deploy minor version -> 0.1.107rc2 (#2953)

Co-authored-by: Deshraj Yadav <deshraj@gatech.edu>

docs/api-reference/memory/v2-get-memories.mdx

@@ -9,6 +9,9 @@ The v2 get memories API is powerful and flexible, allowing for more precise memo
 - `lte`: Less than or equal to
 - `gt`: Greater than
 - `lt`: Less than
+- `ne`: Not equal to
+- `icontains`: Case-insensitive containment check
+- `*`: Wildcard character that matches everything
 
 <CodeGroup>
 ```python Code
@@ -41,3 +44,22 @@ memories = m.get_all(
 ]
 ```
 </CodeGroup>
+
+<CodeGroup>
+```python Wildcard Example
+# Using wildcard to get all memories for a specific user across all run_ids
+memories = m.get_all(
+    filters={
+        "AND": [
+            {
+                "user_id": "alex"
+            },
+            {
+                "run_id": "*"
+            }
+        ]
+    },
+    version="v2"
+)
+```
+</CodeGroup>

docs/api-reference/memory/v2-search-memories.mdx

@@ -11,6 +11,7 @@ The v2 search API is powerful and flexible, allowing for more precise memory ret
 - `lt`: Less than
 - `ne`: Not equal to
 - `icontains`: Case-insensitive containment check
+- `*`: Wildcard character that matches everything
 
   <CodeGroup>
   ```python Code
@@ -49,3 +50,23 @@ The v2 search API is powerful and flexible, allowing for more precise memory ret
   }
   ```
   </CodeGroup>
+
+  <CodeGroup>
+  ```python Wildcard Example
+  # Using wildcard to match all run_ids for a specific user
+  all_memories = m.search(
+      query="What are Alice's hobbies?",
+      version="v2",
+      filters={
+          "AND": [
+              {
+                  "user_id": "alice"
+              },
+              {
+                  "run_id": "*"
+              }
+          ]
+      },
+  )
+  ```
+  </CodeGroup>

docs/changelog.mdx

@@ -288,6 +288,14 @@ mode: "wide"
 
 <Tab title="TypeScript">
 
+<Update label="2025-06-06" description="v2.1.30">
+**New Features:**
+- **OSS:** Added Cloudflare support
+
+**Improvements:**
+- **OSS:** Fixed baseURL param in LLM Config.
+</Update>
+
 <Update label="2025-05-30" description="v2.1.29">
 **Improvements:**
 - **Client:** Added Async Mode Param for `add` method.

docs/components/llms/overview.mdx

@@ -34,7 +34,7 @@ To view all supported llms, visit the [Supported LLMs](./models).
   <Card title="Gemini" href="/components/llms/models/gemini" />
   <Card title="DeepSeek" href="/components/llms/models/deepseek" />
   <Card title="xAI" href="/components/llms/models/xAI" />
-  <Card title="XAI" href="/components/llms/models/sarvam" />
+  <Card title="Sarvam AI" href="/components/llms/models/sarvam" />
   <Card title="LM Studio" href="/components/llms/models/lmstudio" />
   <Card title="Langchain" href="/components/llms/models/langchain" />
 </CardGroup>

docs/components/vectordbs/dbs/vectorize.mdx

@@ -0,0 +1,45 @@
+[Cloudflare Vectorize](https://developers.cloudflare.com/vectorize/) is a vector database offering from Cloudflare, allowing you to build AI-powered applications with vector embeddings.
+
+### Usage
+
+<CodeGroup>
+```typescript TypeScript
+import { Memory } from 'mem0ai/oss';
+
+const config = {
+  vectorStore: {
+    provider: 'vectorize',
+    config: {
+      indexName: 'my-memory-index',
+      accountId: 'your-cloudflare-account-id',
+      apiKey: 'your-cloudflare-api-key',
+      dimension: 1536, // Optional: defaults to 1536
+    },
+  },
+};
+
+const memory = new Memory(config);
+const messages = [
+    {"role": "user", "content": "I'm looking for a good book to read."},
+    {"role": "assistant", "content": "Sure, what genre are you interested in?"},
+    {"role": "user", "content": "I enjoy fantasy novels with strong world-building."},
+    {"role": "assistant", "content": "Great! I'll keep that in mind for future recommendations."}
+]
+await memory.add(messages, { userId: "bob", metadata: { interest: "books" } });
+```
+</CodeGroup>
+
+### Config
+
+Let's see the available parameters for the `vectorize` config:
+
+<Tabs>
+<Tab title="TypeScript">
+| Parameter | Description | Default Value |
+| --- | --- | --- |
+| `indexName` | The name of the Vectorize index | `None` (Required) |
+| `accountId` | Your Cloudflare account ID | `None` (Required) |
+| `apiKey` | Your Cloudflare API token | `None` (Required) |
+| `dimension` | Dimensions of the embedding model | `1536` |
+</Tab>
+</Tabs>

docs/components/vectordbs/overview.mdx

@@ -13,7 +13,7 @@ Mem0 includes built-in support for various popular databases. Memory can utilize
 See the list of supported vector databases below.
 
 <Note>
-  The following vector databases are supported in the Python implementation. The TypeScript implementation currently only supports Qdrant, Redis and in-memory vector database.
+  The following vector databases are supported in the Python implementation. The TypeScript implementation currently only supports Qdrant, Redis,Vectorize and in-memory vector database.
 </Note>
 
 <CardGroup cols={3}>

docs/integrations/livekit.mdx

@@ -12,8 +12,7 @@ Before you begin, make sure you have:
 
 1. Installed Livekit Agents SDK with voice dependencies of silero and deepgram:
 ```bash
-pip install livekit \
-livekit-agents \
+pip install livekit-agents[voice] \
 livekit-plugins-silero \
 livekit-plugins-deepgram \
 livekit-plugins-openai
@@ -38,7 +37,7 @@ OPENAI_API_KEY=your_openai_api_key
 
 ## Code Breakdown
 
-Let's break down the key components of this implementation:
+Let's break down the key components of this implementation using LiveKit Agents:
 
 ### 1. Setting Up Dependencies and Environment
 
@@ -51,17 +50,19 @@ from typing import List, Dict, Any, Annotated
 import aiohttp
 from dotenv import load_dotenv
 from livekit.agents import (
+    Agent,
+    AgentSession,
     AutoSubscribe,
     JobContext,
-    JobProcess,
-    WorkerOptions,
-    cli,
     llm,
-    metrics,
+    function_tool,
+    RunContext,
+    cli,
+    WorkerOptions,
+    ModelSettings,
 )
-from livekit import rtc, api
-from livekit.agents.pipeline import VoicePipelineAgent
 from livekit.plugins import deepgram, openai, silero
+from livekit.plugins.turn_detector.multilingual import MultilingualModel
 from mem0 import AsyncMemoryClient
 
 # Load environment variables
@@ -88,36 +89,45 @@ This section handles:
 ### 2. Memory Enrichment Function
 
 ```python
-async def _enrich_with_memory(agent: VoicePipelineAgent, chat_ctx: llm.ChatContext):
-    """Add memories and Augment chat context with relevant memories"""
+async def _enrich_with_memory(chat_ctx: llm.ChatContext):
+    """Add memories and augment chat context with relevant memories"""
     if not chat_ctx.messages:
         return
-    
-    # Store user message in Mem0
+
+    # Get the latest user message
     user_msg = chat_ctx.messages[-1]
+    if user_msg.role != "user":
+        return
+
+    user_content = user_msg.text_content()
+    if not user_content:
+        return
+
+    # Store user message in Mem0
     await mem0.add(
-        [{"role": "user", "content": user_msg.content}], 
+        [{"role": "user", "content": user_content}],
         user_id=USER_ID
     )
-    
+
     # Search for relevant memories
     results = await mem0.search(
-        user_msg.content, 
+        user_content,
         user_id=USER_ID,
     )
-    
+
     # Augment context with retrieved memories
     if results:
         memories = ' '.join([result["memory"] for result in results])
         logger.info(f"Enriching with memory: {memories}")
-        
-        rag_msg = llm.ChatMessage.create(
+
+        # Add memory context as a assistant message
+        memory_msg = llm.ChatMessage.create(
             text=f"Relevant Memory: {memories}\n",
             role="assistant",
         )
-        
+
         # Modify chat context with retrieved memories
-        chat_ctx.messages[-1] = rag_msg
+        chat_ctx.messages[-1] = memory_msg
         chat_ctx.messages.append(user_msg)
 ```
 
@@ -130,62 +140,45 @@ This function:
 ### 3. Prewarm and Entrypoint Functions
 
 ```python
-def prewarm_process(proc: JobProcess):
-    # Preload silero VAD in memory to speed up session start
+def prewarm_process(proc):
+    """Preload components to speed up session start"""
     proc.userdata["vad"] = silero.VAD.load()
 
 async def entrypoint(ctx: JobContext):
+    """Main entrypoint for the memory-enabled voice agent"""
+
     # Connect to LiveKit room
     await ctx.connect(auto_subscribe=AutoSubscribe.AUDIO_ONLY)
-    
-    # Wait for participant
-    participant = await ctx.wait_for_participant()
-    
-    # Initialize Mem0 client
-    mem0 = AsyncMemoryClient()
 
-    # Define initial system context
-    initial_ctx = llm.ChatContext().append(
-        role="system",
-        text=(
-            """
-            You are a helpful voice assistant.
-            You are a travel guide named George and will help the user to plan a travel trip of their dreams. 
-            You should help the user plan for various adventures like work retreats, family vacations or solo backpacking trips. 
-            You should be careful to not suggest anything that would be dangerous, illegal or inappropriate.
-            You can remember past interactions and use them to inform your answers.
-            Use semantic memory retrieval to provide contextually relevant responses. 
-            """
-        ),
-    )
-
-    # Create VoicePipelineAgent with memory capabilities
-    agent = VoicePipelineAgent(
-        chat_ctx=initial_ctx,
-        vad=silero.VAD.load(),
+    # Create agent session with modern 1.0 architecture
+    session = AgentSession(
         stt=deepgram.STT(),
         llm=openai.LLM(model="gpt-4o-mini"),
         tts=openai.TTS(),
-        before_llm_cb=_enrich_with_memory,
+        vad=silero.VAD.load(),
+        turn_detection=MultilingualModel(),
     )
 
