fix: update skills and docs (#4868)

skills/mem0/references/api-reference.md

@@ -8,13 +8,15 @@ All endpoints require: `Authorization: Token <MEM0_API_KEY>`
 
 | Operation | Method | URL |
 |-----------|--------|-----|
-| Add Memories | `POST` | `/v1/memories/` |
-| Search Memories | `POST` | `/v2/memories/search/` |
-| Get All Memories | `POST` | `/v2/memories/` |
+| Add Memories | `POST` | `/v3/memories/add/` |
+| Search Memories | `POST` | `/v3/memories/search/` |
+| Get All Memories | `POST` | `/v3/memories/` |
 | Get Single Memory | `GET` | `/v1/memories/{memory_id}/` |
 | Update Memory | `PUT` | `/v1/memories/{memory_id}/` |
 | Delete Memory | `DELETE` | `/v1/memories/{memory_id}/` |
 
+Note: v1/v2 endpoints still work (backward compatible).
+
 ## Memory Object Structure
 
 | Field | Type | Description |
@@ -27,8 +29,6 @@ All endpoints require: `Authorization: Token <MEM0_API_KEY>`
 | `run_id` | string (nullable) | Run/session identifier |
 | `metadata` | object | Custom key-value pairs |
 | `categories` | array of strings | Auto-assigned category tags |
-| `immutable` | boolean | If true, prevents modification |
-| `expiration_date` | datetime (nullable) | Auto-expiry date |
 | `hash` | string | Content hash |
 | `created_at` | datetime | Creation timestamp |
 | `updated_at` | datetime | Last modification timestamp |
@@ -50,10 +50,9 @@ Memories can be scoped to different levels:
 
 ## Processing Model
 
-- Memories are processed **asynchronously by default** (`async_mode=true`)
-- Add responses return queued events (`ADD`, `UPDATE`, `DELETE`) for tracking
-- Set `async_mode=false` for synchronous processing when needed
-- Graph metadata is processed asynchronously -- use `get_all()` for complete graph data
+- Memories are processed **asynchronously** (v3 default)
+- Add responses return queued `ADD` events only (v3 is ADD-only, no UPDATE/DELETE)
+- Poll status via `GET /v1/event/{event_id}/`
 
 ## Filter System
 
@@ -106,19 +105,17 @@ Root must be `AND`, `OR`, or `NOT`. Simple shorthand `{"user_id": "alice"}` also
 
 ## Response Formats
 
-### Add Response
+### Add Response (v3)
 
 ```json
-[
-  {
-    "id": "mem_01JF8ZS4Y0R0SPM13R5R6H32CJ",
-    "event": "ADD",
-    "data": { "memory": "The user moved to Austin in 2025." }
-  }
-]
+{
+  "message": "Memory processing has been queued for background execution",
+  "status": "PENDING",
+  "event_id": "evt-uuid"
+}
 ```
 
-Event types: `ADD`, `UPDATE`, `DELETE`. A single add can trigger multiple events.
+v3 is ADD-only. No UPDATE or DELETE events.
 
 ### Search Response
 
@@ -137,4 +134,17 @@ Event types: `ADD`, `UPDATE`, `DELETE`. A single add can trigger multiple events
 }
 ```
 
-With `enable_graph=true`, includes additional `relations` array with entity relationships.
+In v3, `score` is a combined multi-signal relevance score.
+
+### Get All Response (v3)
+
+```json
+{
+  "count": 123,
+  "next": "https://api.mem0.ai/v3/memories/?page=2&page_size=50",
+  "previous": null,
+  "results": [...]
+}
+```
+
+v3 returns paginated envelope. Use `page` and `page_size` query params.

skills/mem0/references/architecture.md

@@ -25,9 +25,9 @@ User Input → Retrieve relevant memories → Enrich LLM prompt → Generate res
 
 Mem0 handles the complexity of extraction, deduplication, conflict resolution, and semantic retrieval so your application only needs to call `search()` and `add()`.
 
-**Dual storage architecture:**
+**Storage architecture:**
 - **Vector store**: Embeddings for semantic similarity search
-- **Graph store** (optional): Entity nodes and relationship edges for structured knowledge
+- **Entity store**: Automatic entity linking for relationship-aware retrieval
 
 ---
 
@@ -40,41 +40,32 @@ Messages In
     │
     ▼
 ┌─────────────────────┐
-│  1. EXTRACTION       │  LLM analyzes messages, extracts key facts
+│  1. EXTRACTION       │  Single LLM call extracts all distinct new facts
 │     (infer=True)     │  If infer=False, stores raw text as-is
 └─────────┬───────────┘
           │
           ▼
 ┌─────────────────────┐
-│  2. CONFLICT         │  Checks existing memories for duplicates
-│     RESOLUTION       │  Latest truth wins (newer overrides older)
-│                      │  Only runs when infer=True
+│  2. DEDUPLICATION    │  Hash-based dedup (MD5 prevents exact duplicates)
+│                      │  No UPDATE/DELETE - v3 is ADD-only
 └─────────┬───────────┘
           │
           ▼
 ┌─────────────────────┐
-│  3. STORAGE          │  Generates embeddings → vector store
-│                      │  Optional: entity extraction → graph store
-│                      │  Indexes metadata, categories, timestamps
+│  3. STORAGE          │  Batch embed → vector store
+│                      │  Entity extraction → entity store
 └─────────┬───────────┘
           │
           ▼
     Memory Object
-    (id, memory, categories, structured_attributes)
 ```
 
