_filter) if app_id_filter else None,
-            "from_date": from_ts,
-            "to_date": to_ts,
-            "version": "1",
-            "generated_at": datetime.datetime.now(datetime.timezone.utc).isoformat(),
-        },
-    }
-
-    # Write memories.json
-    out_json = "/tmp/memories.json"
-    with open(out_json, "w", encoding="utf-8") as f:
-        json.dump(sqlite_payload, f, indent=2, ensure_ascii=False)
-
-    # Write logical jsonl.gz
-    out_jsonl_gz = "/tmp/memories.jsonl.gz"
-    with gzip.open(out_jsonl_gz, "wb") as gz:
-        for m in mem_rows:
-            record = {
-                "id": str(m["id"]),
-                "content": m.get("content") or "",
-                "metadata": _json_load_maybe(m.get("metadata")) or {},
-                "created_at": _iso(m.get("created_at")),
-                "updated_at": _iso(m.get("updated_at")),
-                "state": m.get("state"),
-                "app": app_name_by_id.get(m.get("app_id")) if m.get("app_id") else None,
-                "categories": [c for c in mem_cat_names_map.get(m["id"], []) if c],
-            }
-            gz.write((json.dumps(record, ensure_ascii=False) + "\n").encode("utf-8"))
-
-    print(out_json)
-    print(out_jsonl_gz)
-PYCODE
-PY_EXIT=$?
-set -e
-if [[ $PY_EXIT -ne 0 ]]; then
-  echo "ERROR: Export failed inside container (exit code $PY_EXIT)"
-  exit $PY_EXIT
-fi
-
-# Copy files out of the container
-TMPDIR="$(mktemp -d)"
-docker cp "${CONTAINER}:/tmp/memories.json" "${TMPDIR}/memories.json"
-docker cp "${CONTAINER}:/tmp/memories.jsonl.gz" "${TMPDIR}/memories.jsonl.gz"
-
-# Create zip on host
-ZIP_NAME="memories_export_${USER_ID}.zip"
-if command -v zip >/dev/null 2>&1; then
-  (cd "${TMPDIR}" && zip -q -r "../${ZIP_NAME}" "memories.json" "memories.jsonl.gz")
-  mv "${TMPDIR}/../${ZIP_NAME}" "./${ZIP_NAME}"
-else
-  # Fallback: use Python zipfile
-  python3 - <<PYFALLBACK
-import sys, zipfile
-zf = zipfile.ZipFile("${ZIP_NAME}", "w", compression=zipfile.ZIP_DEFLATED)
-zf.write("${TMPDIR}/memories.json", arcname="memories.json")
-zf.write("${TMPDIR}/memories.jsonl.gz", arcname="memories.jsonl.gz")
-zf.close()
-print("${ZIP_NAME}")
-PYFALLBACK
-fi
-
-echo "Wrote ./${ZIP_NAME}"
-echo "Done."
@@ -1,11 +0,0 @@
-services:
-  mem0_store:
-    image: ghcr.io/chroma-core/chroma:latest
-    restart: unless-stopped
-    environment:
-      - CHROMA_SERVER_HOST=0.0.0.0
-      - CHROMA_SERVER_HTTP_PORT=8000
-    ports:
-      - "8000:8000"
-    volumes:
-      - mem0_storage:/data
@@ -1,15 +0,0 @@
-services:
-  mem0_store:
-    image: docker.elastic.co/elasticsearch/elasticsearch:8.13.4
-    restart: unless-stopped
-    environment:
-      - discovery.type=single-node
-      - xpack.security.enabled=false
-      - ES_JAVA_OPTS=-Xms512m -Xmx512m
-    ulimits:
-      memlock: { soft: -1, hard: -1 }
-      nofile:  { soft: 65536, hard: 65536 }
-    ports:
-      - "9200:9200"
-    volumes:
-      - mem0_storage:/usr/share/elasticsearch/data
@@ -1,3 +0,0 @@
-services:
-  # FAISS is a local file-based vector store, so no separate container is needed
-  # Data will be persisted through volume mounts in the main application
@@ -1,43 +0,0 @@
-services:
-  etcd:
-    image: quay.io/coreos/etcd:v3.5.5
-    restart: unless-stopped
-    environment:
-      - ETCD_AUTO_COMPACTION_MODE=revision
-      - ETCD_QUOTA_BACKEND_BYTES=4294967296
-      - ETCD_SNAPSHOT_COUNT=50000
-      - ETCD_LISTEN_CLIENT_URLS=http://0.0.0.0:2379
-      - ETCD_ADVERTISE_CLIENT_URLS=http://etcd:2379
-      - ETCD_LISTEN_PEER_URLS=http://0.0.0.0:2380
-      - ETCD_INITIAL_ADVERTISE_PEER_URLS=http://etcd:2380