-    # Start agent and initial greeting
-    agent.start(ctx.room, participant)
-    await agent.say(
-        "Hello! I'm George. Can I help you plan an upcoming trip? ",
-        allow_interruptions=True
+    # Create memory-enabled agent
+    agent = MemoryEnabledAgent()
+
+    # Start the session
+    await session.start(
+        room=ctx.room,
+        agent=agent,
     )
 
-# Run the application
-if __name__ == "__main__":
-    cli.run_app(WorkerOptions(entrypoint_fnc=entrypoint, prewarm_fnc=prewarm_process))
+    # Initial greeting
+    await session.generate_reply(
+        instructions="Greet the user warmly as George the travel guide and ask how you can help them plan their next adventure."
+    )
 ```
 
 The entrypoint function:
 - Connects to LiveKit room
 - Initializes Mem0 memory client
-- Sets up initial system context
-- Creates a VoicePipelineAgent with memory enrichment
+- Create agent session using `AgentSession` orchestrator with memory enrichment
+- Uses modern turn detection with `MultilingualModel()`
 - Starts the agent with an initial greeting
 
 ## Create a Memory-Enabled Voice Agent
@@ -196,22 +189,22 @@ Now that we've explained each component, here's the complete implementation that
 import asyncio
 import logging
 import os
-from typing import List, Dict, Any, Annotated
+from typing import AsyncIterable, Any
 
-import aiohttp
 from dotenv import load_dotenv
 from livekit.agents import (
-    AutoSubscribe,
+    Agent,
+    AgentSession,
     JobContext,
-    JobProcess,
-    WorkerOptions,
-    cli,
     llm,
-    metrics,
+    function_tool,
+    RunContext,
+    cli,
+    WorkerOptions,
+    ModelSettings,
 )
-from livekit import rtc, api
-from livekit.agents.pipeline import VoicePipelineAgent
 from livekit.plugins import deepgram, openai, silero
+from livekit.plugins.turn_detector.multilingual import MultilingualModel
 from mem0 import AsyncMemoryClient
 
 # Load environment variables
@@ -227,92 +220,129 @@ USER_ID = "voice_user"
 # Initialize Mem0 memory client
 mem0 = AsyncMemoryClient()
 
-def prewarm_process(proc: JobProcess):
-    # Preload silero VAD in memory to speed up session start
-    proc.userdata["vad"] = silero.VAD.load()
+class MemoryEnabledAgent(Agent):
+    """Travel guide agent with Mem0 memory integration"""
 
-async def entrypoint(ctx: JobContext):
-    # Connect to LiveKit room
-    await ctx.connect(auto_subscribe=AutoSubscribe.AUDIO_ONLY)
-    
-    # Wait for participant
-    participant = await ctx.wait_for_participant()
-    
-    async def _enrich_with_memory(agent: VoicePipelineAgent, chat_ctx: llm.ChatContext):
-        """Add memories and Augment chat context with relevant memories"""
+    def __init__(self):
+        super().__init__(
+            instructions="""
+            You are a helpful voice assistant.
+            You are a travel guide named George and will help the user to plan a travel trip of their dreams.
+            You should help the user plan for various adventures like work retreats, family vacations or solo backpacking trips.
+            You should be careful to not suggest anything that would be dangerous, illegal or inappropriate.
+            You can remember past interactions and use them to inform your answers.
+            Use semantic memory retrieval to provide contextually relevant responses.
+            """
+        )
+
+    async def llm_node(
+        self,
+        chat_ctx: llm.ChatContext,
+        tools: list[llm.FunctionTool],
+        model_settings: ModelSettings,
+    ) -> AsyncIterable[llm.ChatChunk]:
+        """Override LLM node to add memory enrichment before inference"""
+
+        # Enrich context with memory before LLM inference
+        await self._enrich_with_memory(chat_ctx)
+
+        # Call default LLM node with enriched context
+        async for chunk in Agent.default.llm_node(self, chat_ctx, tools, model_settings):
+            yield chunk
+
+    async def _enrich_with_memory(self, chat_ctx: llm.ChatContext):
+        """Add memories and augment chat context with relevant memories"""
         if not chat_ctx.messages:
             return
-        
-        # Store user message in Mem0
+
+        # Get the latest user message
         user_msg = chat_ctx.messages[-1]
+        if user_msg.role != "user":
+            return
+
+        user_content = user_msg.text_content()
+        if not user_content:
+            return
+
+        # Store user message in Mem0
         await mem0.add(
-            [{"role": "user", "content": user_msg.content}], 
+            [{"role": "user", "content": user_content}],
             user_id=USER_ID
         )
-        
+
         # Search for relevant memories
         results = await mem0.search(
-            user_msg.content, 
+            user_content,
             user_id=USER_ID,
         )
-        
+
         # Augment context with retrieved memories
         if results:
             memories = ' '.join([result["memory"] for result in results])
             logger.info(f"Enriching with memory: {memories}")
-            
-            rag_msg = llm.ChatMessage.create(
+
+            # Add memory context as a assistant message
+            memory_msg = llm.ChatMessage.create(
                 text=f"Relevant Memory: {memories}\n",
                 role="assistant",
             )
-            
+
             # Modify chat context with retrieved memories
-            chat_ctx.messages[-1] = rag_msg
+            chat_ctx.messages[-1] = memory_msg
             chat_ctx.messages.append(user_msg)
 
-    # Define initial system context
-    initial_ctx = llm.ChatContext().append(
-        role="system",
-        text=(
-            """
-            You are a helpful voice assistant.
-            You are a travel guide named George and will help the user to plan a travel trip of their dreams. 
-            You should help the user plan for various adventures like work retreats, family vacations or solo backpacking trips. 
-            You should be careful to not suggest anything that would be dangerous, illegal or inappropriate.
-            You can remember past interactions and use them to inform your answers.
-            Use semantic memory retrieval to provide contextually relevant responses. 
-            """
-        ),
-    )
+def prewarm_process(proc):
+    """Preload components to speed up session start"""
+    proc.userdata["vad"] = silero.VAD.load()
 
-    # Create VoicePipelineAgent with memory capabilities
-    agent = VoicePipelineAgent(
-        chat_ctx=initial_ctx,
-        vad=silero.VAD.load(),
+async def entrypoint(ctx: JobContext):
+    """Main entrypoint for the memory-enabled voice agent"""
+
+    # Connect to LiveKit room
+    await ctx.connect(auto_subscribe=AutoSubscribe.AUDIO_ONLY)
+
+    # Initialize Mem0 client
+    mem0 = AsyncMemoryClient()
+
+    # Create agent session with modern 1.0 architecture
+    session = AgentSession(
         stt=deepgram.STT(),
         llm=openai.LLM(model="gpt-4o-mini"),
         tts=openai.TTS(),
-        before_llm_cb=_enrich_with_memory,
+        vad=silero.VAD.load(),
+        turn_detection=MultilingualModel(),
     )
 
-    # Start agent and initial greeting
-    agent.start(ctx.room, participant)
-    await agent.say(
-        "Hello! I'm George. Can I help you plan an upcoming trip? ",
+    # Create memory-enabled agent
+    agent = MemoryEnabledAgent()
+
+    # Start the session
+    await session.start(
+        room=ctx.room,
+        agent=agent,
+    )
+
+    # Initial greeting
+    await session.generate_reply(
+        instructions="Greet the user warmly as George the travel guide and ask how you can help them plan their next adventure.",
         allow_interruptions=True
     )
 
 # Run the application
 if __name__ == "__main__":
-    cli.run_app(WorkerOptions(entrypoint_fnc=entrypoint, prewarm_fnc=prewarm_process))
+    cli.run_app(WorkerOptions(
+        entrypoint_fnc=entrypoint,
+        prewarm_fnc=prewarm_process
+    ))
 ```
 
 ## Key Features of This Implementation
 
 1. **Semantic Memory Retrieval**: Uses Mem0 to store and retrieve contextually relevant memories
-2. **Voice Interaction**: Leverages LiveKit for voice communication
+2. **Voice Interaction**: Leverages LiveKit for voice communication with proper turn detection
 3. **Intelligent Context Management**: Augments conversations with past interactions
 4. **Travel Planning Specialization**: Focused on creating a helpful travel guide assistant
+5. **Function Tools**: Modern tool definition for enhanced capabilities
 
 ## Running the Example
 
@@ -325,13 +355,13 @@ To run this example:
 ```sh
 python mem0-livekit-voice-agent.py start
 ```
-5. After the script starts, you can interact with the voice agent using [Livekit's Agent Platform](https://agents-playground.livekit.io/) and Connect to the agent inorder to start conversations. 
+5. After the script starts, you can interact with the voice agent using [Livekit's Agent Platform](https://agents-playground.livekit.io/) and connect to the agent inorder to start conversations.
 
 ## Best Practices for Voice Agents with Memory
 
 1. **Context Preservation**: Store enough context with each memory for effective retrieval
 2. **Privacy Considerations**: Implement secure memory management
-3. **Relevant Memory Filtering**: Use semantic search to retrieve only the most pertinent memories
+3. **Relevant Memory Filtering**: Use semantic search to retrieve only the most relevant memories
 4. **Error Handling**: Implement robust error handling for memory operations
 
 ## Debugging Function Tools

docs/openmemory/overview.mdx

@@ -6,6 +6,24 @@ iconType: "solid"
 
 <Snippet file="paper-release.mdx" />
 
+## 🚀 Hosted OpenMemory MCP Now Available!
+
+#### Sign Up Now - [app.openmemory.dev](https://app.openmemory.dev)
+
+Everything you love about OpenMemory MCP but with zero setup.
+
+✅ Works with all MCP-compatible tools (Claude Desktop, Cursor...)  
+✅ Same standard memory ops: `add_memories`, `search_memory`, etc  
+✅ One-click provisioning, no Docker required  
+✅ Powered by Mem0  
+
+Add shared, persistent, low-friction memory to your MCP-compatible clients in seconds.
+
+### 🌟 Get Started Now
+**Sign up and get your access key at [app.openmemory.dev](https://app.openmemory.dev)**
+
+Example installation: `npx @openmemory/install --client claude --env OPENMEMORY_API_KEY=your-key`
+
 OpenMemory is a local memory infrastructure powered by Mem0 that lets you carry your memory accross any AI app. It provides a unified memory layer that stays with you, enabling agents and assistants to remember what matters across applications.
 
