Repo Memory MCP Server

by yubinkim444 Your server? Claim it

local only

Repo Memory runs on your own machine — the client starts it, so there is no endpoint to ping. 99 installs a week from pypi. Last commit 26 Aug 2026.

Shared, git-tracked working memory for AI agents on the same codebase.

Installs per day peak 214 · avg 20 · -75% w/w

a month agotoday

Installs / week

pypi · repo-memory-mcp

Stars

0 open issues

26 Aug 2026

Last commit

0 releases in 90 days

MIT

License

Python

Nothing serious here today

Today is the operative word: we check Repo Memory every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add repo-memory -- uvx repo-memory-mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "repo-memory": {
      "args": [
        "repo-memory-mcp"
      ],
      "command": "uvx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.repo-memory]
command = "uvx"
args = ["repo-memory-mcp"]

.cursor/mcp.json

{
  "mcpServers": {
    "repo-memory": {
      "args": [
        "repo-memory-mcp"
      ],
      "command": "uvx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "repo-memory": {
      "args": [
        "repo-memory-mcp"
      ],
      "command": "uvx"
    }
  }
}

This one needs environment variables set before it will start: REPO_MEMORY_ROOT (Absolute path to the repository whose .ai-memory/ to read/write. Defaults to the current working directory.). The author declared them in the registry entry; get the values from the project itself.

Alternatives to Repo Memory

same job, measured the same way

Sirro

by jonathanmberg

Shared memory for AI coding agents. Save once, reuse from Cursor, Claude Code, Codex.

answering

TeamShared

by xhad

Shared memory for coding agents. Stop re-explaining your codebase every session.

92 tools answering

Shift MCP Server

by cyanheads

Lightweight coordination layer for multiple AI agents working on the same codebase simultaneously.

45 installs/wk local only

Agent Guard MCP

by kavachh

Git-aware safe file ops for AI agents: delete anything except git-tracked source code.

local only

projectmind

by nodemint-dev

Persistent project memory for AI coding agents: one compact digest instead of re-reading the repo.

65 installs/wk local only

Instagit

by instagitai

MCP server for Instagit — AI-powered Git repository analysis for coding agents

38 installs/wk local only

Droste

by lorismascio17

Local code-memory graph for AI coding agents.

119 installs/wk local only

Global Agent Memory

by ozankasikci

Shared, project-aware memory for Claude Code, Codex, and other agents with human review.

85 installs/wk local only

Repo Memory — questions

Answers built from our own checks of this server.

Why is there no uptime for Repo Memory?

Repo Memory runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package repo-memory-mcp was installed 99 times last week.

How do I connect Repo Memory?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls repo-memory-mcp straight from pypi; nothing to host, nothing to sign up for.

How many people use Repo Memory?

The pypi package repo-memory-mcp was installed 99 times in the last week. Week over week that is -75%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Repo Memory open source?

Yes — it is published under the MIT licence, written in Python and 1 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.