-      - ETCD_INITIAL_CLUSTER=default=http://etcd:2380
-      - ETCD_NAME=default
-      - ETCD_DATA_DIR=/etcd
-    volumes:
-      - ./data/milvus/etcd:/etcd
-
-  minio:
-    image: minio/minio:RELEASE.2023-10-25T06-33-25Z
-    restart: unless-stopped
-    command: server /minio_data
-    environment:
-      - MINIO_ACCESS_KEY=minioadmin
-      - MINIO_SECRET_KEY=minioadmin
-    volumes:
-      - ./data/milvus/minio:/minio_data
-
-  mem0_store:
-    image: milvusdb/milvus:v2.4.7
-    restart: unless-stopped
-    command: ["milvus", "run", "standalone"]
-    depends_on:
-      - etcd
-      - minio
-    environment:
-      - ETCD_ENDPOINTS=etcd:2379
-      - MINIO_ADDRESS=minio:9000
-    ports:
-      - "19530:19530"
-      - "9091:9091"
-    volumes:
-      - ./data/milvus/milvus:/var/lib/milvus
@@ -1,19 +0,0 @@
-services:
-  mem0_store:
-    image: opensearchproject/opensearch:2.13.0
-    restart: unless-stopped
-    user: "1000:1000"
-    environment:
-      - discovery.type=single-node
-      - plugins.security.disabled=true
-      - OPENSEARCH_JAVA_OPTS=-Xms512m -Xmx512m
-      - OPENSEARCH_INITIAL_ADMIN_PASSWORD=Openmemory123!
-      - bootstrap.memory_lock=true
-    ulimits:
-      memlock: { soft: -1, hard: -1 }
-      nofile:  { soft: 65536, hard: 65536 }
-    ports:
-      - "9200:9200"
-      - "9600:9600"
-    volumes:
-      - mem0_storage:/usr/share/opensearch/data
@@ -1,12 +0,0 @@
-services:
-  mem0_store:
-    image: pgvector/pgvector:pg16
-    restart: unless-stopped
-    environment:
-      - POSTGRES_DB=mem0
-      - POSTGRES_USER=mem0
-      - POSTGRES_PASSWORD=mem0
-    ports:
-      - "5432:5432"
-    volumes:
-      - mem0_storage:/var/lib/postgresql/data
@@ -1,8 +0,0 @@
-services:
-  mem0_store:
-    image: qdrant/qdrant:latest
-    restart: unless-stopped
-    ports:
-      - "6333:6333"
-    volumes:
-      - mem0_storage:/mem0/storage
@@ -1,13 +0,0 @@
-services:
-  mem0_store:
-    image: redis/redis-stack-server:latest
-    restart: unless-stopped
-    ports:
-      - "6379:6379"
-    volumes:
-      - mem0_storage:/var/lib/redis-stack
-    command: >
-      redis-stack-server
-      --appendonly yes
-      --appendfsync everysec
-      --save 900 1 300 10 60 10000
@@ -1,14 +0,0 @@
-services:
-  mem0_store:
-    image: semitechnologies/weaviate:latest
-    restart: unless-stopped
-    environment:
-      - QUERY_DEFAULTS_LIMIT=25
-      - AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED=true
-      - PERSISTENCE_DATA_PATH=/var/lib/weaviate
-      - CLUSTER_HOSTNAME=node1
-      - WEAVIATE_CLUSTER_URL=http://mem0_store:8080
-    ports:
-      - "8080:8080"
-    volumes:
-      - mem0_storage:/var/lib/weaviate
@@ -1,36 +0,0 @@
-services:
-  mem0_store:
-    image: qdrant/qdrant
-    ports:
-      - "6333:6333"
-    volumes:
-      - mem0_storage:/mem0/storage
-  openmemory-mcp:
-    image: mem0/openmemory-mcp
-    build: api/
-    environment:
-      - USER
-      - API_KEY
-    env_file:
-      - api/.env
-    depends_on:
-      - mem0_store
-    ports:
-      - "8765:8765"
-    volumes:
-      - ./api:/usr/src/openmemory
-    command: >
-      sh -c "uvicorn main:app --host 0.0.0.0 --port 8765 --reload --workers 4"
-  openmemory-ui:
-    build:
-      context: ui/
-      dockerfile: Dockerfile
-    image: mem0/openmemory-ui:latest
-    ports:
-      - "3000:3000"
-    environment:
-      - NEXT_PUBLIC_API_URL=${NEXT_PUBLIC_API_URL}
-      - NEXT_PUBLIC_USER_ID=${USER}
-
-volumes:
-  mem0_storage:
@@ -1,400 +0,0 @@
-#!/bin/bash
-
-set -e
-
-echo "🚀 Starting OpenMemory installation..."
