Mem0

​

Overview

Mem0MemoryService provides long-term memory capabilities for conversational agents by integrating with Mem0’s API. It automatically stores conversation history and retrieves relevant past context based on the current conversation, enhancing LLM responses with persistent memory across sessions.

​

Installation

To use the Mem0 memory service, install the required dependencies:

pip install "pipecat-ai[mem0]"

You’ll also need to set up your Mem0 API key as an environment variable: MEM0_API_KEY.

​

Mem0MemoryService

​

Constructor Parameters

​

Input Parameters

The params object accepts the following configuration settings:

​

Input Frames

The service processes the following input frames:

​

Output Frames

The service may produce the following output frames:

​

Memory Operations

The service performs two main operations automatically:

​

Message Storage

All conversation messages are stored in Mem0 for future reference. The service:

• Captures full message history from context frames
• Associates messages with the specified user/agent/run IDs
• Stores metadata to enable efficient retrieval

​

Memory Retrieval

When a new user message is detected, the service:

1. Uses the message as a search query
2. Retrieves relevant past memories from Mem0
3. Formats memories with the configured system prompt
4. Adds the formatted memories to the conversation context
5. Passes the enhanced context downstream in the pipeline

​

Pipeline Positioning

The memory service should be positioned after the user context aggregator but before the LLM service:

context_aggregator.user() → memory_service → llm

This ensures that:

1. The user’s latest message is included in the context
2. The memory service can enhance the context before the LLM processes it
3. The LLM receives the enhanced context with relevant memories

​

Usage Examples

​

Basic Integration

from pipecat.services.mem0 import Mem0MemoryService
from pipecat.pipeline.pipeline import Pipeline

# Create the memory service
memory = Mem0MemoryService(
    api_key=os.getenv("MEM0_API_KEY"),
    user_id="user123",  # Unique user identifier
)

# Position the memory service between context aggregator and LLM
pipeline = Pipeline([
    transport.input(),
    context_aggregator.user(),
    memory,           # <-- Memory service enhances context here
    llm,
    tts,
    transport.output(),
    context_aggregator.assistant()
])

​

Frame Flow

​

Error Handling

The service includes basic error handling to ensure conversation flow continues even when memory operations fail:

• Exceptions during memory storage and retrieval are caught and logged
• If an error occurs during frame processing, an ErrorFrame is emitted with error details
• The original frame is still passed downstream to prevent the pipeline from stalling
• Connection and authentication errors from the Mem0 API will be logged but won’t interrupt the conversation