-### Processing modes
+### Processing (v3)
 
-**Async (default, `async_mode=True`):**
-- API returns immediately: `{"status": "PENDING", "event_id": "..."}`
-- Processing happens in background
+v3 processes memories asynchronously by default:
+- API returns immediately: `{"status": "PENDING", "event_id": "evt-..."}`
+- Poll status via `GET /v1/event/{event_id}/`
 - Use webhooks for completion notifications
-- Best for: high-throughput, non-blocking workflows
-
-**Sync (`async_mode=False`):**
-- API waits for full processing
-- Returns complete memory object with `id`, `event`, `memory`
-- Best for: real-time access immediately after add
 
 ### Extraction modes
 
@@ -93,7 +84,7 @@ Messages In
 
 ---
 
-## Retrieval Pipeline
+## Retrieval Pipeline (v3)
 
 ### What happens when you call `client.search()`
 
@@ -102,45 +93,37 @@ Query In
     │
     ▼
 ┌─────────────────────┐
-│  1. QUERY EMBEDDING  │  Convert query to vector representation
+│  1. PREPROCESSING    │  Lemmatize keywords, extract entities
 └─────────┬───────────┘
           │
           ▼
 ┌─────────────────────┐
-│  2. VECTOR SEARCH    │  Cosine similarity across stored embeddings
-│                      │  Scoped by filters (user_id, agent_id, etc.)
-└─────────┬───────────┘
-          │
-          ▼  (optional enhancements)
-┌─────────────────────┐
-│  3a. KEYWORD SEARCH  │  Expands results with specific terms (+10ms)
-│  3b. RERANKING       │  Deep semantic reordering (+150-200ms)
-│  3c. FILTER MEMORIES │  Precision filtering, removes low-relevance (+200-300ms)
-└─────────┬───────────┘
-          │
-          ▼  (if enable_graph=True)
-┌─────────────────────┐
-│  4. GRAPH LOOKUP     │  Finds entity relationships
-│                      │  Appends relations WITHOUT reranking vector results
+│  2. PARALLEL SCORING │  Semantic search (vector similarity)
+│                      │  BM25 keyword search (term matching)
+│                      │  Entity matching (entity graph boost)
 └─────────┬───────────┘
           │
           ▼
-    Results + Relations
+┌─────────────────────┐
+│  3. SCORE FUSION     │  Combine signals into single score
+│                      │  Optional: rerank=True for deep reordering
+└─────────┬───────────┘
+          │
+          ▼
+    Results (combined score per memory)
 ```
 
-### Retrieval enhancement combinations
+### v3 Search Defaults
 
-| Configuration | Latency | Best for |
-|--------------|---------|----------|
-| Base search only | ~100ms | Simple lookups |
-| `keyword_search=True` | ~110ms | Entity-heavy queries, broad coverage |
-| `rerank=True` | ~250-300ms | User-facing results, top-N precision |
-| `keyword_search=True` + `rerank=True` | ~310ms | Balanced (recommended for most apps) |
-| `rerank=True` + `filter_memories=True` | ~400-500ms | Safety-critical, production systems |
+| Parameter | Default | Notes |
+|-----------|---------|-------|
+| `top_k` | 20 | Was 100 in v2 |
+| `threshold` | 0.1 | Was None in v2 |
+| `rerank` | False | Was True in v2 |
 
 ### Implicit null scoping
 
-When you search with `user_id="alice"` only, Mem0 returns memories where `agent_id`, `app_id`, and `run_id` are all null. This prevents cross-scope leakage by default.
+When you search with `filters={"user_id": "alice"}` only, Mem0 returns memories where `agent_id`, `app_id`, and `run_id` are all null. This prevents cross-scope leakage by default.
 
 To include memories with non-null fields, use explicit filters:
 ```python
@@ -150,53 +133,23 @@ filters={"OR": [{"user_id": "alice"}]}
 
 ---
 
-## Memory Lifecycle
+## Memory Lifecycle (v3)
 
-```
-CREATE ──→ ACTIVE ──→ UPDATE ──→ ACTIVE
-  │           │                     │
-  │           ▼                     ▼
-  │       EXPIRED              EXPIRED
-  │      (still stored,       (still stored,
-  │       not retrieved)       not retrieved)
-  │           │                     │
-  ▼           ▼                     ▼
-DELETE    DELETE               DELETE
-(permanent)
-```
+v3 uses ADD-only extraction. Memories accumulate over time rather than being consolidated.
 