-
-# Set environment variables
-OPENAI_API_KEY="${OPENAI_API_KEY:-}"
-USER="${USER:-$(whoami)}"
-NEXT_PUBLIC_API_URL="${NEXT_PUBLIC_API_URL:-http://localhost:8765}"
-
-if [ -z "$OPENAI_API_KEY" ]; then
-  echo "❌ OPENAI_API_KEY not set. Please run with: curl -sL https://raw.githubusercontent.com/mem0ai/mem0/main/openmemory/run.sh | OPENAI_API_KEY=your_api_key bash"
-  echo "❌ OPENAI_API_KEY not set. You can also set it as global environment variable: export OPENAI_API_KEY=your_api_key"
-  exit 1
-fi
-
-# Check if Docker is installed
-if ! command -v docker &> /dev/null; then
-  echo "❌ Docker not found. Please install Docker first."
-  exit 1
-fi
-
-# Check if docker compose is available
-if ! docker compose version &> /dev/null; then
-  echo "❌ Docker Compose not found. Please install Docker Compose V2."
-  exit 1
-fi
-
-# Check if the container "mem0_ui" already exists and remove it if necessary
-if [ $(docker ps -aq -f name=mem0_ui) ]; then
-  echo "⚠️ Found existing container 'mem0_ui'. Removing it..."
-  docker rm -f mem0_ui
-fi
-
-# Find an available port starting from 3000
-echo "🔍 Looking for available port for frontend..."
-for port in {3000..3010}; do
-  if ! lsof -i:$port >/dev/null 2>&1; then
-    FRONTEND_PORT=$port
-    break
-  fi
-done
-
-if [ -z "$FRONTEND_PORT" ]; then
-  echo "❌ Could not find an available port between 3000 and 3010"
-  exit 1
-fi
-
-# Export required variables for Compose and frontend
-export OPENAI_API_KEY
-export USER
-export NEXT_PUBLIC_API_URL
-export NEXT_PUBLIC_USER_ID="$USER"
-export FRONTEND_PORT
-
-# Parse vector store selection (env var or flag). Default: qdrant
-VECTOR_STORE="${VECTOR_STORE:-qdrant}"
-EMBEDDING_DIMS="${EMBEDDING_DIMS:-1536}"
-
-for arg in "$@"; do
-  case $arg in
-    --vector-store=*)
-      VECTOR_STORE="${arg#*=}"
-      shift
-      ;;
-    --vector-store)
-      VECTOR_STORE="$2"
-      shift 2
-      ;;
-    *)
-      ;;
-  esac
-done
-
-export VECTOR_STORE
-echo "🧰 Using vector store: $VECTOR_STORE"
-
-# Function to create compose file by merging vector store config with openmemory-mcp service
-create_compose_file() {
-  local vector_store=$1
-  local compose_file="compose/${vector_store}.yml"
-  local volume_name="${vector_store}_data"  # Vector-store-specific volume name
-  
-  # Check if the compose file exists
-  if [ ! -f "$compose_file" ]; then
-    echo "❌ Compose file not found: $compose_file"
-    echo "Available vector stores: $(ls compose/*.yml | sed 's/compose\///g' | sed 's/\.yml//g' | tr '\n' ' ')"
-    exit 1
-  fi
-  
-  echo "📝 Creating docker-compose.yml using $compose_file..."