 <img src="https://github.com/user-attachments/assets/3c701757-ad82-4afa-bfbe-e049c2b4320b" alt="OpenMemory UI" />

docs/openmemory/quickstart.mdx

@@ -6,6 +6,46 @@ iconType: "solid"
 
 <Snippet file="paper-release.mdx" />
 
+## 🚀 Hosted OpenMemory MCP Now Available!
+
+#### Sign Up Now - [app.openmemory.dev](https://app.openmemory.dev)
+
+Everything you love about OpenMemory MCP but with zero setup.
+
+✅ Works with all MCP-compatible tools (Claude Desktop, Cursor...)  
+✅ Same standard memory ops: `add_memories`, `search_memory`, etc  
+✅ One-click provisioning, no Docker required  
+✅ Powered by Mem0  
+
+Add shared, persistent, low-friction memory to your MCP-compatible clients in seconds.
+
+### 🌟 Get Started Now
+**Sign up and get your access key at [app.openmemory.dev](https://app.openmemory.dev)**
+
+Example installation: `npx @openmemory/install --client claude --env OPENMEMORY_API_KEY=your-key`
+
+## Getting Started with Hosted OpenMemory
+
+The fastest way to get started is with our hosted version - no setup required:
+
+### 1. Get your API key
+Visit [app.openmemory.dev](https://app.openmemory.dev) to sign up and get your `OPENMEMORY_API_KEY`.
+
+### 2. Install and connect to your preferred client
+Example commands (replace `your-key` with your actual API key):
+
+For Claude Desktop: `npx @openmemory/install --client claude --env OPENMEMORY_API_KEY=your-key`
+
+For Cursor: `npx @openmemory/install --client cursor --env OPENMEMORY_API_KEY=your-key`
+
+For Windsurf: `npx @openmemory/install --client windsurf --env OPENMEMORY_API_KEY=your-key`
+
+That's it! Your AI client now has persistent memory across sessions.
+
+## Local Setup (Self-Hosted)
+
+Prefer to run OpenMemory locally? Follow the instructions below for a self-hosted setup.
+
 ## OpenMemory Easy Setup
 
 ### Prerequisites
@@ -38,22 +78,75 @@ We suggest you follow the instructions below to set up OpenMemory on your local
 Getting started with OpenMemory is straight forward and takes just a few minutes to set up on your local machine. Follow these steps:
 
 ### Getting started
-First clone the repository and then follow the instructions:
+
+
+### 1. First clone the repository and then follow the instructions:
 ```bash
 # Clone the repository
 git clone https://github.com/mem0ai/mem0.git
 cd mem0/openmemory
-
-# Create the backend .env file with your OpenAI key
-make env
-
-# Build the Docker images
-make build
-
-# Start all services (API server, vector database, and MCP server components)
-make up
 ```
 
