MCP Documentation
GitMem MCP (Manhattan) – Persistent AI memory that reduces token costs by 37%
GitMem MCP (Manhattan)
Overview
AI-powered persistent memory for Claude, Cursor, Copilot, Windsurf, and other AI agents.
What is GitMem MCP?
GitMem MCP is a Model Context Protocol server that gives AI coding agents persistent, semantic memory across conversations. Instead of re-explaining your codebase, preferences, and project context every session, GitMem remembers it — cutting token usage by up to 37%.
It works with any MCP-compatible client: Claude Desktop, Cursor IDE, GitHub Copilot, Windsurf, Cline, and more.
How We Reduce Tokens by 37%
Stores project context once and retrieves only what's relevant, eliminating redundant context in every prompt.
Detects duplicate information across sessions and merges it, preventing the same facts from consuming tokens repeatedly.
Uses vector similarity to inject only the most relevant memories, keeping prompt size minimal and focused.
Key Capabilities
Store and retrieve information across conversations and sessions.
Find relevant memories using natural language queries.
Get comprehensive answers from memory context directly.
Separate memory spaces for different projects or use cases.
Track memory usage, queries, and performance metrics.
Easily export and import your memory data.