mcp-memory
The MCP Memory Server is designed to enhance AI assistants with long-term memory features, leveraging PostgreSQL's capabilities for efficient memory retrieval. It incorporates automatic embeddings, semantic search, and provides a RESTful API, integrating seamlessly with MCP protocols for ease of use.
What is the purpose of the MCP Memory Server?
The MCP Memory Server provides long-term memory capabilities for AI assistants, enabling them to store and retrieve memories efficiently using vector similarity search.
What database technology does the MCP Memory Server use?
The server uses PostgreSQL with the pgvector extension for efficient vector similarity search.
How does the server generate embeddings for memory content?
The server uses BERT to automatically generate embeddings for memory content, facilitating semantic search capabilities.
Can the server handle different types of memories?
Yes, the server supports various types of memories, including learnings and experiences, and allows for tag-based retrieval.
Does the server provide real-time updates?
Yes, the server supports Server-Sent Events (SSE) for real-time updates on memory operations.