+### 2. 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`
+
+``` bash
+OPENAI_API_KEY=sk-xxx
+USER=<user-id> # The User Id you want to associate the memories with 
+```
+- #### Example `/ui/.env`
+
+```bash
+NEXT_PUBLIC_API_URL=http://localhost:8765
+NEXT_PUBLIC_USER_ID=<user-id> # Same as the user id for environment variable in api
+```
+
+### 3. 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 http://localhost:3000?
+
+If the UI does not start properly on http://localhost:3000, try running it manually:
+
+```bash
+cd ui
+pnpm install
+pnpm dev
+```
+
+
 You can configure the MCP client using the following command (replace username with your username):
 
 ```bash

docs/platform/quickstart.mdx

@@ -458,7 +458,7 @@ curl -X POST "https://api.mem0.ai/v1/memories/search/?version=v2" \
 
 #### Search using custom filters
 
-Our advanced search allows you to set custom search filters. You can filter by user_id, agent_id, app_id, run_id, created_at, updated_at, categories, and text. The filters support logical operators (AND, OR) and comparison operators (in, gte, lte, gt, lt, ne, contains, icontains). For more details, see [V2 Search Memories](/api-reference/memory/v2-search-memories).
+Our advanced search allows you to set custom search filters. You can filter by user_id, agent_id, app_id, run_id, created_at, updated_at, categories, and text. The filters support logical operators (AND, OR) and comparison operators (in, gte, lte, gt, lt, ne, contains, icontains, *). The wildcard character (*) matches everything for a specific field. For more details, see [V2 Search Memories](/api-reference/memory/v2-search-memories).
 
 Here you need to define `version` as `v2` in the search method.
 
@@ -765,6 +765,81 @@ curl -X POST "https://api.mem0.ai/v1/memories/search/?version=v2" \
 
 </CodeGroup>
 
+Example 5: Search using wildcard filters
+<CodeGroup>
+```python Python
+query = "What do you know about me?"
+filters = {
+    "AND": [
+        {
+            "user_id": "alex"
+        },
+        {
+            "run_id": "*"  # Matches all run_ids
+        }
+    ]
+}
+client.search(query, version="v2", filters=filters)
+```
+
+```javascript JavaScript
+const query = "What do you know about me?";
+const filters = {
+    "AND": [
+        {
+            "user_id": "alex"
+        },
+        {
+            "run_id": "*"  // Matches all run_ids
+        }
+    ]
+};
+
+client.search(query, { version: "v2", filters })
+    .then(results => console.log(results))
+    .catch(error => console.error(error));
+```
+
+```bash cURL
+curl -X POST "https://api.mem0.ai/v1/memories/search/?version=v2" \
+     -H "Authorization: Token your-api-key" \
+     -H "Content-Type: application/json" \
+     -d '{
+         "query": "What do you know about me?",
+         "filters": {
+             "AND": [
+                 {
+                     "user_id": "alex"
+                 },
+                 {
+                     "run_id": "*"
+                 }
+             ]
+         }
+     }'
+```
+
+```json Output
+{
+    "results": [
+        {
+            "id": "7f165f7e-b411-4afe-b7e5-35789b72c4a5",
+            "memory": "Name: Alex. Vegetarian. Allergic to nuts.",
+            "user_id": "alex",
+            "run_id": "session-1",
+            "metadata": null,
+            "categories": ["food_preferences"],
+            "immutable": false,
+            "expiration_date": null,
+            "created_at": "2024-07-20T01:30:36.275141-07:00",
+            "updated_at": "2024-07-20T01:30:36.275172-07:00"
+        }
+    ]
+}
+```
+
+</CodeGroup>
+
 
 ### 4.3 Get All Users
 
@@ -1138,7 +1213,7 @@ curl -X GET "https://api.mem0.ai/v1/memories/?user_id=alex&keywords=to play&page
 
 #### Get all memories using custom filters
 
-Our advanced retrieval allows you to set custom filters when fetching memories. You can filter by user_id, agent_id, app_id, run_id, created_at, updated_at, categories, and keywords. The filters support logical operators (AND, OR) and comparison operators (in, gte, lte, gt, lt, ne, contains, icontains). For more details, see [v2 Get Memories](/api-reference/memory/v2-get-memories).
+Our advanced retrieval allows you to set custom filters when fetching memories. You can filter by user_id, agent_id, app_id, run_id, created_at, updated_at, categories, and keywords. The filters support logical operators (AND, OR) and comparison operators (in, gte, lte, gt, lt, ne, contains, icontains, *). The wildcard character (*) matches everything for a specific field. For more details, see [v2 Get Memories](/api-reference/memory/v2-get-memories).
 
 Here you need to define `version` as `v2` in the get_all method.
 
@@ -1497,6 +1572,119 @@ curl -X GET "https://api.mem0.ai/v1/memories/?version=v2&page=1&page_size=50" \
 
 </CodeGroup>
 
+Example 4: Get all memories using wildcard filters
+<CodeGroup>
+```python Python
+filters = {
+    "AND": [
+        {
+            "user_id": "alex"
+        },
+        {
+            "run_id": "*"  # Matches all run_ids
+        }
+    ]
+}
+
+# Default (No Pagination)
+client.get_all(version="v2", filters=filters)
+
+# Pagination (You can also use the page and page_size parameters)
+client.get_all(version="v2", filters=filters, page=1, page_size=50)
+```
+
+```javascript JavaScript
+const filters = {
+    "AND": [
+        {
+            "user_id": "alex"
+        },
+        {
+            "run_id": "*"  // Matches all run_ids
+        }
+    ]
+};
+
+// Default (No Pagination)
+client.getAll({ version: "v2", filters })
+    .then(memories => console.log(memories))
+    .catch(error => console.error(error));
+
+// Pagination (You can also use the page and page_size parameters)
+client.getAll({ version: "v2", filters, page: 1, page_size: 50 })
+    .then(memories => console.log(memories))
+    .catch(error => console.error(error));
+```
+
+```bash cURL
+# Default (No Pagination)
+curl -X GET "https://api.mem0.ai/v1/memories/?version=v2" \
+     -H "Authorization: Token your-api-key" \
+     -H "Content-Type: application/json" \
+     -d '{
+         "filters": {
+             "AND": [
+                {"user_id":"alex"},
+                {"run_id": "*"}
+             ]
+         }
+     }'
+
+# Pagination (You can also use the page and page_size parameters)
+curl -X GET "https://api.mem0.ai/v1/memories/?version=v2&page=1&page_size=50" \
+     -H "Authorization: Token your-api-key" \
+     -H "Content-Type: application/json" \
+     -d '{
+         "filters": {
+             "AND": [
+                {"user_id":"alex"},
+                {"run_id": "*"}
+             ]
+         }
+     }'
+```
+
+```json Output (Default)
+[
+    {
+        "id": "f38b689d-6b24-45b7-bced-17fbb4d8bac7",
+        "memory": "Name: Alex. Vegetarian. Allergic to nuts.",
+        "user_id": "alex",
+        "run_id": "session-1",
+        "metadata": null,
+        "categories": ["food_preferences"],
+        "immutable": false,
+        "expiration_date": null,
+        "created_at": "2024-07-20T01:30:36.275141-07:00",
+        "updated_at": "2024-07-20T01:30:36.275172-07:00"
+    }
+]
+```
+
+```json Output (Paginated)
+{
+    "count": 1,
+    "next": null,
+    "previous": null,
+    "results": [
+        {
+            "id": "f38b689d-6b24-45b7-bced-17fbb4d8bac7",
+            "memory": "Name: Alex. Vegetarian. Allergic to nuts.",
+            "user_id": "alex",
+            "run_id": "session-1",
+            "metadata": null,
+            "categories": ["food_preferences"],
+            "immutable": false,
+            "expiration_date": null,
+            "created_at": "2024-07-20T01:30:36.275141-07:00",
+            "updated_at": "2024-07-20T01:30:36.275172-07:00"
+        }
+    ]
+}
+```
+
+</CodeGroup>
+
 
 ### 4.5 Memory History
 

mem0-ts/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mem0ai",
-  "version": "2.1.29",
+  "version": "2.1.30",
   "description": "The Memory Layer For Your AI Apps",
   "main": "./dist/index.js",
   "module": "./dist/index.mjs",
@@ -107,6 +107,8 @@
     "@types/sqlite3": "3.1.11",
     "groq-sdk": "0.3.0",
     "@langchain/core": "^0.3.44",
+    "cloudflare": "^4.2.0",
+    "@cloudflare/workers-types": "^4.20250504.0",
     "neo4j-driver": "^5.28.1",
     "ollama": "^0.5.14",
     "pg": "8.11.3",

mem0-ts/pnpm-lock.yaml

@@ -10,6 +10,9 @@ importers:
       "@anthropic-ai/sdk":
         specifier: ^0.40.1
         version: 0.40.1(encoding@0.1.13)
+      "@cloudflare/workers-types":
+        specifier: ^4.20250504.0
+        version: 4.20250606.0
       "@google/genai":
         specifier: ^1.2.0
         version: 1.2.0(@modelcontextprotocol/sdk@1.12.1)(encoding@0.1.13)
@@ -37,6 +40,9 @@ importers:
       axios:
         specifier: 1.7.7
         version: 1.7.7
+      cloudflare:
+        specifier: ^4.2.0
+        version: 4.3.0(encoding@0.1.13)
       groq-sdk:
         specifier: 0.3.0
         version: 0.3.0(encoding@0.1.13)
@@ -385,6 +391,12 @@ packages:
         integrity: sha512-gAmrUZSGtKc3AiBL71iNWxDsyUC5uMaKKGdvzYsBoTW/xi42JQHl7eKV2OYzCUqvc+D2RCcf7EXY2iCyFIk6og==,
       }
 
+  "@cloudflare/workers-types@4.20250606.0":
+    resolution:
+      {
+        integrity: sha512-9T/Y/Mxe57UVzqgfjJKheiMplnStj/3CmCHlgoZNLU8JW2waRbXvpY3EEeliiYAJfeHZTjeAaKO2pCabxAoyCw==,
+      }
+
   "@cspotcode/source-map-support@0.8.1":
     resolution:
       {
@@ -1811,6 +1823,12 @@ packages:
       }
     engines: { node: ">=12" }
 
+  cloudflare@4.3.0:
+    resolution:
+      {
+        integrity: sha512-C+4Jhsl/OY4V5sykRB1yJxComDld5BkKW1xd3s0MDJ1yYamT2sFAoC2FEUQg5zipyxMaaGU4N7hZ6il+gfJxZg==,
+      }
+
   cluster-key-slot@1.1.2:
     resolution:
       {
@@ -5465,6 +5483,8 @@ snapshots:
 
   "@cfworker/json-schema@4.1.1": {}
 
+  "@cloudflare/workers-types@4.20250606.0": {}
+
   "@cspotcode/source-map-support@0.8.1":
     dependencies:
       "@jridgewell/trace-mapping": 0.3.9
@@ -6397,6 +6417,18 @@ snapshots:
       strip-ansi: 6.0.1
       wrap-ansi: 7.0.0
 
+  cloudflare@4.3.0(encoding@0.1.13):
+    dependencies:
+      "@types/node": 18.19.76
+      "@types/node-fetch": 2.6.12
+      abort-controller: 3.0.0
+      agentkeepalive: 4.6.0
+      form-data-encoder: 1.7.2
+      formdata-node: 4.4.1
+      node-fetch: 2.7.0(encoding@0.1.13)
+    transitivePeerDependencies:
+      - encoding
+
   cluster-key-slot@1.1.2: {}
 
   co@4.6.0: {}

mem0-ts/src/oss/package.json

@@ -21,6 +21,7 @@
     "@types/redis": "^4.0.10",
     "@types/sqlite3": "^3.1.11",
     "@types/uuid": "^9.0.8",
+    "cloudflare": "^4.2.0",
     "dotenv": "^16.4.4",
     "groq-sdk": "^0.3.0",
     "openai": "^4.28.0",
@@ -31,6 +32,7 @@
     "zod": "^3.22.4"
   },
   "devDependencies": {
+    "@cloudflare/workers-types": "^4.20250504.0",
     "@types/jest": "^29.5.12",
     "jest": "^29.7.0",
     "rimraf": "^5.0.5",

mem0-ts/src/oss/src/index.ts

@@ -22,4 +22,5 @@ export * from "./vector_stores/qdrant";
 export * from "./vector_stores/redis";
 export * from "./vector_stores/supabase";
 export * from "./vector_stores/langchain";
+export * from "./vector_stores/vectorize";
 export * from "./utils/factory";

mem0-ts/src/oss/src/types/index.ts

@@ -117,6 +117,7 @@ export const MemoryConfigSchema = z.object({
       modelProperties: z.record(z.string(), z.any()).optional(),
       apiKey: z.string().optional(),
       model: z.union([z.string(), z.any()]).optional(),
+      baseURL: z.string().optional(),
     }),
   }),
   vectorStore: z.object({
@@ -135,6 +136,7 @@ export const MemoryConfigSchema = z.object({
       apiKey: z.string().optional(),
       model: z.union([z.string(), z.any()]).optional(),
       modelProperties: z.record(z.string(), z.any()).optional(),
+      baseURL: z.string().optional(),
     }),
   }),
   historyDbPath: z.string().optional(),

mem0-ts/src/oss/src/utils/factory.ts

@@ -16,6 +16,7 @@ import { Embedder } from "../embeddings/base";
 import { LLM } from "../llms/base";
 import { VectorStore } from "../vector_stores/base";
 import { Qdrant } from "../vector_stores/qdrant";
+import { VectorizeDB } from "../vector_stores/vectorize";
 import { RedisDB } from "../vector_stores/redis";
 import { OllamaLLM } from "../llms/ollama";
 import { SupabaseDB } from "../vector_stores/supabase";
@@ -90,6 +91,8 @@ export class VectorStoreFactory {
         return new SupabaseDB(config as any);
       case "langchain":
         return new LangchainVectorStore(config as any);
+      case "vectorize":
+        return new VectorizeDB(config as any);