 ### Creation
-- Triggered by `client.add(messages, user_id="...")`
-- Messages processed through extraction → conflict resolution → storage
-- Gets unique UUID, `created_at` timestamp
-- Optional: custom `timestamp`, `expiration_date`, `metadata`, `immutable`
+- `client.add(messages, user_id="...")`
+- Single-pass extraction → deduplication → storage
+- Returns `{"event_id": "...", "status": "PENDING"}`
 
 ### Updates
-- `client.update(memory_id, text="...")` replaces text and reindexes
-- `client.batch_update([...])` for up to 1000 memories at once
-- Immutable memories (`immutable=True`) cannot be updated — must delete and re-add
-
-### Deduplication
-- Automatic during `add()` with `infer=True`
-- Conflict resolution merges duplicate facts
-- Latest truth wins when contradictions detected
-- Prevents memory bloat from repeated information
-
-### Expiration
-- Optional `expiration_date` parameter (ISO 8601 or `YYYY-MM-DD`)
-- After expiration: memory NOT returned in searches but remains in storage
-- Useful for time-sensitive info (events, temporary preferences, session state)
+- `client.update(memory_id, text="...")` replaces text
+- Batch: `client.batch_update([...])`
 
 ### Deletion
-- Single: `client.delete(memory_id)` — permanent, no recovery
-- Batch: `client.batch_delete([memory_ids])` — up to 1000
-- Bulk: `client.delete_all(user_id="alice")` — all memories for entity
-- `delete_all()` without filters raises error to prevent accidental data loss
-
-### History tracking
-- `client.history(memory_id)` returns version timeline
-- Shows all changes: `{previous_value, new_value, action, timestamps}`
-- Useful for audit trails and debugging
+- Single: `client.delete(memory_id)`
+- Batch: `client.batch_delete([...])`
+- Bulk: `client.delete_all(filters={"user_id": "alice"})`
 
 ---
 
@@ -214,8 +167,6 @@ DELETE    DELETE               DELETE
   "categories": ["health", "preferences"],
   "created_at": "2025-03-12T12:34:56Z",
   "updated_at": "2025-03-12T12:34:56Z",
-  "expiration_date": null,
-  "immutable": false,
   "structured_attributes": {
     "day": 12, "month": 3, "year": 2025,
     "hour": 12, "minute": 34,
@@ -239,8 +190,6 @@ DELETE    DELETE               DELETE
 | `categories` | array | Auto-assigned or custom category tags |
 | `created_at` | datetime | Creation timestamp |
 | `updated_at` | datetime | Last modification timestamp |
-| `expiration_date` | datetime | Auto-expiry date (stops retrieval, data persists) |
-| `immutable` | boolean | If true, prevents modification |
 | `structured_attributes` | object | Temporal breakdown for time-based queries |
 | `score` | float | Semantic similarity (search results only, 0-1) |
 