-  echo "💾 Using volume: $volume_name"
-  
-  # Start the compose file with services section
-  echo "services:" > docker-compose.yml
-  
-  # Extract services from the compose file and replace volume name
-  # First get everything except the last volumes section
-  tail -n +2 "$compose_file" | sed '/^volumes:/,$d' | sed "s/mem0_storage/${volume_name}/g" >> docker-compose.yml
-  
-  # Add a newline to ensure proper YAML formatting
-  echo "" >> docker-compose.yml
-  
-  # Add the openmemory-mcp service
-  cat >> docker-compose.yml <<EOF
-  openmemory-mcp:
-    image: mem0/openmemory-mcp:latest
-    environment:
-      - OPENAI_API_KEY=${OPENAI_API_KEY}
-      - USER=${USER}
-EOF
-
-  # Add vector store specific environment variables
-  case "$vector_store" in
-    weaviate)
-      cat >> docker-compose.yml <<EOF
-      - WEAVIATE_HOST=mem0_store
-      - WEAVIATE_PORT=8080
-EOF
-      ;;
-    redis)
-      cat >> docker-compose.yml <<EOF
-      - REDIS_URL=redis://mem0_store:6379
-EOF
-      ;;
-    pgvector)
-      cat >> docker-compose.yml <<EOF
-      - PG_HOST=mem0_store
-      - PG_PORT=5432
-      - PG_DB=mem0
-      - PG_USER=mem0
-      - PG_PASSWORD=mem0
-EOF
-      ;;
-    qdrant)
-      cat >> docker-compose.yml <<EOF
-      - QDRANT_HOST=mem0_store
-      - QDRANT_PORT=6333
-EOF
-      ;;
-    chroma)
-      cat >> docker-compose.yml <<EOF
-      - CHROMA_HOST=mem0_store
-      - CHROMA_PORT=8000
-EOF
-      ;;
-    milvus)
-      cat >> docker-compose.yml <<EOF
-      - MILVUS_HOST=mem0_store
-      - MILVUS_PORT=19530
-EOF
-      ;;
-    elasticsearch)
-      cat >> docker-compose.yml <<EOF
-      - ELASTICSEARCH_HOST=mem0_store
-      - ELASTICSEARCH_PORT=9200
-      - ELASTICSEARCH_USER=elastic
-      - ELASTICSEARCH_PASSWORD=changeme
-EOF
-      ;;
-    faiss)
-      cat >> docker-compose.yml <<EOF
-      - FAISS_PATH=/tmp/faiss
-EOF
-      ;;
-    *)
-      echo "⚠️ Unknown vector store: $vector_store. Using default Qdrant configuration."
-      cat >> docker-compose.yml <<EOF
-      - QDRANT_HOST=mem0_store
-      - QDRANT_PORT=6333
-EOF
-      ;;
-  esac
-
-  # Add common openmemory-mcp service configuration
-  if [ "$vector_store" = "faiss" ]; then
-    # FAISS doesn't need a separate service, just volume mounts
-    cat >> docker-compose.yml <<EOF
-    ports:
-      - "8765:8765"
-    volumes:
-      - openmemory_db:/usr/src/openmemory
-      - ${volume_name}:/tmp/faiss
-
-volumes:
-  ${volume_name}:
-  openmemory_db:
-EOF
-  else
-    cat >> docker-compose.yml <<EOF
-    depends_on:
-      - mem0_store
-    ports:
-      - "8765:8765"
-    volumes:
-      - openmemory_db:/usr/src/openmemory
-
-volumes:
-  ${volume_name}:
-  openmemory_db:
-EOF
-  fi
-}
-
-# Create docker-compose.yml file based on selected vector store
-echo "📝 Creating docker-compose.yml..."
-create_compose_file "$VECTOR_STORE"
-
-# Ensure local data directories exist for bind-mounted vector stores
-if [ "$VECTOR_STORE" = "milvus" ]; then
-  echo "🗂️ Ensuring local data directories for Milvus exist..."