       default:
         throw new Error(`Unsupported vector store provider: ${provider}`);
     }

mem0-ts/src/oss/src/vector_stores/vectorize.ts

@@ -0,0 +1,436 @@
+import Cloudflare from "cloudflare";
+import type { Vectorize, VectorizeVector } from "@cloudflare/workers-types";
+import { VectorStore } from "./base";
+import { SearchFilters, VectorStoreConfig, VectorStoreResult } from "../types";
+
+interface VectorizeConfig extends VectorStoreConfig {
+  apiKey?: string;
+  indexName: string;
+  accountId: string;
+}
+
+interface CloudflareVector {
+  id: string;
+  values: number[];
+  metadata?: Record<string, any>;
+}
+
+export class VectorizeDB implements VectorStore {
+  private client: Cloudflare | null = null;
+  private dimensions: number;
+  private indexName: string;
+  private accountId: string;
+
+  constructor(config: VectorizeConfig) {
+    this.client = new Cloudflare({ apiToken: config.apiKey });
+    this.dimensions = config.dimension || 1536;
+    this.indexName = config.indexName;
+    this.accountId = config.accountId;
+    this.initialize().catch(console.error);
+  }
+
+  async insert(
+    vectors: number[][],
+    ids: string[],
+    payloads: Record<string, any>[],
+  ): Promise<void> {
+    try {
+      const vectorObjects: CloudflareVector[] = vectors.map(
+        (vector, index) => ({
+          id: ids[index],
+          values: vector,
+          metadata: payloads[index] || {},
+        }),
+      );
+
+      const ndjsonPayload = vectorObjects
+        .map((v) => JSON.stringify(v))
+        .join("\n");
+
+      const response = await fetch(
+        `https://api.cloudflare.com/client/v4/accounts/${this.accountId}/vectorize/v2/indexes/${this.indexName}/insert`,
+        {
+          method: "POST",
+          headers: {
+            "Content-Type": "application/x-ndjson",
+            Authorization: `Bearer ${this.client?.apiToken}`,
+          },
+          body: ndjsonPayload,
+        },
+      );
+
+      if (!response.ok) {
+        const errorText = await response.text();
+        throw new Error(
+          `Failed to insert vectors: ${response.status} ${errorText}`,
+        );
+      }
+    } catch (error) {
+      console.error("Error inserting vectors:", error);
+      throw new Error(
+        `Failed to insert vectors: ${error instanceof Error ? error.message : String(error)}`,
+      );
+    }
+  }
+
+  async search(
+    query: number[],
+    limit: number = 5,
+    filters?: SearchFilters,
+  ): Promise<VectorStoreResult[]> {
+    try {
+      const result = await this.client?.vectorize.indexes.query(
+        this.indexName,
+        {
+          account_id: this.accountId,
+          vector: query,
+          filter: filters,
+          returnMetadata: "all",
+          topK: limit,
+        },
+      );
+
+      return (
+        (result?.matches?.map((match) => ({
+          id: match.id,
+          payload: match.metadata,
+          score: match.score,
+        })) as VectorStoreResult[]) || []
+      ); // Return empty array if result or matches is null/undefined
+    } catch (error) {
+      console.error("Error searching vectors:", error);
+      throw new Error(
+        `Failed to search vectors: ${error instanceof Error ? error.message : String(error)}`,
+      );
+    }
+  }
+
+  async get(vectorId: string): Promise<VectorStoreResult | null> {
+    try {
+      const result = (await this.client?.vectorize.indexes.getByIds(
+        this.indexName,
+        {
+          account_id: this.accountId,
+          ids: [vectorId],
+        },
+      )) as any;
+
+      if (!result?.length) return null;
+
+      return {
+        id: vectorId,
+        payload: result[0].metadata,
+      };
+    } catch (error) {
+      console.error("Error getting vector:", error);
+      throw new Error(
+        `Failed to get vector: ${error instanceof Error ? error.message : String(error)}`,
+      );
+    }
+  }
+
+  async update(
+    vectorId: string,
+    vector: number[],
+    payload: Record<string, any>,
+  ): Promise<void> {
+    try {
+      const data: VectorizeVector = {
+        id: vectorId,
+        values: vector,
+        metadata: payload,
+      };
+
+      const response = await fetch(
+        `https://api.cloudflare.com/client/v4/accounts/${this.accountId}/vectorize/v2/indexes/${this.indexName}/upsert`,
+        {
+          method: "POST",
+          headers: {
+            "Content-Type": "application/x-ndjson",
+            Authorization: `Bearer ${this.client?.apiToken}`,
+          },
+          body: JSON.stringify(data) + "\n", // ndjson format
+        },
+      );
+
+      if (!response.ok) {
+        const errorText = await response.text();
+        throw new Error(
+          `Failed to update vector: ${response.status} ${errorText}`,
+        );
+      }
+    } catch (error) {
+      console.error("Error updating vector:", error);
+      throw new Error(
+        `Failed to update vector: ${error instanceof Error ? error.message : String(error)}`,
+      );
+    }
+  }
+
+  async delete(vectorId: string): Promise<void> {
+    try {
+      await this.client?.vectorize.indexes.deleteByIds(this.indexName, {
+        account_id: this.accountId,
+        ids: [vectorId],
+      });
+    } catch (error) {
+      console.error("Error deleting vector:", error);
+      throw new Error(
+        `Failed to delete vector: ${error instanceof Error ? error.message : String(error)}`,
+      );
+    }
+  }
+
+  async deleteCol(): Promise<void> {
+    try {
+      await this.client?.vectorize.indexes.delete(this.indexName, {
+        account_id: this.accountId,
+      });
+    } catch (error) {
+      console.error("Error deleting collection:", error);
+      throw new Error(
+        `Failed to delete collection: ${error instanceof Error ? error.message : String(error)}`,
+      );
+    }
+  }
+
+  async list(
+    filters?: SearchFilters,
+    limit: number = 20,
+  ): Promise<[VectorStoreResult[], number]> {
+    try {
+      const result = await this.client?.vectorize.indexes.query(
+        this.indexName,
+        {
+          account_id: this.accountId,
+          vector: Array(this.dimensions).fill(0), // Dummy vector for listing
+          filter: filters,
+          topK: limit,
+          returnMetadata: "all",
+        },
+      );
+
+      const matches =
+        (result?.matches?.map((match) => ({
+          id: match.id,
+          payload: match.metadata,
+          score: match.score,
+        })) as VectorStoreResult[]) || [];
+
+      return [matches, matches.length];
+    } catch (error) {
+      console.error("Error listing vectors:", error);
+      throw new Error(
+        `Failed to list vectors: ${error instanceof Error ? error.message : String(error)}`,
+      );
+    }
+  }
+
+  private generateUUID(): string {
+    return "xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx".replace(
+      /[xy]/g,
+      function (c) {
+        const r = (Math.random() * 16) | 0;
+        const v = c === "x" ? r : (r & 0x3) | 0x8;
+        return v.toString(16);
+      },
+    );
+  }
+
+  async getUserId(): Promise<string> {
+    try {
+      let found = false;
+      for await (const index of this.client!.vectorize.indexes.list({
+        account_id: this.accountId,
+      })) {
+        if (index.name === "memory_migrations") {
+          found = true;
+        }
+      }
+
+      if (!found) {
+        await this.client?.vectorize.indexes.create({
+          account_id: this.accountId,
+          name: "memory_migrations",
+          config: {
+            dimensions: 1,
+            metric: "cosine",
+          },
+        });
+      }
+
+      // Now try to get the userId
+      const result: any = await this.client?.vectorize.indexes.query(
+        "memory_migrations",
+        {
+          account_id: this.accountId,
+          vector: [0],
+          topK: 1,
+          returnMetadata: "all",
+        },
+      );
+      if (result.matches.length > 0) {
+        return result.matches[0].metadata.userId as string;
+      }
+
+      // Generate a random userId if none exists
+      const randomUserId =
+        Math.random().toString(36).substring(2, 15) +
+        Math.random().toString(36).substring(2, 15);
+      const data: VectorizeVector = {
+        id: this.generateUUID(),
+        values: [0],
+        metadata: { userId: randomUserId },
+      };
+
+      await fetch(
+        `https://api.cloudflare.com/client/v4/accounts/${this.accountId}/vectorize/v2/indexes/memory_migrations/upsert`,
+        {
+          method: "POST",
+          headers: {
+            "Content-Type": "application/x-ndjson",
+            Authorization: `Bearer ${this.client?.apiToken}`,
+          },
+          body: JSON.stringify(data) + "\n", // ndjson format
+        },
+      );
+      return randomUserId;
+    } catch (error) {
+      console.error("Error getting user ID:", error);
+      throw new Error(
+        `Failed to get user ID: ${error instanceof Error ? error.message : String(error)}`,
+      );
+    }
+  }
+
+  async setUserId(userId: string): Promise<void> {
+    try {
+      // Get existing point ID
+      const result: any = await this.client?.vectorize.indexes.query(
+        "memory_migrations",
+        {
+          account_id: this.accountId,
+          vector: [0],
+          topK: 1,
+          returnMetadata: "all",
+        },
+      );
+      const pointId =
+        result.matches.length > 0 ? result.matches[0].id : this.generateUUID();
+
+      const data: VectorizeVector = {
+        id: pointId,
+        values: [0],
+        metadata: { userId },
+      };
+      await fetch(
+        `https://api.cloudflare.com/client/v4/accounts/${this.accountId}/vectorize/v2/indexes/memory_migrations/upsert`,
+        {
+          method: "POST",
+          headers: {
+            "Content-Type": "application/x-ndjson",
+            Authorization: `Bearer ${this.client?.apiToken}`,
+          },
+          body: JSON.stringify(data) + "\n", // ndjson format
+        },
+      );
+    } catch (error) {
+      console.error("Error setting user ID:", error);
+      throw new Error(
+        `Failed to set user ID: ${error instanceof Error ? error.message : String(error)}`,
+      );
+    }
+  }
+
+  async initialize(): Promise<void> {
+    try {
+      // Check if the index already exists
+      let indexFound = false;
+      for await (const idx of this.client!.vectorize.indexes.list({
+        account_id: this.accountId,
+      })) {
+        if (idx.name === this.indexName) {
+          indexFound = true;
+          break;
+        }
+      }
+      // If the index doesn't exist, create it
+      if (!indexFound) {
+        try {
+          await this.client?.vectorize.indexes.create({
+            account_id: this.accountId,
+            name: this.indexName,
+            config: {
+              dimensions: this.dimensions,
+              metric: "cosine",
+            },
+          });
+
+          const properties = ["userId", "agentId", "runId"];
+
+          for (const propertyName of properties) {
+            await this.client?.vectorize.indexes.metadataIndex.create(
+              this.indexName,
+              {
+                account_id: this.accountId,
+                indexType: "string",
+                propertyName,
+              },
+            );
+          }
+        } catch (err: any) {
+          throw new Error(err);
+        }
+      }
+
+      // check for metadata index
+      const metadataIndexes =
+        await this.client?.vectorize.indexes.metadataIndex.list(
+          this.indexName,
+          {
+            account_id: this.accountId,
+          },
+        );
+      const existingMetadataIndexes = new Set<string>();
+      for (const metadataIndex of metadataIndexes?.metadataIndexes || []) {
+        existingMetadataIndexes.add(metadataIndex.propertyName!);
+      }
+      const properties = ["userId", "agentId", "runId"];
+      for (const propertyName of properties) {
+        if (!existingMetadataIndexes.has(propertyName)) {
+          await this.client?.vectorize.indexes.metadataIndex.create(
+            this.indexName,
+            {
+              account_id: this.accountId,
+              indexType: "string",
+              propertyName,
+            },
+          );
+        }
+      }
+      // Create memory_migrations collection if it doesn't exist
+      let found = false;