@@ -322,7 +271,7 @@ Mem0 supports three layers of memory, from shortest to longest lived:
 ```python
 def chat(user_input: str, user_id: str, session_id: str) -> str:
     # 1. Retrieve user memories (long-term preferences)
-    user_mems = mem0.search(user_input, user_id=user_id)
+    user_mems = mem0.search(user_input, filters={"user_id": user_id})
 
     # 2. Retrieve session memories (current task context)
     session_mems = mem0.search(user_input, filters={
@@ -350,18 +299,13 @@ def chat(user_input: str, user_id: str, session_id: str) -> str:
 
 | Operation | Typical Latency |
 |-----------|----------------|
-| Base vector search | ~100ms |
-| + keyword_search | +10ms |
+| Hybrid search (v3 default) | ~100-150ms |
 | + reranking | +150-200ms |
-| + filter_memories | +200-300ms |
-| Add (async, default) | < 50ms response, background processing |
-| Add (sync) | 500ms-2s depending on extraction complexity |
-| Graph operations | Slight overhead for large stores |
+| Add (async) | < 50ms response |
 
 ### Processing
 
-- **Async mode (default):** Returns immediately, processes in background
-- **Sync mode:** Waits for full extraction + storage pipeline
+- **Async (default):** Returns immediately, processes in background
 - **Batch operations:** Up to 1000 memories per batch_update/batch_delete
 - **Webhooks:** Real-time notifications when async processing completes
 

skills/mem0/references/features.md

@@ -5,7 +5,7 @@ Additional platform capabilities beyond core CRUD operations.
 ## Table of Contents
 
 - [Advanced Retrieval](#advanced-retrieval)
-- [Graph Memory](#graph-memory)
+- [Entity Linking](#entity-linking)
 - [Custom Categories](#custom-categories)
 - [Custom Instructions](#custom-instructions)
 - [Criteria Retrieval](#criteria-retrieval)
@@ -18,124 +18,58 @@ Additional platform capabilities beyond core CRUD operations.
 
 ## Advanced Retrieval
 
-Three enhancement options for tuning search precision, recall, and latency.
+### Hybrid Search (v3 Default)
 
-### Keyword Search (`keyword_search=True`)
+v3 uses multi-signal hybrid search combining:
+- **Semantic search** (vector similarity)
+- **BM25 keyword search** (normalized term matching)
+- **Entity matching** (entity graph boost)
 
-Expands results to include memories with specific terms, names, and technical keywords.
-
-- Latency: +10ms
-- Recall: Significantly increased
-- Best for: entity-heavy queries, comprehensive coverage
+This is automatic — no configuration needed.
 
 ### Reranking (`rerank=True`)
 
 Deep semantic reordering of results — most relevant first.
 
 - Latency: +150-200ms
-- Accuracy: Significantly improved
+- Default: `False` (was `True` in v2)
 - Best for: user-facing results, top-N precision
 
-### Filter Memories (`filter_memories=True`)
-
-Precision filtering — removes low-relevance results entirely.
-
-- Latency: +200-300ms
-- Precision: Maximized
-- Best for: safety-critical applications, production systems
-
-### Recommended Combinations
-
 **Python:**
 ```python
-# Fast & broad
-results = client.search(query, keyword_search=True, user_id="user123")
-
-# Balanced (recommended for most apps)
-results = client.search(query, keyword_search=True, rerank=True, user_id="user123")
-
-# High precision (critical apps)
-results = client.search(query, rerank=True, filter_memories=True, user_id="user123")
+results = client.search(query, filters={"user_id": "user123"}, rerank=True)
 ```
 
 **TypeScript:**
 ```typescript
 const results = await client.search(query, {
-    user_id: 'user123',
-    keyword_search: true,
+    filters: { user_id: 'user123' },
     rerank: true,
 });
 ```
 
 ---
 
-## Graph Memory
+## Entity Linking
 
-Entity-level knowledge graph that creates relationships between memories.
+v3 replaces graph memory with built-in entity linking. Entities (proper nouns, quoted text, compound noun phrases) are automatically extracted and linked across memories.
 
 ### How It Works
 
-1. **Extraction**: LLM analyzes conversation and identifies entities and relationships
-2. **Storage**: Embeddings go to vector store; entity nodes and edges go to graph store
-3. **Retrieval**: Vector search returns semantic matches; graph relations are appended to results
+1. **Extraction**: During `add()`, entities are automatically extracted from memory text
+2. **Storage**: Entities are stored in a parallel collection (`{collection}_entities`)
+3. **Retrieval**: During `search()`, query entities are matched and used to boost relevant memories
 
-Graph relations **augment** vector results without reordering them. Vector similarity always determines hit sequence.
+Entity linking is automatic — no configuration required. The boost is folded into the combined `score` on each result.
 
-### Enabling Graph Memory
+### v2 Migration Note
 
-**Per request:**
-```python
-client.add(messages, user_id="alice", enable_graph=True)
-client.search("query", user_id="alice", enable_graph=True)
-client.get_all(filters={"AND": [{"user_id": "alice"}]}, enable_graph=True)
-```
+If you were using `enable_graph=True` in v2:
+- Remove `enable_graph` from all API calls
+- Remove `graph_store` from OSS configuration
+- Entity relationships are now consumed through retrieval ranking, not exposed as a separate `relations` array
 
-**Project-level (default for all operations):**
-```python
-client.project.update(enable_graph=True)
-```
-
-```javascript
-await client.updateProject({ enable_graph: true });
-```
-
-### Relation Structure
-
-Each relation in the response contains:
-
-| Field | Type | Description |
-|-------|------|-------------|
-| `source` | string | Source entity name |
-| `source_type` | string | Source entity type (e.g., "Person") |
-| `relationship` | string | Relationship label (e.g., "lives_in") |
-| `target` | string | Target entity name |
-| `target_type` | string | Target entity type (e.g., "City") |
-| `score` | number | Confidence score |
-
-**Example:**
-```json
-{
-  "relations": [
-    {
-      "source": "Joseph",
-      "source_type": "Person",
-      "relationship": "lives_in",
-      "target": "Seattle",
-      "target_type": "City",
-      "score": 0.92
-    }
-  ]
-}
-```
-
-### Technical Notes
-
-- Graph Memory adds processing time; see docs for current plan availability
-- Works optimally with rich conversation histories containing entity relationships
-- Best suited for long-running assistants tracking evolving information
-- Graph writes and reads toggle independently per request
-- Multi-agent context supported via `user_id`, `agent_id`, `run_id` scoping
-- Add operations are asynchronous; graph metadata may not be immediately available
+See the [v2 to v3 migration guide](https://docs.mem0.ai/migration/oss-v2-to-v3) for details.
 
 ---
 
@@ -160,7 +94,7 @@ client.project.update(custom_categories=new_categories)
 ```
 
 ```javascript
-await client.updateProject({ custom_categories: new_categories });
+await client.updateProject({ customCategories: newCategories });
 ```
 
 **Retrieve active categories:**
@@ -185,7 +119,7 @@ client.project.update(custom_instructions="Your guidelines here...")
 ```
 
 ```javascript
-await client.updateProject({ custom_instructions: "Your guidelines here..." });
+await client.updateProject({ customInstructions: "Your guidelines here..." });
 ```
 
 ### Template Structure
@@ -229,7 +163,7 @@ client.project.update(retrieval_criteria=retrieval_criteria)
 
 ```typescript
 await client.updateProject({
-    retrieval_criteria: [
+    retrievalCriteria: [
         { name: 'joy', description: 'Positive emotions', weight: 3 },
         { name: 'urgency', description: 'Time-sensitive items', weight: 4 },
     ],
@@ -281,7 +215,7 @@ for item in feedback_data:
 ```typescript
 await client.feedback('mem-123', {
     feedback: 'POSITIVE',
-    feedback_reason: 'Accurately captured dietary preference',
+    feedbackReason: 'Accurately captured dietary preference',
 });
 ```
 

skills/mem0/references/integration-patterns.md

@@ -27,7 +27,7 @@ from langchain_core.messages import SystemMessage, HumanMessage
 from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
 from mem0 import MemoryClient
 