-  mkdir -p ./data/milvus/etcd ./data/milvus/minio ./data/milvus/milvus
-fi
-
-# Function to install vector store specific packages
-install_vector_store_packages() {
-  local vector_store=$1
-  echo "📦 Installing packages for vector store: $vector_store..."
-  
-  case "$vector_store" in
-    qdrant)
-      docker exec openmemory-openmemory-mcp-1 pip install "qdrant-client>=1.9.1" || echo "⚠️ Failed to install qdrant packages"
-      ;;
-    chroma)
-      docker exec openmemory-openmemory-mcp-1 pip install "chromadb>=0.4.24" || echo "⚠️ Failed to install chroma packages"
-      ;;
-    weaviate)
-      docker exec openmemory-openmemory-mcp-1 pip install "weaviate-client>=4.4.0,<4.15.0" || echo "⚠️ Failed to install weaviate packages"
-      ;;
-    faiss)
-      docker exec openmemory-openmemory-mcp-1 pip install "faiss-cpu>=1.7.4" || echo "⚠️ Failed to install faiss packages"
-      ;;
-    pgvector)
-      docker exec openmemory-openmemory-mcp-1 pip install "vecs>=0.4.0" "psycopg>=3.2.8" || echo "⚠️ Failed to install pgvector packages"
-      ;;
-    redis)
-      docker exec openmemory-openmemory-mcp-1 pip install "redis>=5.0.0,<6.0.0" "redisvl>=0.1.0,<1.0.0" || echo "⚠️ Failed to install redis packages"
-      ;;
-    elasticsearch)
-      docker exec openmemory-openmemory-mcp-1 pip install "elasticsearch>=8.0.0,<9.0.0" || echo "⚠️ Failed to install elasticsearch packages"
-      ;;
-    milvus)
-      docker exec openmemory-openmemory-mcp-1 pip install "pymilvus>=2.4.0,<2.6.0" || echo "⚠️ Failed to install milvus packages"
-      ;;
-    *)
-      echo "⚠️ Unknown vector store: $vector_store. Installing default qdrant packages."
-      docker exec openmemory-openmemory-mcp-1 pip install "qdrant-client>=1.9.1" || echo "⚠️ Failed to install qdrant packages"
-      ;;
-  esac
-}
-
-# Start services
-echo "🚀 Starting backend services..."
-docker compose up -d
-
-# Wait for container to be ready before installing packages
-echo "⏳ Waiting for container to be ready..."
-for i in {1..30}; do
-  if docker exec openmemory-openmemory-mcp-1 python -c "import sys; print('ready')" >/dev/null 2>&1; then
-    break
-  fi
-  sleep 1
-done
-
-# Install vector store specific packages
-install_vector_store_packages "$VECTOR_STORE"
-
-# If a specific vector store is selected, seed the backend config accordingly
-if [ "$VECTOR_STORE" = "milvus" ]; then
-  echo "⏳ Waiting for API to be ready at ${NEXT_PUBLIC_API_URL}..."
-  for i in {1..60}; do
-    if curl -fsS "${NEXT_PUBLIC_API_URL}/api/v1/config" >/dev/null 2>&1; then
-      break
-    fi
-    sleep 1
-  done
-
-  echo "🧩 Configuring vector store (milvus) in backend..."
-  curl -fsS -X PUT "${NEXT_PUBLIC_API_URL}/api/v1/config/mem0/vector_store" \
-    -H 'Content-Type: application/json' \
-    -d "{\"provider\":\"milvus\",\"config\":{\"collection_name\":\"openmemory\",\"embedding_model_dims\":${EMBEDDING_DIMS},\"url\":\"http://mem0_store:19530\",\"token\":\"\",\"db_name\":\"\",\"metric_type\":\"COSINE\"}}" >/dev/null || true
-elif [ "$VECTOR_STORE" = "weaviate" ]; then
-  echo "⏳ Waiting for API to be ready at ${NEXT_PUBLIC_API_URL}..."
-  for i in {1..60}; do
-    if curl -fsS "${NEXT_PUBLIC_API_URL}/api/v1/config" >/dev/null 2>&1; then
-      break
-    fi
-    sleep 1
-  done
-
-  echo "🧩 Configuring vector store (weaviate) in backend..."