+      for await (const index of this.client!.vectorize.indexes.list({
+        account_id: this.accountId,
+      })) {
+        if (index.name === "memory_migrations") {
+          found = true;
+          break;
+        }
+      }
+
+      if (!found) {
+        await this.client?.vectorize.indexes.create({
+          account_id: this.accountId,
+          name: "memory_migrations",
+          config: {
+            dimensions: 1,
+            metric: "cosine",
+          },
+        });
+      }
+    } catch (err: any) {
+      throw new Error(err);
+    }
+  }
+}

mem0/client/main.py

@@ -472,6 +472,22 @@ class MemoryClient:
         capture_client_event("client.get_memory_export", self, {"keys": list(kwargs.keys()), "sync_type": "sync"})
         return response.json()
 
+    @api_error_handler
+    def get_summary(self, filters: Optional[Dict[str, Any]] = None) -> Dict[str, Any]:
+        """Get the summary of a memory export.
+
+        Args:
+            filters: Optional filters to apply to the summary request
+
+        Returns:
+            Dict containing the export status and summary data
+        """
+
+        response = self.client.post("/v1/summary/", json=self._prepare_params({"filters": filters}))
+        response.raise_for_status()
+        capture_client_event("client.get_summary", self, {"sync_type": "sync"})
+        return response.json()
+
     @api_error_handler
     def get_project(self, fields: Optional[List[str]] = None) -> Dict[str, Any]:
         """Get instructions or categories for the current project.
@@ -526,7 +542,13 @@ class MemoryClient:
         if not (self.org_id and self.project_id):
             raise ValueError("org_id and project_id must be set to update instructions or categories")
 
-        if custom_instructions is None and custom_categories is None and retrieval_criteria is None and enable_graph is None and version is None:
+        if (
+            custom_instructions is None
+            and custom_categories is None
+            and retrieval_criteria is None
+            and enable_graph is None
+            and version is None
+        ):
             raise ValueError(
                 "Currently we only support updating custom_instructions or custom_categories or retrieval_criteria, so you must provide at least one of them"
             )
@@ -675,9 +697,7 @@ class MemoryClient:
         capture_client_event("client.feedback", self, data, {"sync_type": "sync"})
         return response.json()
 
-    def _prepare_payload(
-        self, messages: List[Dict[str, str]], kwargs: Dict[str, Any]
-    ) -> Dict[str, Any]:
+    def _prepare_payload(self, messages: List[Dict[str, str]], kwargs: Dict[str, Any]) -> Dict[str, Any]:
         """Prepare the payload for API requests.
 
         Args:
@@ -795,7 +815,7 @@ class AsyncMemoryClient:
 
             return data.get("user_email")
 
-        except requests.HTTPStatusError as e:
+        except requests.exceptions.HTTPError as e:
             try:
                 error_data = e.response.json()
                 error_message = error_data.get("detail", str(e))
@@ -803,9 +823,7 @@ class AsyncMemoryClient:
                 error_message = str(e)
             raise ValueError(f"Error: {error_message}")
 
-    def _prepare_payload(
-        self, messages: List[Dict[str, str]], kwargs: Dict[str, Any]
-    ) -> Dict[str, Any]:
+    def _prepare_payload(self, messages: List[Dict[str, str]], kwargs: Dict[str, Any]) -> Dict[str, Any]:
         """Prepare the payload for API requests.
 
         Args:
@@ -1115,7 +1133,13 @@ class AsyncMemoryClient:
         if not (self.org_id and self.project_id):
             raise ValueError("org_id and project_id must be set to update instructions or categories")
 
-        if custom_instructions is None and custom_categories is None and retrieval_criteria is None and enable_graph is None and version is None:
+        if (
+            custom_instructions is None
+            and custom_categories is None
+            and retrieval_criteria is None
+            and enable_graph is None
+            and version is None
+        ):
             raise ValueError(
                 "Currently we only support updating custom_instructions or custom_categories or retrieval_criteria, so you must provide at least one of them"
             )

mem0/llms/sarvam.py

@@ -18,22 +18,15 @@ class SarvamLLM(LLMBase):
 
         if not self.api_key:
             raise ValueError(
-                "Sarvam API key is required. Set SARVAM_API_KEY environment variable "
-                "or provide api_key in config."
+                "Sarvam API key is required. Set SARVAM_API_KEY environment variable " "or provide api_key in config."
             )
 
         # Set base URL - use config value or environment or default
         self.base_url = (
-                getattr(self.config, 'sarvam_base_url', None) or
-                os.getenv("SARVAM_API_BASE") or
-                "https://api.sarvam.ai/v1"
+            getattr(self.config, "sarvam_base_url", None) or os.getenv("SARVAM_API_BASE") or "https://api.sarvam.ai/v1"
         )
 
-    def generate_response(
-            self,
-            messages: List[Dict[str, str]],
-            response_format=None
-    ) -> str:
+    def generate_response(self, messages: List[Dict[str, str]], response_format=None) -> str:
         """
         Generate a response based on the given messages using Sarvam-M.
 
@@ -47,10 +40,7 @@ class SarvamLLM(LLMBase):
         """
         url = f"{self.base_url}/chat/completions"
 
-        headers = {
-            "Authorization": f"Bearer {self.api_key}",
-            "Content-Type": "application/json"
-        }
+        headers = {"Authorization": f"Bearer {self.api_key}", "Content-Type": "application/json"}
 
         # Prepare the request payload
         params = {
@@ -74,10 +64,7 @@ class SarvamLLM(LLMBase):
             params["model"] = self.config.model.get("name", "sarvam-m")
 
             # Add Sarvam-specific parameters
-            sarvam_specific_params = [
-                'reasoning_effort', 'frequency_penalty', 'presence_penalty',
-                'seed', 'stop', 'n'
-            ]
+            sarvam_specific_params = ["reasoning_effort", "frequency_penalty", "presence_penalty", "seed", "stop", "n"]
 
             for param in sarvam_specific_params:
                 if param in self.config.model:
@@ -89,12 +76,12 @@ class SarvamLLM(LLMBase):
 
             result = response.json()
 
-            if 'choices' in result and len(result['choices']) > 0:
-                return result['choices'][0]['message']['content']
+            if "choices" in result and len(result["choices"]) > 0:
+                return result["choices"][0]["message"]["content"]
             else:
                 raise ValueError("No response choices found in Sarvam API response")
 
         except requests.exceptions.RequestException as e:
             raise RuntimeError(f"Sarvam API request failed: {e}")
         except KeyError as e:
-            raise ValueError(f"Unexpected response format from Sarvam API: {e}")
+            raise ValueError(f"Unexpected response format from Sarvam API: {e}")

mem0/memory/main.py

@@ -29,6 +29,7 @@ from mem0.memory.utils import (
     parse_messages,
     parse_vision_messages,
     remove_code_blocks,
+    process_telemetry_filters,
 )
 from mem0.utils.factory import EmbedderFactory, LlmFactory, VectorStoreFactory
 
@@ -45,13 +46,13 @@ def _build_filters_and_metadata(
     """
     Constructs metadata for storage and filters for querying based on session and actor identifiers.
 
-    This helper ties every memory/query to exactly one session id (`user_id`, `agent_id`, or `run_id`) and optionally narrows queries to a specific `actor_id`.  It returns two dicts:
-
+    This helper supports multiple session identifiers (`user_id`, `agent_id`, and/or `run_id`)
+    for flexible session scoping and optionally narrows queries to a specific `actor_id`. It returns two dicts:
 
     1. `base_metadata_template`: Used as a template for metadata when storing new memories.
-       It includes the primary session identifier(s) and any `input_metadata`.
-    2. `effective_query_filters`: Used for querying existing memories. It includes the
-       primary session identifier(s), any `input_filters`, and a resolved actor
+       It includes all provided session identifier(s) and any `input_metadata`.
+    2. `effective_query_filters`: Used for querying existing memories. It includes all
+       provided session identifier(s), any `input_filters`, and a resolved actor
        identifier for targeted filtering if specified by any actor-related inputs.
 
     Actor filtering precedence: explicit `actor_id` arg → `filters["actor_id"]`
@@ -59,11 +60,9 @@ def _build_filters_and_metadata(
     as the actor for storage is typically derived from message content at a later stage.
 
     Args:
-        user_id (Optional[str]): User identifier, primarily for Classic Mode session scoping.
-        agent_id (Optional[str]): Agent identifier, for Classic Mode session scoping or
-            as auxiliary information in Group Mode.
-        run_id (Optional[str]): Run identifier, for Classic Mode session scoping or
-            as auxiliary information in Group Mode.
+        user_id (Optional[str]): User identifier, for session scoping.
+        agent_id (Optional[str]): Agent identifier, for session scoping.
+        run_id (Optional[str]): Run identifier, for session scoping.
         actor_id (Optional[str]): Explicit actor identifier, used as a potential source for
             actor-specific filtering. See actor resolution precedence in the main description.
         input_metadata (Optional[Dict[str, Any]]): Base dictionary to be augmented with
@@ -74,28 +73,34 @@ def _build_filters_and_metadata(
     Returns:
         tuple[Dict[str, Any], Dict[str, Any]]: A tuple containing:
             - base_metadata_template (Dict[str, Any]): Metadata template for storing memories,
-              scoped to the determined session.
+              scoped to the provided session(s).
             - effective_query_filters (Dict[str, Any]): Filters for querying memories,
-              scoped to the determined session and potentially a resolved actor.
+              scoped to the provided session(s) and potentially a resolved actor.
     """
 
     base_metadata_template = deepcopy(input_metadata) if input_metadata else {}
     effective_query_filters = deepcopy(input_filters) if input_filters else {}
 
-    # ---------- resolve session id (mandatory) ----------
-    session_key, session_val = None, None
+    # ---------- add all provided session ids ----------
+    session_ids_provided = []
+
     if user_id:
-        session_key, session_val = "user_id", user_id
-    elif agent_id:
-        session_key, session_val = "agent_id", agent_id
-    elif run_id:
-        session_key, session_val = "run_id", run_id
+        base_metadata_template["user_id"] = user_id
+        effective_query_filters["user_id"] = user_id
+        session_ids_provided.append("user_id")
 
-    if session_key is None:
-        raise ValueError("One of 'user_id', 'agent_id', or 'run_id' must be provided.")
+    if agent_id:
+        base_metadata_template["agent_id"] = agent_id
+        effective_query_filters["agent_id"] = agent_id
+        session_ids_provided.append("agent_id")
 
-    base_metadata_template[session_key] = session_val
-    effective_query_filters[session_key] = session_val
+    if run_id:
+        base_metadata_template["run_id"] = run_id
+        effective_query_filters["run_id"] = run_id
+        session_ids_provided.append("run_id")
+
+    if not session_ids_provided:
+        raise ValueError("At least one of 'user_id', 'agent_id', or 'run_id' must be provided.")
 
     # ---------- optional actor filter ----------
     resolved_actor_id = actor_id or effective_query_filters.get("actor_id")
@@ -433,10 +438,11 @@ class Memory(MemoryBase):
         except Exception as e:
             logging.error(f"Error iterating new_memories_with_actions: {e}")
 
+        keys, encoded_ids = process_telemetry_filters(filters)
         capture_event(
             "mem0.add",
             self,
-            {"version": self.api_version, "keys": list(filters.keys()), "sync_type": "sync"},
+            {"version": self.api_version, "keys": keys, "encoded_ids": encoded_ids, "sync_type": "sync"},