-llm = ChatOpenAI(model="gpt-4.1-nano-2025-04-14")
+llm = ChatOpenAI(model="gpt-5-mini")
 mem0 = MemoryClient()
 
 prompt = ChatPromptTemplate.from_messages([
@@ -128,7 +128,7 @@ import { createMem0 } from "@mem0/vercel-ai-provider";
 
 const mem0 = createMem0();
 const { text } = await generateText({
-    model: mem0("gpt-4-turbo", { user_id: "borat" }),
+    model: mem0("gpt-5-mini", { user_id: "borat" }),
     prompt: "Suggest me a good car to buy!",
 });
 ```
@@ -167,7 +167,7 @@ agent = Agent(
     Use search_memory to recall past conversations.
     Use save_memory to store important information.""",
     tools=[search_memory, save_memory],
-    model="gpt-4.1-nano-2025-04-14"
+    model="gpt-5-mini"
 )
 
 result = Runner.run_sync(agent, "I love Italian food and I'm planning a trip to Rome next month")
@@ -183,21 +183,21 @@ travel_agent = Agent(
     name="Travel Planner",
     instructions="You are a travel planning specialist. Use search_memory and save_memory tools.",
     tools=[search_memory, save_memory],
-    model="gpt-4.1-nano-2025-04-14"
+    model="gpt-5-mini"
 )
 
 health_agent = Agent(
     name="Health Advisor",
     instructions="You are a health and wellness advisor. Use search_memory and save_memory tools.",
     tools=[search_memory, save_memory],
-    model="gpt-4.1-nano-2025-04-14"
+    model="gpt-5-mini"
 )
 
 triage_agent = Agent(
     name="Personal Assistant",
     instructions="""Route travel questions to Travel Planner, health questions to Health Advisor.""",
     handoffs=[travel_agent, health_agent],
-    model="gpt-4.1-nano-2025-04-14"
+    model="gpt-5-mini"
 )
 
 result = Runner.run_sync(triage_agent, "Plan a healthy meal for my Italy trip")
@@ -254,7 +254,7 @@ from langchain_openai import ChatOpenAI
 from mem0 import MemoryClient
 from langchain_core.messages import SystemMessage, HumanMessage, AIMessage
 
-llm = ChatOpenAI(model="gpt-4")
+llm = ChatOpenAI(model="gpt-5-mini")
 mem0 = MemoryClient()
 
 class State(TypedDict):
@@ -319,7 +319,7 @@ memory = Mem0Memory.from_client(
 from llama_index.core.agent import FunctionCallingAgent
 from llama_index.llms.openai import OpenAI
 
-llm = OpenAI(model="gpt-4")
+llm = OpenAI(model="gpt-5-mini")
 agent = FunctionCallingAgent.from_tools(
     tools=[],
     llm=llm,
@@ -352,7 +352,7 @@ USER_ID = "alice"
 
 agent = ConversableAgent(
     "chatbot",
-    llm_config={"config_list": [{"model": "gpt-4", "api_key": os.environ["OPENAI_API_KEY"]}]},
+    llm_config={"config_list": [{"model": "gpt-5-mini", "api_key": os.environ["OPENAI_API_KEY"]}]},
     code_execution_config=False,
     human_input_mode="NEVER",
 )

skills/mem0/references/quickstart.md

@@ -59,11 +59,11 @@ const messages = [
     {"role": "user", "content": "I'm a vegetarian and allergic to nuts."},
     {"role": "assistant", "content": "Got it! I'll remember your dietary preferences."}
 ];
-await client.add(messages, { user_id: "user123" });
+await client.add(messages, { userId: "user123" });
 
 // Search memories
 const results = await client.search("What are my dietary restrictions?", {
-    user_id: "user123"
+    filters: { user_id: "user123" }
 });
 console.log(results);
 ```

skills/mem0/references/sdk-guide.md

@@ -40,16 +40,12 @@ client.add(messages, user_id="alice")
 
 # With metadata
 client.add(messages, user_id="alice", metadata={"source": "onboarding"})
-
-# With graph memory
-client.add(messages, user_id="alice", enable_graph=True)
 ```
 
 **TypeScript:**
 ```typescript
-await client.add(messages, { user_id: "alice" });
-await client.add(messages, { user_id: "alice", metadata: { source: "onboarding" } });
-await client.add(messages, { user_id: "alice", enable_graph: true });
+await client.add(messages, { userId: "alice" });
+await client.add(messages, { userId: "alice", metadata: { source: "onboarding" } });
 ```
 
 ### Parameters
@@ -61,32 +57,14 @@ await client.add(messages, { user_id: "alice", enable_graph: true });
 | `agent_id` | string | Agent identifier |
 | `run_id` | string | Session identifier |
 | `metadata` | object | Custom key-value pairs |
-| `enable_graph` | boolean | Activate knowledge graph |
 | `infer` | boolean | If `false`, store raw text without inference (default: `true`) |
-| `immutable` | boolean | Prevents modification after creation |
-| `expiration_date` | string | Auto-expiry date (`YYYY-MM-DD`) |
-| `includes` | string | Preference filters for inclusion |
-| `excludes` | string | Preference filters for exclusion |
-| `async_mode` | boolean | Async processing (default: `true`). Set `false` to wait |
 
 ### Advanced Add Options
 
 ```python
-# Immutable -- cannot be modified or overwritten
-client.add(messages, user_id="alice", immutable=True)
-
-# Expiring memory
-client.add(messages, user_id="alice", expiration_date="2025-12-31")
-
-# Selective extraction
-client.add(messages, user_id="alice", includes="dietary preferences", excludes="payment info")
-
 # Agent + session scoping
 client.add(messages, user_id="alice", agent_id="nutrition-agent", run_id="session-456")
 
