Memento icon

Memento

Provides a local, offline memory server for AI agents, leveraging SQLite with advanced search capabilities.

About

Memento is a robust, fully-offline MCP (Memory & Context Protocol) memory server designed to enhance the capabilities of AI agents. It utilizes SQLite for persistence, FTS5 for fast keyword searches, and `sqlite-vec` with an integrated `bge-m3` embedding model for powerful semantic vector search. This combination enables the creation of a structured knowledge graph of entities, observations, and relations, ensuring that AI models can maintain persistent, context-rich memories for improved performance and consistency in their interactions.

Key Features

  • Offline `bge-m3` embedding model via @xenova/transformers
  • Easy integration with Claude Desktop via MCP
  • 0 GitHub stars
  • Fast keyword search via FTS5
  • Semantic vector search using `sqlite-vec` (1024d)
  • Structured graph of entities, observations, and relations

Use Cases

  • Integrating custom memory backends with MCP-compatible AI interfaces
  • Enhancing LLM context and memory management
  • Building persistent knowledge bases for AI assistants