-  curl -fsS -X PUT "${NEXT_PUBLIC_API_URL}/api/v1/config/mem0/vector_store" \
-    -H 'Content-Type: application/json' \
-    -d "{\"provider\":\"weaviate\",\"config\":{\"collection_name\":\"openmemory\",\"embedding_model_dims\":${EMBEDDING_DIMS},\"cluster_url\":\"http://mem0_store:8080\"}}" >/dev/null || true
-elif [ "$VECTOR_STORE" = "redis" ]; then
-  echo "⏳ Waiting for API to be ready at ${NEXT_PUBLIC_API_URL}..."
-  for i in {1..60}; do
-    if curl -fsS "${NEXT_PUBLIC_API_URL}/api/v1/config" >/dev/null 2>&1; then
-      break
-    fi
-    sleep 1
-  done
-
-  echo "🧩 Configuring vector store (redis) in backend..."
-  curl -fsS -X PUT "${NEXT_PUBLIC_API_URL}/api/v1/config/mem0/vector_store" \
-    -H 'Content-Type: application/json' \
-    -d "{\"provider\":\"redis\",\"config\":{\"collection_name\":\"openmemory\",\"embedding_model_dims\":${EMBEDDING_DIMS},\"redis_url\":\"redis://mem0_store:6379\"}}" >/dev/null || true
-elif [ "$VECTOR_STORE" = "pgvector" ]; then
-  echo "⏳ Waiting for API to be ready at ${NEXT_PUBLIC_API_URL}..."
-  for i in {1..60}; do
-    if curl -fsS "${NEXT_PUBLIC_API_URL}/api/v1/config" >/dev/null 2>&1; then
-      break
-    fi
-    sleep 1
-  done
-
-  echo "🧩 Configuring vector store (pgvector) in backend..."
-  curl -fsS -X PUT "${NEXT_PUBLIC_API_URL}/api/v1/config/mem0/vector_store" \
-    -H 'Content-Type: application/json' \
-    -d "{\"provider\":\"pgvector\",\"config\":{\"collection_name\":\"openmemory\",\"embedding_model_dims\":${EMBEDDING_DIMS},\"dbname\":\"mem0\",\"user\":\"mem0\",\"password\":\"mem0\",\"host\":\"mem0_store\",\"port\":5432,\"diskann\":false,\"hnsw\":true}}" >/dev/null || true
-elif [ "$VECTOR_STORE" = "qdrant" ]; then
-  echo "⏳ Waiting for API to be ready at ${NEXT_PUBLIC_API_URL}..."
-  for i in {1..60}; do
-    if curl -fsS "${NEXT_PUBLIC_API_URL}/api/v1/config" >/dev/null 2>&1; then
-      break
-    fi
-    sleep 1
-  done
-
-  echo "🧩 Configuring vector store (qdrant) in backend..."
-  curl -fsS -X PUT "${NEXT_PUBLIC_API_URL}/api/v1/config/mem0/vector_store" \
-    -H 'Content-Type: application/json' \
-    -d "{\"provider\":\"qdrant\",\"config\":{\"collection_name\":\"openmemory\",\"embedding_model_dims\":${EMBEDDING_DIMS},\"host\":\"mem0_store\",\"port\":6333}}" >/dev/null || true
-elif [ "$VECTOR_STORE" = "chroma" ]; then
-  echo "⏳ Waiting for API to be ready at ${NEXT_PUBLIC_API_URL}..."
-  for i in {1..60}; do
-    if curl -fsS "${NEXT_PUBLIC_API_URL}/api/v1/config" >/dev/null 2>&1; then
-      break
-    fi
-    sleep 1
-  done
-
-  echo "🧩 Configuring vector store (chroma) in backend..."
-  curl -fsS -X PUT "${NEXT_PUBLIC_API_URL}/api/v1/config/mem0/vector_store" \
-    -H 'Content-Type: application/json' \
-    -d "{\"provider\":\"chroma\",\"config\":{\"collection_name\":\"openmemory\",\"host\":\"mem0_store\",\"port\":8000}}" >/dev/null || true
-elif [ "$VECTOR_STORE" = "elasticsearch" ]; then
-  echo "⏳ Waiting for API to be ready at ${NEXT_PUBLIC_API_URL}..."
