lfrmonteiro99/memento-mcp

What it does

Memento MCP is a Model Context Protocol server that provides persistent memory capabilities for AI coding agents. It captures and stores important information including facts, design decisions, code patterns, and architecture notes in a local SQLite database. The tool supports optional cloud embeddings for enhanced retrieval, helping AI agents maintain continuity and context across multiple sessions without repeatedly processing the same information.

How to set up

As an MCP server, installation involves: 1) Clone or download the repository from GitHub, 2) Install required dependencies, 3) Configure the MCP server connection in your AI tool's settings, 4) Optionally set up cloud embeddings if desired for enhanced search capabilities. Detailed setup instructions are available in the repository documentation.

Key features

• Local-first SQLite storage for persistent memory without external dependencies
• Capture and organize facts, decisions, patterns, and architecture notes
• Optional cloud embeddings for semantic search and retrieval
• Reduces redundant context across AI agent sessions
• Compatible with multiple platforms via MCP protocol
• Cross-platform support for Windows, macOS, and Linux