-# Synchronous processing (wait for completion)
-client.add(messages, user_id="alice", async_mode=False)
-
 # Raw text -- skip LLM inference
 client.add(
     [{"role": "user", "content": "User prefers dark mode."}],
@@ -101,7 +79,7 @@ client.add(
 
 **Python:**
 ```python
-results = client.search("dietary preferences?", user_id="alice")
+results = client.search("dietary preferences?", filters={"user_id": "alice"})
 
 # With filters and reranking
 results = client.search(
@@ -111,20 +89,14 @@ results = client.search(
     rerank=True,
     threshold=0.5
 )
-
-# With graph relations
-results = client.search("colleagues", user_id="alice", enable_graph=True)
-
-# Keyword search
-results = client.search("vegetarian", user_id="alice", keyword_search=True)
 ```
 
 **TypeScript:**
 ```typescript
-const results = await client.search("dietary preferences", { user_id: "alice" });
+const results = await client.search("dietary preferences", { filters: { user_id: "alice" } });
 const results = await client.search("work experience", {
     filters: { AND: [{ user_id: "alice" }, { categories: { contains: "professional_details" } }] },
-    top_k: 5,
+    topK: 5,
     rerank: true,
 });
 ```
@@ -134,19 +106,17 @@ const results = await client.search("work experience", {
 | Name | Type | Description |
 |------|------|-------------|
 | `query` | string | Natural language search query |
-| `user_id` | string | Filter by user |
-| `filters` | object | V2 filter object (AND/OR operators) |
-| `top_k` | number | Number of results (default: 10) |
-| `rerank` | boolean | Enable reranking for better relevance |
-| `threshold` | number | Minimum similarity score (default: 0.3) |
-| `keyword_search` | boolean | Use keyword-based search |
-| `enable_graph` | boolean | Include graph relations |
+| `filters` | object | Filter object (AND/OR operators). Use `{"user_id": "..."}` to filter by user |
+| `top_k` | number | Number of results (default: 10 for Platform) |
+| `rerank` | boolean | Enable reranking for better relevance (default: `false`) |
+| `threshold` | number | Minimum similarity score (default: 0.1) |
 
 ### Common Filter Patterns
 
+**Python:**
 ```python
-# Single user (shorthand)
-client.search("query", user_id="alice")
+# Single user filter
+filters={"user_id": "alice"}
 
 # OR across agents
 filters={"OR": [{"user_id": "alice"}, {"agent_id": {"in": ["travel-agent", "sports-agent"]}}]}
@@ -179,6 +149,21 @@ filters={"AND": [
 ]}
 ```
 
+**TypeScript:**
+```typescript
+// Single user filter
+filters: { user_id: "alice" }
+
+// OR across agents
+filters: { OR: [{ user_id: "alice" }, { agent_id: { in: ["travel-agent", "sports-agent"] } }] }
+
+// Category filtering (partial match)
+filters: { AND: [{ user_id: "alice" }, { categories: { contains: "finance" } }] }
+
+// Category filtering (exact match)
+filters: { AND: [{ user_id: "alice" }, { categories: { in: ["personal_information"] } }] }
+```
+
 ---
 
 ## get() / getAll() -- Retrieve Memories
@@ -189,7 +174,7 @@ filters={"AND": [
 memory = client.get(memory_id="ea925981-...")
 
 # All memories for a user
-memories = client.get_all(filters={"AND": [{"user_id": "alice"}]})
+memories = client.get_all(filters={"user_id": "alice"})
 
 # With date range
 memories = client.get_all(
@@ -198,15 +183,12 @@ memories = client.get_all(
         {"created_at": {"gte": "2024-07-01", "lte": "2024-07-31"}}
     ]}
 )
-
-# With graph data
-memories = client.get_all(filters={"AND": [{"user_id": "alice"}]}, enable_graph=True)
 ```
 
 **TypeScript:**
 ```typescript
 const memory = await client.get("ea925981-...");
-const memories = await client.getAll({ filters: { AND: [{ user_id: "alice" }] } });
+const memories = await client.getAll({ filters: { user_id: "alice" } });
 ```
 
 **Note:** `get_all` requires at least one of `user_id`, `agent_id`, `app_id`, or `run_id` in filters.
@@ -226,8 +208,6 @@ client.update(memory_id="ea925981-...", text="Updated", metadata={"verified": Tr
 await client.update("ea925981-...", { text: "Updated: vegan since 2024" });
 ```
 
-Cannot update immutable memories.
-
 ---
 
 ## delete() / deleteAll() -- Remove Memories
@@ -241,7 +221,7 @@ client.delete_all(user_id="alice")  # Irreversible bulk delete
 **TypeScript:**
 ```typescript
 await client.delete("ea925981-...");
-await client.deleteAll({ user_id: "alice" });
+await client.deleteAll({ userId: "alice" });
 ```
 
 ---
@@ -301,10 +281,73 @@ data = client.get_memory_export(memory_export_id=export["id"])
 2. **SQL operators rejected** -- use `gte`, `lt`, etc. Not `>=`, `<`.
 3. **Metadata filtering is limited** -- only top-level keys with `eq`, `contains`, `ne`.
 4. **Wildcard `*` excludes null** -- only matches non-null values.
-5. **Default threshold is 0.3** -- increase for stricter matching.
+5. **Default threshold is 0.1** -- increase for stricter matching.
 6. **Async processing** -- memories process asynchronously. Wait 2-3s after `add()` before searching.
-7. **Immutable memories** -- cannot be updated or deleted once created.
 
