mcp-memory
If you are the rightful owner of mcp-memory and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
The MCP Memory Server provides long-term memory capabilities for AI assistants using mem0 principles, leveraging PostgreSQL with pgvector for efficient vector similarity search.
The MCP Memory Server is designed to enhance AI assistants with long-term memory capabilities by implementing mem0 principles. It utilizes PostgreSQL with the pgvector extension to perform efficient vector similarity searches. The server supports various types of memories, such as learnings and experiences, and offers features like automatic embedding generation using BERT, semantic search, and tag-based memory retrieval. It also provides a RESTful API for memory operations and supports real-time updates through Server-Sent Events (SSE). The server is compatible with the Cursor MCP protocol, allowing seamless integration with other MCP tools.
Features
- PostgreSQL with pgvector for vector similarity search
- Automatic embedding generation using BERT
- RESTful API for memory operations
- Semantic search capabilities
- Support for different types of memories (learnings, experiences, etc.)
