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.
MCP Memory Server
This project provides long-term memory capabilities for AI assistants using PostgreSQL with pgvector for vector similarity search, incorporating features like automatic embedding generation using BERT and a RESTful API for memory operations. It supports various types of memories, semantic search capabilities, tag-based memory retrieval, and more. The server offers real-time updates via Server-Sent Events, supports confidence scoring, and is compatible with Cursor MCP protocol.