         )
         return returned_memories
 
@@ -529,8 +535,9 @@ class Memory(MemoryBase):
         if not any(key in effective_filters for key in ("user_id", "agent_id", "run_id")):
             raise ValueError("At least one of 'user_id', 'agent_id', or 'run_id' must be specified.")
 
+        keys, encoded_ids = process_telemetry_filters(effective_filters)
         capture_event(
-            "mem0.get_all", self, {"limit": limit, "keys": list(effective_filters.keys()), "sync_type": "sync"}
+            "mem0.get_all", self, {"limit": limit, "keys": keys, "encoded_ids": encoded_ids, "sync_type": "sync"}
         )
 
         with concurrent.futures.ThreadPoolExecutor() as executor:
@@ -564,7 +571,9 @@ class Memory(MemoryBase):
     def _get_all_from_vector_store(self, filters, limit):
         memories_result = self.vector_store.list(filters=filters, limit=limit)
         actual_memories = (
-            memories_result[0] if isinstance(memories_result, tuple) and len(memories_result) > 0 else memories_result
+            memories_result[0]
+            if isinstance(memories_result, (tuple, list)) and len(memories_result) > 0
+            else memories_result
         )
 
         promoted_payload_keys = [
@@ -607,6 +616,7 @@ class Memory(MemoryBase):
         run_id: Optional[str] = None,
         limit: int = 100,
         filters: Optional[Dict[str, Any]] = None,
+        threshold: Optional[float] = None,
     ):
         """
         Searches for memories based on a query
@@ -617,6 +627,7 @@ class Memory(MemoryBase):
             run_id (str, optional): ID of the run to search for. Defaults to None.
             limit (int, optional): Limit the number of results. Defaults to 100.
             filters (dict, optional): Filters to apply to the search. Defaults to None..
+            threshold (float, optional): Minimum score for a memory to be included in the results. Defaults to None.
 
         Returns:
             dict: A dictionary containing the search results, typically under a "results" key,
@@ -630,14 +641,22 @@ class Memory(MemoryBase):
         if not any(key in effective_filters for key in ("user_id", "agent_id", "run_id")):
             raise ValueError("At least one of 'user_id', 'agent_id', or 'run_id' must be specified.")
 
+        keys, encoded_ids = process_telemetry_filters(effective_filters)
         capture_event(
             "mem0.search",
             self,
-            {"limit": limit, "version": self.api_version, "keys": list(effective_filters.keys()), "sync_type": "sync"},
+            {
+                "limit": limit,
+                "version": self.api_version,
+                "keys": keys,
+                "encoded_ids": encoded_ids,
+                "sync_type": "sync",
+                "threshold": threshold,
+            },
         )
 
         with concurrent.futures.ThreadPoolExecutor() as executor:
-            future_memories = executor.submit(self._search_vector_store, query, effective_filters, limit)
+            future_memories = executor.submit(self._search_vector_store, query, effective_filters, limit, threshold)
             future_graph_entities = (
                 executor.submit(self.graph.search, query, effective_filters, limit) if self.enable_graph else None
             )
@@ -664,7 +683,7 @@ class Memory(MemoryBase):
         else:
             return {"results": original_memories}
 
-    def _search_vector_store(self, query, filters, limit):
+    def _search_vector_store(self, query, filters, limit, threshold: Optional[float] = None):
         embeddings = self.embedding_model.embed(query, "search")
         memories = self.vector_store.search(query=query, vectors=embeddings, limit=limit, filters=filters)
 
@@ -697,7 +716,8 @@ class Memory(MemoryBase):
             if additional_metadata:
                 memory_item_dict["metadata"] = additional_metadata
 
-            original_memories.append(memory_item_dict)
+            if threshold is None or mem.score >= threshold:
+                original_memories.append(memory_item_dict)
 
         return original_memories
 
@@ -752,7 +772,8 @@ class Memory(MemoryBase):
                 "At least one filter is required to delete all memories. If you want to delete all memories, use the `reset()` method."
             )
 
-        capture_event("mem0.delete_all", self, {"keys": list(filters.keys()), "sync_type": "sync"})
+        keys, encoded_ids = process_telemetry_filters(filters)
+        capture_event("mem0.delete_all", self, {"keys": keys, "encoded_ids": encoded_ids, "sync_type": "sync"})
         memories = self.vector_store.list(filters=filters)[0]
         for memory in memories:
             self._delete_memory(memory.id)
@@ -1086,7 +1107,7 @@ class AsyncMemory(MemoryBase):
         self,
         messages: list,
         metadata: dict,
-        filters: dict,
+        effective_filters: dict,
         infer: bool,
     ):
         if not infer:
@@ -1160,7 +1181,7 @@ class AsyncMemory(MemoryBase):
                 query=new_mem_content,
                 vectors=embeddings,
                 limit=5,
-                filters=filters,  # 'filters' is query_filters_for_inference
+                filters=effective_filters,  # 'filters' is query_filters_for_inference
             )
             return [{"id": mem.id, "text": mem.payload["data"]} for mem in existing_mems]
 
@@ -1189,7 +1210,6 @@ class AsyncMemory(MemoryBase):
                 response_format={"type": "json_object"},
             )
         except Exception as e:
-
             response = ""
             logging.error(f"Error in new memory actions response: {e}")
             response = ""
@@ -1197,7 +1217,6 @@ class AsyncMemory(MemoryBase):
             response = remove_code_blocks(response)
             new_memories_with_actions = json.loads(response)
         except Exception as e:
-
             new_memories_with_actions = {}
 
         if not new_memories_with_actions:
@@ -1207,7 +1226,6 @@ class AsyncMemory(MemoryBase):
             logging.error(f"Invalid JSON response: {e}")
             new_memories_with_actions = {}
 
-
         returned_memories = []
         try:
             memory_tasks = []
@@ -1267,8 +1285,11 @@ class AsyncMemory(MemoryBase):
         except Exception as e:
             logging.error(f"Error in memory processing loop (async): {e}")
 
+        keys, encoded_ids = process_telemetry_filters(effective_filters)
         capture_event(
-            "mem0.add", self, {"version": self.api_version, "keys": list(filters.keys()), "sync_type": "async"}
+            "mem0.add",
+            self,
+            {"version": self.api_version, "keys": keys, "encoded_ids": encoded_ids, "sync_type": "async"},
         )
         return returned_memories
 
@@ -1364,8 +1385,9 @@ class AsyncMemory(MemoryBase):
                 "at least one of 'user_id', 'agent_id', or 'run_id' must be specified for get_all."
             )
 
+        keys, encoded_ids = process_telemetry_filters(effective_filters)
         capture_event(
-            "mem0.get_all", self, {"limit": limit, "keys": list(effective_filters.keys()), "sync_type": "async"}
+            "mem0.get_all", self, {"limit": limit, "keys": keys, "encoded_ids": encoded_ids, "sync_type": "async"}
         )
 
         with concurrent.futures.ThreadPoolExecutor() as executor:
@@ -1442,6 +1464,7 @@ class AsyncMemory(MemoryBase):
         run_id: Optional[str] = None,
         limit: int = 100,
         filters: Optional[Dict[str, Any]] = None,
+        threshold: Optional[float] = None,
     ):
         """
         Searches for memories based on a query
@@ -1451,7 +1474,8 @@ class AsyncMemory(MemoryBase):
             agent_id (str, optional): ID of the agent to search for. Defaults to None.
             run_id (str, optional): ID of the run to search for. Defaults to None.
             limit (int, optional): Limit the number of results. Defaults to 100.
-            filters (dict, optional): Filters to apply to the search. Defaults to None..
+            filters (dict, optional): Filters to apply to the search. Defaults to None.
+            threshold (float, optional): Minimum score for a memory to be included in the results. Defaults to None.
 
         Returns:
             dict: A dictionary containing the search results, typically under a "results" key,
@@ -1466,13 +1490,21 @@ class AsyncMemory(MemoryBase):
         if not any(key in effective_filters for key in ("user_id", "agent_id", "run_id")):
             raise ValueError("at least one of 'user_id', 'agent_id', or 'run_id' must be specified ")
 
+        keys, encoded_ids = process_telemetry_filters(effective_filters)
         capture_event(
             "mem0.search",
             self,
-            {"limit": limit, "version": self.api_version, "keys": list(effective_filters.keys()), "sync_type": "async"},
+            {
+                "limit": limit,
+                "version": self.api_version,
+                "keys": keys,
+                "encoded_ids": encoded_ids,
+                "sync_type": "async",
+                "threshold": threshold,
+            },
         )
 
-        vector_store_task = asyncio.create_task(self._search_vector_store(query, effective_filters, limit))
+        vector_store_task = asyncio.create_task(self._search_vector_store(query, effective_filters, limit, threshold))
 
         graph_task = None
         if self.enable_graph:
@@ -1502,7 +1534,7 @@ class AsyncMemory(MemoryBase):
         else:
             return {"results": original_memories}
 
-    async def _search_vector_store(self, query, filters, limit):
+    async def _search_vector_store(self, query, filters, limit, threshold: Optional[float] = None):
         embeddings = await asyncio.to_thread(self.embedding_model.embed, query, "search")
         memories = await asyncio.to_thread(
             self.vector_store.search, query=query, vectors=embeddings, limit=limit, filters=filters
@@ -1537,7 +1569,8 @@ class AsyncMemory(MemoryBase):
             if additional_metadata:
                 memory_item_dict["metadata"] = additional_metadata
 
-            original_memories.append(memory_item_dict)
+            if threshold is None or mem.score >= threshold:
+                original_memories.append(memory_item_dict)
 
         return original_memories
 
@@ -1593,7 +1626,8 @@ class AsyncMemory(MemoryBase):
                 "At least one filter is required to delete all memories. If you want to delete all memories, use the `reset()` method."
             )
 
-        capture_event("mem0.delete_all", self, {"keys": list(filters.keys()), "sync_type": "async"})
+        keys, encoded_ids = process_telemetry_filters(filters)
+        capture_event("mem0.delete_all", self, {"keys": keys, "encoded_ids": encoded_ids, "sync_type": "async"})
         memories = await asyncio.to_thread(self.vector_store.list, filters=filters)
 
         delete_tasks = []

mem0/memory/storage.py

@@ -21,59 +21,107 @@ class SQLiteManager:
         rename it, create the new schema, copy the intersecting data, then
         drop the old table.
         """
-        with self._lock, self.connection:
-            cur = self.connection.cursor()
-            cur.execute("SELECT name FROM sqlite_master WHERE type='table' AND name='history'")
-            if cur.fetchone() is None:
-                return  # nothing to migrate
+        with self._lock:
+            try:
+                # Start a transaction
+                self.connection.execute("BEGIN")
+                cur = self.connection.cursor()
 
-            cur.execute("PRAGMA table_info(history)")
-            old_cols = {row[1] for row in cur.fetchall()}
+                cur.execute("SELECT name FROM sqlite_master WHERE type='table' AND name='history'")
+                if cur.fetchone() is None:
+                    self.connection.execute("COMMIT")
+                    return  # nothing to migrate
 
-            expected_cols = {
-                "id",
-                "memory_id",
-                "old_memory",
-                "new_memory",
-                "event",
-                "created_at",
-                "updated_at",
-                "is_deleted",
-                "actor_id",
-                "role",
-            }
+                cur.execute("PRAGMA table_info(history)")
+                old_cols = {row[1] for row in cur.fetchall()}
 
-            if old_cols == expected_cols:
-                return
+                expected_cols = {
+                    "id",
+                    "memory_id",
+                    "old_memory",
+                    "new_memory",
+                    "event",
+                    "created_at",
+                    "updated_at",
+                    "is_deleted",
+                    "actor_id",
+                    "role",
+                }
 
-            logger.info("Migrating history table to new schema (no convo columns).")
-            cur.execute("ALTER TABLE history RENAME TO history_old")
+                if old_cols == expected_cols:
+                    self.connection.execute("COMMIT")
+                    return
 
-            self._create_history_table()
+                logger.info("Migrating history table to new schema (no convo columns).")
 
-            intersecting = list(expected_cols & old_cols)
-            cols_csv = ", ".join(intersecting)
-            cur.execute(f"INSERT INTO history ({cols_csv}) SELECT {cols_csv} FROM history_old")
-            cur.execute("DROP TABLE history_old")
+                # Clean up any existing history_old table from previous failed migration
+                cur.execute("DROP TABLE IF EXISTS history_old")
+
+                # Rename the current history table
+                cur.execute("ALTER TABLE history RENAME TO history_old")
+
+                # Create the new history table with updated schema
+                cur.execute(
+                    """
+                    CREATE TABLE history (
+                        id           TEXT PRIMARY KEY,
+                        memory_id    TEXT,
+                        old_memory   TEXT,
+                        new_memory   TEXT,
+                        event        TEXT,
+                        created_at   DATETIME,
+                        updated_at   DATETIME,
+                        is_deleted   INTEGER,
+                        actor_id     TEXT,
+                        role         TEXT
+                    )
+                """
+                )
+
+                # Copy data from old table to new table
+                intersecting = list(expected_cols & old_cols)
+                if intersecting:
+                    cols_csv = ", ".join(intersecting)
+                    cur.execute(f"INSERT INTO history ({cols_csv}) SELECT {cols_csv} FROM history_old")
+
+                # Drop the old table
+                cur.execute("DROP TABLE history_old")
+
+                # Commit the transaction
+                self.connection.execute("COMMIT")
+                logger.info("History table migration completed successfully.")
+
+            except Exception as e:
+                # Rollback the transaction on any error
+                self.connection.execute("ROLLBACK")
+                logger.error(f"History table migration failed: {e}")
+                raise
 
     def _create_history_table(self) -> None:
-        with self._lock, self.connection:
-            self.connection.execute(
+        with self._lock:
+            try:
+                self.connection.execute("BEGIN")
+                self.connection.execute(
+                    """
+                    CREATE TABLE IF NOT EXISTS history (
+                        id           TEXT PRIMARY KEY,
+                        memory_id    TEXT,
+                        old_memory   TEXT,
+                        new_memory   TEXT,
+                        event        TEXT,
+                        created_at   DATETIME,
+                        updated_at   DATETIME,
+                        is_deleted   INTEGER,
+                        actor_id     TEXT,
+                        role         TEXT
+                    )
                 """
-                CREATE TABLE IF NOT EXISTS history (
-                    id           TEXT PRIMARY KEY,
-                    memory_id    TEXT,
-                    old_memory   TEXT,
-                    new_memory   TEXT,
-                    event        TEXT,
-                    created_at   DATETIME,
-                    updated_at   DATETIME,
-                    is_deleted   INTEGER,
-                    actor_id     TEXT,
-                    role         TEXT
                 )
-            """
-            )
+                self.connection.execute("COMMIT")
+            except Exception as e:
+                self.connection.execute("ROLLBACK")
+                logger.error(f"Failed to create history table: {e}")
+                raise
 
     def add_history(
         self,
@@ -88,28 +136,35 @@ class SQLiteManager:
         actor_id: Optional[str] = None,
         role: Optional[str] = None,
     ) -> None:
-        with self._lock, self.connection:
-            self.connection.execute(
-                """
-                INSERT INTO history (
-                    id, memory_id, old_memory, new_memory, event,
-                    created_at, updated_at, is_deleted, actor_id, role
+        with self._lock:
+            try:
+                self.connection.execute("BEGIN")
+                self.connection.execute(
+                    """
+                    INSERT INTO history (
+                        id, memory_id, old_memory, new_memory, event,
+                        created_at, updated_at, is_deleted, actor_id, role
+                    )
+                    VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
+                """,
+                    (
+                        str(uuid.uuid4()),
+                        memory_id,
+                        old_memory,
+                        new_memory,
+                        event,
+                        created_at,
+                        updated_at,
+                        is_deleted,
+                        actor_id,
+                        role,
+                    ),
                 )
-                VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
-            """,
-                (
-                    str(uuid.uuid4()),
-                    memory_id,
-                    old_memory,
-                    new_memory,
-                    event,
-                    created_at,
-                    updated_at,
-                    is_deleted,
-                    actor_id,
-                    role,
-                ),
-            )
+                self.connection.execute("COMMIT")
+            except Exception as e:
+                self.connection.execute("ROLLBACK")
+                logger.error(f"Failed to add history record: {e}")
+                raise
 
     def get_history(self, memory_id: str) -> List[Dict[str, Any]]:
         with self._lock:
@@ -143,9 +198,16 @@ class SQLiteManager:
 
     def reset(self) -> None:
         """Drop and recreate the history table."""
-        with self._lock, self.connection:
-            self.connection.execute("DROP TABLE IF EXISTS history")
-        self._create_history_table()
+        with self._lock:
+            try:
+                self.connection.execute("BEGIN")
+                self.connection.execute("DROP TABLE IF EXISTS history")
+                self.connection.execute("COMMIT")
+                self._create_history_table()
+            except Exception as e:
+                self.connection.execute("ROLLBACK")
+                logger.error(f"Failed to reset history table: {e}")
+                raise
 
     def close(self) -> None:
         if self.connection:

mem0/memory/utils.py

@@ -1,4 +1,5 @@
 import re
+import hashlib
 
 from mem0.configs.prompts import FACT_RETRIEVAL_PROMPT
 
@@ -98,3 +99,21 @@ def parse_vision_messages(messages, llm=None, vision_details="auto"):
             returned_messages.append(msg)
 
     return returned_messages
+
+
+def process_telemetry_filters(filters):
+    """
+    Process the telemetry filters
+    """
+    if filters is None:
+        return {}
+
+    encoded_ids = {}
+    if "user_id" in filters:
+        encoded_ids["user_id"] = hashlib.md5(filters["user_id"].encode()).hexdigest()
+    if "agent_id" in filters:
+        encoded_ids["agent_id"] = hashlib.md5(filters["agent_id"].encode()).hexdigest()
+    if "run_id" in filters:
+        encoded_ids["run_id"] = hashlib.md5(filters["run_id"].encode()).hexdigest()
+
+    return list(filters.keys()), encoded_ids

openmemory/README.md

@@ -37,6 +37,45 @@ curl -sL https://raw.githubusercontent.com/mem0ai/mem0/main/openmemory/run.sh |
 
 ## 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 
+```
+- #### 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
@@ -47,6 +86,17 @@ 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
+```
+
+
 ## Project Structure
 
 - `api/` - Backend APIs + MCP server

openmemory/api/.env.example

@@ -1 +1,2 @@
-OPENAI_API_KEY=sk-xxx
+OPENAI_API_KEY=sk-xxx
+USER=user

openmemory/api/alembic/versions/afd00efbd06b_add_unique_user_id_constraints.py

@@ -0,0 +1,36 @@
+"""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
+import sqlalchemy as sa
+
+
+# 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 ###

openmemory/api/app/models.py

@@ -1,6 +1,7 @@
 import enum
 import uuid
 import datetime
+import sqlalchemy as sa
 from sqlalchemy import (
     Column, String, Boolean, ForeignKey, Enum, Table,
     DateTime, JSON, Integer, UUID, Index, event
@@ -43,7 +44,7 @@ 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, unique=True, 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)
@@ -55,6 +56,10 @@ class App(Base):
     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"

openmemory/api/app/routers/memories.py

@@ -212,7 +212,8 @@ async def create_memory(
     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).first()
+    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)

openmemory/api/app/utils/categorization.py

@@ -1,15 +1,13 @@
-import json
 import logging
-
-from openai import OpenAI
 from typing import List
+
 from dotenv import load_dotenv
+from openai import OpenAI
 from pydantic import BaseModel
 from tenacity import retry, stop_after_attempt, wait_exponential
 from app.utils.prompts import MEMORY_CATEGORIZATION_PROMPT
 
 load_dotenv()
-
 openai_client = OpenAI()
 
 
@@ -19,19 +17,28 @@ class MemoryCategories(BaseModel):
 
 @retry(stop=stop_after_attempt(3), wait=wait_exponential(multiplier=1, min=4, max=15))
 def get_categories_for_memory(memory: str) -> List[str]:
-    """Get categories for a memory."""
     try:
-        response = openai_client.responses.parse(
+        messages = [
+            {"role": "system", "content": MEMORY_CATEGORIZATION_PROMPT},
+            {"role": "user", "content": memory}
+        ]
+
+        # Let OpenAI handle the pydantic parsing directly
+        completion = openai_client.chat.completions.with_response_format(
+            response_format=MemoryCategories
+        ).create(
             model="gpt-4o-mini",
-            instructions=MEMORY_CATEGORIZATION_PROMPT,
-            input=memory,
-            temperature=0,
-            text_format=MemoryCategories,
+            messages=messages,
+            temperature=0
         )
-        response_json =json.loads(response.output[0].content[0].text)
-        categories = response_json['categories']
-        categories = [cat.strip().lower() for cat in categories]
-        # TODO: Validate categories later may be
-        return categories
+
+        parsed: MemoryCategories = completion.choices[0].message.parsed
+        return [cat.strip().lower() for cat in parsed.categories]
+
     except Exception as e:
-        raise 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

openmemory/ui/store/profileSlice.ts

@@ -10,7 +10,7 @@ interface ProfileState {
 }
 
 const initialState: ProfileState = {
-  userId: process.env.NEXT_PUBLIC_USER_ID || 'deshraj',
+  userId: process.env.NEXT_PUBLIC_USER_ID || 'user',
   totalMemories: 0,
   totalApps: 0,
   status: 'idle',
@@ -36,7 +36,7 @@ const profileSlice = createSlice({
     resetProfileState: (state) => {
       state.status = 'idle';
       state.error = null;
-      state.userId = process.env.NEXT_PUBLIC_USER_ID || 'deshraj';
+      state.userId = process.env.NEXT_PUBLIC_USER_ID || 'user';
     },
     setTotalMemories: (state, action: PayloadAction<number>) => {
       state.totalMemories = action.payload;

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "mem0ai"
-version = "0.1.103"
+version = "0.1.107rc2"
 description = "Long-term memory for AI Agents"
 authors = [
     { name = "Mem0", email = "founders@mem0.ai" }