-  for i in {1..60}; do
-    if curl -fsS "${NEXT_PUBLIC_API_URL}/api/v1/config" >/dev/null 2>&1; then
-      break
-    fi
-    sleep 1
-  done
-
-  echo "🧩 Configuring vector store (elasticsearch) in backend..."
-  curl -fsS -X PUT "${NEXT_PUBLIC_API_URL}/api/v1/config/mem0/vector_store" \
-    -H 'Content-Type: application/json' \
-    -d "{\"provider\":\"elasticsearch\",\"config\":{\"collection_name\":\"openmemory\",\"embedding_model_dims\":${EMBEDDING_DIMS},\"host\":\"http://mem0_store\",\"port\":9200,\"user\":\"elastic\",\"password\":\"changeme\",\"verify_certs\":false,\"use_ssl\":false}}" >/dev/null || true
-elif [ "$VECTOR_STORE" = "faiss" ]; then
-  echo "⏳ Waiting for API to be ready at ${NEXT_PUBLIC_API_URL}..."
-  for i in {1..60}; do
-    if curl -fsS "${NEXT_PUBLIC_API_URL}/api/v1/config" >/dev/null 2>&1; then
-      break
-    fi
-    sleep 1
-  done
-
-  echo "🧩 Configuring vector store (faiss) in backend..."
-  curl -fsS -X PUT "${NEXT_PUBLIC_API_URL}/api/v1/config/mem0/vector_store" \
-    -H 'Content-Type: application/json' \
-    -d "{\"provider\":\"faiss\",\"config\":{\"collection_name\":\"openmemory\",\"embedding_model_dims\":${EMBEDDING_DIMS},\"path\":\"/tmp/faiss\",\"distance_strategy\":\"cosine\"}}" >/dev/null || true
-fi
-
-# Start the frontend
-echo "🚀 Starting frontend on port $FRONTEND_PORT..."
-docker run -d \
-  --name mem0_ui \
-  -p ${FRONTEND_PORT}:3000 \
-  -e NEXT_PUBLIC_API_URL="$NEXT_PUBLIC_API_URL" \
-  -e NEXT_PUBLIC_USER_ID="$USER" \
-  mem0/openmemory-ui:latest
-
-echo "✅ Backend:  http://localhost:8765"
-echo "✅ Frontend: http://localhost:$FRONTEND_PORT"
-
-# Open the frontend URL in the default web browser
-echo "🌐 Opening frontend in the default browser..."
-URL="http://localhost:$FRONTEND_PORT"
-
-if command -v xdg-open > /dev/null; then
-  xdg-open "$URL"        # Linux
-elif command -v open > /dev/null; then
-  open "$URL"            # macOS
-elif command -v start > /dev/null; then
-  start "$URL"           # Windows (if run via Git Bash or similar)
-else
-  echo "⚠️ Could not detect a method to open the browser. Please open $URL manually."
-fi
@@ -1,23 +0,0 @@
-# Ignore all .env files
-**/.env
-
-
-# Ignore all database files
-**/*.db
-**/*.sqlite
-**/*.sqlite3
-
-# Ignore logs
-**/*.log
-
-# Ignore runtime data
-**/node_modules
-**/__pycache__
-**/.pytest_cache
-**/.coverage
-**/coverage
-
-# Ignore Docker runtime files
-**/.dockerignore
-**/Dockerfile
-**/docker-compose*.yml 
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
karthik	88a371c95d	docs: remove stray tags that broke Dream page MDX parsing Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-08-04 18:14:50 +05:30
karthik	6b5c93c715	docs: note Synthesis only considers user_id-scoped memories Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-08-04 15:08:29 +05:30
karthik	66fea46287	docs: soften Dream page prose and link directly to the Dream dashboard Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-08-04 14:06:47 +05:30
karthik	df11be83fc	docs: add Dream feature to llms.txt index Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>	2026-07-30 19:43:38 +05:30
karthik	f39a726395	Dream Feature doc	2026-07-30 19:38:05 +05:30
