repomemory

What it is

An MCP server over a .context/ directory in your repository. That directory holds facts, decisions, regressions, preferences, session summaries and monthly changelog syncs; the server lets an MCP client search it and orient itself in it without you pasting anything.

What you get

• The context library searched, so an agent looks something up instead of rediscovering it
• Automatic orientation at the start of a session, from the index that loads every time
• Facts about architecture, database and deployment kept in files rather than in a chat
• Decisions recorded with their reasoning, so a settled argument is not reopened
• Regressions recorded, so a bug that was already fixed is not reintroduced
• Coding preferences that follow you across every repository, not just this one

Requirements

Node and npx. npx repomemory go sets up the global profile, creates .context/, configures Claude Code and Cursor and runs the initial analysis — that path needs one provider key: ANTHROPIC_API_KEY, OPENAI_API_KEY, GEMINI_API_KEY or GROK_API_KEY. npx repomemory setup cursor needs no API key: it installs the MCP server into ~/.cursor/mcp.json, adds the rules file, and lets Cursor's own model do the analysis when you run /repomemory-analyze.

Setup effort

One command plus a key — npx repomemory go, then supply credentials

Tools you get

7 tools named in the project's documentation.

Requires

• npx on PATH
• One LLM provider key for the analysis npx repomemory go runs: ANTHROPIC_API_KEY, OPENAI_API_KEY, GEMINI_API_KEY or GROK_API_KEY (the Cursor route, npx repomemory setup cursor, needs none)

Where it runs

Both documented clients run the server on your machine.