 ## Naming Conventions
 
-Python uses `snake_case` (`user_id`, `memory_id`, `get_all`). TypeScript uses `camelCase` for methods (`getAll`, `deleteAll`, `batchUpdate`) but `snake_case` for API parameters (`user_id`, `agent_id`).
+Python uses `snake_case` everywhere (`user_id`, `memory_id`, `get_all`). TypeScript uses `camelCase` for methods (`getAll`, `deleteAll`, `batchUpdate`) and top-level parameters (`userId`, `topK`, `pageSize`), but filter keys use `snake_case` (`user_id`, `agent_id`).
+
+---
+
+## v2 to v3 Migration
+
+### Breaking Changes in v3
+
+**1. Entity IDs in search() and getAll()**
+
+v3 requires entity IDs (`user_id`, `agent_id`, `run_id`) inside `filters` instead of as top-level parameters:
+
+```python
+# v2 (deprecated)
+client.search("query", user_id="alice")
+client.get_all(user_id="alice")
+
+# v3
+client.search("query", filters={"user_id": "alice"})
+client.get_all(filters={"user_id": "alice"})
+```
+
+```typescript
+// v2 (deprecated)
+await client.search("query", { user_id: "alice" });
+await client.getAll({ user_id: "alice" });
+
+// v3
+await client.search("query", { filters: { user_id: "alice" } });
+await client.getAll({ filters: { user_id: "alice" } });
+```
+
+**2. TypeScript Parameter Naming**
+
+v3 TypeScript uses camelCase for all parameters:
+
+| v2 | v3 |
+|----|-----|
+| `user_id` | `userId` |
+| `agent_id` | `agentId` |
+| `run_id` | `runId` |
+| `top_k` | `topK` |
+| `page_size` | `pageSize` |
+
+**3. Default Values Changed**
+
+| Parameter | v2 Default | v3 Default |
+|-----------|------------|------------|
+| `threshold` | 0.3 | 0.1 |
+| `rerank` | (not specified) | `false` |
+
+**4. Removed Parameters**
+
+The following parameters are no longer supported:
+
+| Parameter | Status |
+|-----------|--------|
+| `enable_graph` | Removed from add/search/getAll |
+| `keyword_search` | Removed from search |
+| `filter_memories` | Removed |
+| `immutable` | Removed from add |
+| `expiration_date` | Removed from add |
+| `includes` | Removed from add |
+| `excludes` | Removed from add |
+| `async_mode` | Removed from add |

skills/mem0/references/use-cases.md

@@ -39,7 +39,7 @@ Use these known facts about the user to personalize your response:
 {context if context else 'No prior context yet.'}"""
 
     response = openai_client.chat.completions.create(
-        model="gpt-4.1-nano-2025-04-14",
+        model="gpt-5-mini",
         messages=[
             {"role": "system", "content": system_prompt},
             {"role": "user", "content": user_input},
@@ -72,14 +72,14 @@ const openai = new OpenAI();
 
 async function chat(userInput: string, userId: string): Promise<string> {
     // 1. Retrieve relevant memories
-    const memories = await mem0.search(userInput, { user_id: userId });
+    const memories = await mem0.search(userInput, { filters: { user_id: userId } });
     const context = memories.results
         ?.map((m: any) => `- ${m.memory}`)
         .join('\n') || 'No prior context yet.';
 
     // 2. Generate response with memory context
     const response = await openai.chat.completions.create({
-        model: 'gpt-4.1-nano-2025-04-14',
+        model: 'gpt-5-mini',
         messages: [
             { role: 'system', content: `You are Ray, a personal fitness coach.\nUser context:\n${context}` },
             { role: 'user', content: userInput },
@@ -90,7 +90,7 @@ async function chat(userInput: string, userId: string): Promise<string> {
     // 3. Store interaction
     await mem0.add(
         [{ role: 'user', content: userInput }, { role: 'assistant', content: reply }],
-        { user_id: userId }
+        { userId: userId }
     );
     return reply;
 }
@@ -182,7 +182,7 @@ await client.updateProject({
 async function logInteraction(userId: string, message: string, priority = 'normal') {
     await client.add(
         [{ role: 'user', content: message }],
-        { user_id: userId, metadata: { priority, source: 'support_chat' } }
+        { userId: userId, metadata: { priority, source: 'support_chat' } }
     );
 }
 
