postg-mem

postg-mem

3.6

PostgMem is a .NET-based MCP server that provides vector memory storage using PostgreSQL and pgvector for AI applications.

PostgMem is a service designed to facilitate AI agents in storing, retrieving, and searching through memories using vector embeddings. It utilizes PostgreSQL with the pgvector extension to enable efficient similarity search capabilities. The service is built on .NET 9.0 and integrates the Model Context Protocol (MCP) to streamline its use with AI agents. PostgMem allows for the storage of structured memories, retrieval by ID, semantic search through vector similarity, and filtering of search results using tags. It is particularly useful for applications requiring advanced memory management and retrieval functionalities.

Features

  • Store structured memories with vector embeddings
  • Retrieve memories by ID
  • Semantic search through memories using vector similarity
  • Filter search results using tags
  • MCP integration for easy use with AI agents