MCP server for long term agent memory with Mem0. Also useful as a template to get you started building your own MCP server with Python!
Overview
What is MCP-Mem0?
MCP-Mem0 is a template implementation of the Model Context Protocol (MCP) server integrated with Mem0, designed to provide AI agents with persistent memory capabilities.
How to use MCP-Mem0?
To use MCP-Mem0, clone the repository, install the necessary dependencies, configure your environment variables, and run the server using either uv or Docker.
Key features of MCP-Mem0?
save_memory: Store information in long-term memory with semantic indexing.get_all_memories: Retrieve all stored memories for comprehensive context.search_memories: Find relevant memories using semantic search.
Use cases of MCP-Mem0?
- Enabling AI agents to remember user interactions over time.
- Assisting in complex decision-making by recalling past experiences.
- Providing context-aware responses in conversational AI applications.
FAQ from MCP-Mem0?
- Can MCP-Mem0 be used with any AI model?
Yes! MCP-Mem0 can integrate with various LLM providers like OpenAI, OpenRouter, or Ollama.
- Is MCP-Mem0 free to use?
Yes! MCP-Mem0 is open-source and free to use under the MIT license.
- What are the prerequisites for running MCP-Mem0?
You need Python 3.12+, a PostgreSQL database, and API keys for your chosen LLM provider.