karthik	18ca31db8f	Dream Feature doc	2026-07-29 21:23:30 +05:30
Kartik	ea2ee07586	chore: remove OpenMemory from the monorepo (#6530 )	2026-07-29 15:10:32 +05:30
Kartik	540d23d610	docs: serve an unconditioned favicon at the docs domain root (#6649 )	2026-07-29 00:07:35 -07:00
Kartik	3274390f82	docs: redirect /integrations/keywords to /integrations/respan (#6648 )	2026-07-28 23:57:37 -07:00
Kartik	b357a5a1b0	chore(release): Python SDK v2.0.14, TypeScript SDK v3.1.2 (#6589 )	2026-07-25 17:51:48 +05:30
Hrushikesh Yadav	d653b63fac	fix(milvus): guard text field in update() with _has_bm25_schema check (#5705 )	2026-07-24 18:27:54 +05:30
Abhay Singh	cc4671579f	fix(ts-oss/cassandra): apply every operator in a compound field filter (#6511 )	2026-07-24 18:26:10 +05:30
Bartok	01afdde3e7	salvage: fix(opensearch) re-raise search errors (credit @yashwanth123 #6477 ) (#6519 ) Co-authored-by: yashwanth123 <yashwanth123@users.noreply.github.com>	2026-07-24 18:19:26 +05:30
Elif Sema Balcioglu	d6d89c987b	Add Oracle Vector Store Integration (#5358 ) Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>	2026-07-23 21:30:01 +05:30
Kartik	c2150e8f1a	docs: SEO and AEO updates for the memory expiration page (#6535 )	2026-07-23 20:46:29 +05:30
microbluey	19c7bb84a2	fix(ts-oss/chroma): stop dropping filter conditions in where-clause translation (#6521 )	2026-07-23 20:07:19 +05:30
Abhishek Chauhan	e6281ab724	fix(ts-oss): forward responseFormat to Gemini in generateResponse (#6468 )	2026-07-23 19:48:33 +05:30
Rod Boev	a71d7bdbe3	fix(dashboard): clear the LLM API key on provider change (#6475 )	2026-07-23 19:44:54 +05:30
microbluey	56ec7d20f1	fix(vector_stores/opensearch): translate the '*' wildcard to an exists query for every key (#6522 )	2026-07-23 19:41:09 +05:30
Abhay Singh	ca2abca2b8	fix(ts-oss/milvus): skip '*' wildcard filter values instead of matching literally (#6508 )	2026-07-23 00:41:45 +05:30
Abhay Singh	0e582adc6c	fix(ts-oss/anthropic): find the text block in no-tools responses (#6506 )	2026-07-23 00:40:40 +05:30
Clement Antony	9caffeaa7b	fix(ts-sdk): use textLemmatized for BM25 keyword search on Milvus, OpenSearch, and MongoDB (#6497 ) Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>	2026-07-23 00:39:18 +05:30
microbluey	a58e0586ad	fix(vector_stores/opensearch): honor all filter keys instead of a hardcoded identity-key list (#6454 ) Co-authored-by: kartik-mem0 <kartik.labhshetwar@mem0.ai>	2026-07-23 00:24:16 +05:30
microbluey	a9cb4bb644	fix(vector_stores/chroma): stop dropping filter conditions in where-clause translation (#6452 )	2026-07-23 00:22:10 +05:30
Gyubin Son	7bf84b8d38	fix: drop unused vector column from pgvector get() and list() queries (#6483 )	2026-07-23 00:11:40 +05:30
				`@@ -0,0 +1 @@`
				`<svg fill="#8F74E0" role="img" viewBox="0 0 93.9 59.4" xmlns="http://www.w3.org/2000/svg"><title>Oracle</title><path d="M30.5,59.4H65c16.4-0.4,29.3-14.1,28.9-30.4C93.5,13.1,80.7,0.4,65,0H30.5C14.1-0.4,0.4,12.5,0,28.9s12.5,30,28.9,30.4C29.4,59.4,29.9,59.4,30.5,59.4 M64.2,48.9h-33c-10.6-0.3-18.9-9.2-18.6-19.8C13,19,21.1,10.8,31.2,10.5h33c10.6-0.3,19.5,8,19.8,18.6c0.3,10.6-8,19.5-18.6,19.8C65,48.9,64.6,48.9,64.2,48.9"/></svg>`
				`@@ -1 +0,0 @@`
				`# This file makes the app directory a Python package`