@@ -230,7 +230,7 @@ def consult(user_id: str, question: str) -> str:
     context = "\n".join([f"- {m['memory']}" for m in memories.get("results", [])])
 
     response = openai_client.chat.completions.create(
-        model="gpt-4.1-nano-2025-04-14",
+        model="gpt-5-mini",
         messages=[
             {"role": "system", "content": f"You are a health coach. Patient context:\n{context}"},
             {"role": "user", "content": question},
@@ -264,20 +264,20 @@ const openai = new OpenAI();
 async function savePatientInfo(userId: string, info: string) {
     await mem0.add(
         [{ role: 'user', content: info }],
-        { user_id: userId, run_id: 'healthcare_session', metadata: { type: 'patient_information' } }
+        { userId: userId, runId: 'healthcare_session', metadata: { type: 'patient_information' } }
     );
 }
 
 async function consult(userId: string, question: string): Promise<string> {
     const memories = await mem0.search(question, {
-        user_id: userId,
-        top_k: 5,
+        filters: { user_id: userId },
+        topK: 5,
         threshold: 0.7,
     });
     const context = memories.results?.map((m: any) => `- ${m.memory}`).join('\n') || '';
 
     const response = await openai.chat.completions.create({
-        model: 'gpt-4.1-nano-2025-04-14',
+        model: 'gpt-5-mini',
         messages: [
             { role: 'system', content: `You are a health coach. Patient context:\n${context}` },
             { role: 'user', content: question },
@@ -287,7 +287,7 @@ async function consult(userId: string, question: string): Promise<string> {
 
     await mem0.add(
         [{ role: 'user', content: question }, { role: 'assistant', content: reply }],
-        { user_id: userId, run_id: 'healthcare_session' }
+        { userId: userId, runId: 'healthcare_session' }
     );
     return reply;
 }
@@ -333,7 +333,7 @@ def draft_content(user_id: str, topic: str) -> str:
     style_context = "\n".join([f"- {m['memory']}" for m in prefs.get("results", [])])
 
     response = openai_client.chat.completions.create(
-        model="gpt-4.1-nano-2025-04-14",
+        model="gpt-5-mini",
         messages=[
             {"role": "system", "content": f"Write content matching these style preferences:\n{style_context}"},
             {"role": "user", "content": f"Write a blog post about: {topic}"},
@@ -359,7 +359,7 @@ const openai = new OpenAI();
 async function storePreferences(userId: string, preferences: string) {
     await mem0.add(
         [{ role: 'user', content: preferences }],
-        { user_id: userId, run_id: 'editing_session', metadata: { type: 'preferences' } }
+        { userId: userId, runId: 'editing_session', metadata: { type: 'preferences' } }
     );
 }
 
@@ -370,7 +370,7 @@ async function draftContent(userId: string, topic: string): Promise<string> {
     const styleContext = prefs.results?.map((m: any) => `- ${m.memory}`).join('\n') || '';
 
     const response = await openai.chat.completions.create({
-        model: 'gpt-4.1-nano-2025-04-14',
+        model: 'gpt-5-mini',
         messages: [
             { role: 'system', content: `Write content matching these preferences:\n${styleContext}` },
             { role: 'user', content: `Write a blog post about: ${topic}` },
@@ -465,10 +465,10 @@ async function storeScopedMemory(
     userId: string, agentId: string, runId: string, appId: string
 ) {
     await client.add(messages, {
-        user_id: userId,
-        agent_id: agentId,
-        run_id: runId,
-        app_id: appId,
+        userId: userId,
+        agentId: agentId,
+        runId: runId,
+        appId: appId,
     });
 }
 
@@ -520,7 +520,7 @@ def personalized_search(user_id: str, query: str, search_results: list) -> str:
     user_context = "\n".join([f"- {m['memory']}" for m in memories.get("results", [])])
 
     response = openai_client.chat.completions.create(
-        model="gpt-4.1-nano-2025-04-14",
+        model="gpt-5-mini",
         messages=[
             {"role": "system", "content": f"Personalize search results using user context:\n{user_context}"},
             {"role": "user", "content": f"Query: {query}\n\nSearch results:\n{search_results}"},
@@ -551,11 +551,11 @@ const mem0 = new MemoryClient({ apiKey: process.env.MEM0_API_KEY! });
 const openai = new OpenAI();
 
 async function personalizedSearch(userId: string, query: string, searchResults: string[]): Promise<string> {
-    const memories = await mem0.search(query, { user_id: userId, top_k: 5 });
+    const memories = await mem0.search(query, { filters: { user_id: userId }, topK: 5 });
     const context = memories.results?.map((m: any) => `- ${m.memory}`).join('\n') || '';
 
     const response = await openai.chat.completions.create({
-        model: 'gpt-4.1-nano-2025-04-14',
+        model: 'gpt-5-mini',
         messages: [
             { role: 'system', content: `Personalize results using user context:\n${context}` },
             { role: 'user', content: `Query: ${query}\nResults: ${searchResults.join(', ')}` },
@@ -563,7 +563,7 @@ async function personalizedSearch(userId: string, query: string, searchResults:
     });
     const reply = response.choices[0].message.content!;
 
-    await mem0.add([{ role: 'user', content: query }], { user_id: userId });
+    await mem0.add([{ role: 'user', content: query }], { userId: userId });
     return reply;
 }
 ```
@@ -631,14 +631,14 @@ const client = new MemoryClient({ apiKey: process.env.MEM0_API_KEY! });
 async function storeEmail(userId: string, sender: string, subject: string, body: string, date: string) {
     await client.add(
         [{ role: 'user', content: `Email from ${sender}: ${subject}\n\n${body}` }],
-        { user_id: userId, metadata: { email_type: 'incoming', sender, subject, date } }
+        { userId: userId, metadata: { email_type: 'incoming', sender, subject, date } }
     );
 }
 
 async function searchEmails(userId: string, query: string) {
     return client.search(query, {
         filters: { AND: [{ user_id: userId }, { categories: { contains: 'email' } }] },
-        top_k: 10,
+        topK: 10,
     });
 }
 ```