Code Memory MCP Server

by kapillamba4 Your server? Claim it

local only

Code Memory runs on your own machine — the client starts it, so there is no endpoint to ping. 216 installs a week from pypi. Last commit 20 May 2026.

Local semantic code search with Git history. Works offline, no API key needed.

Installs per day peak 282 · avg 47 · +17% w/w

a month agotoday

216

Installs / week

pypi · code-memory

Stars

3 open issues

20 May 2026

Last commit

from GitHub

MIT

License

Python

Nothing serious here today

Today is the operative word: we check Code 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 code-memory -- uvx code-memory

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

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

~/.codex/config.toml

[mcp_servers.code-memory]
command = "uvx"
args = ["code-memory"]

.cursor/mcp.json

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

.vscode/mcp.json

{
  "servers": {
    "code-memory": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "code-memory"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: CODE_MEMORY_LOG_LEVEL (Logging verbosity (DEBUG, INFO, WARNING, ERROR)), EMBEDDING_MODEL (HuggingFace model ID for embeddings).

Alternatives to Code Memory

same job, measured the same way

Vectr

by swapnanil

Semantic codebase search + persistent working memory for AI code editors. Local, no API key.

156 installs/wk local only

MCP Local RAG

by damoqiongqiu

Semantic code & doc search with keyword boost. AST code nav, auto HF mirror, local, privacy-first.

132 installs/wk local only

Longhand

by wynelson94

Local memory for Claude Code. Semantic recall across session history with zero API calls.

408 installs/wk local only

Vibe Hnindex

by andyanh174

Index source code into a local knowledge base, search with keyword + semantic + hybrid modes.

497 installs/wk local only

Sunstone Weave: Local Semantic Code Search

by space-bacon

Semantic search over local folders of code and docs, with a code-search encoder running on your CPU.

105 installs/wk local only

Git Why

by alliecatowo

Finds the Git commits that explain why code is the way it is: semantic and full-text history search.

99 installs/wk local only

Filesift

by roshunsunder

Local file search for AI agents — semantic + keyword indexing over your codebase.

44 installs/wk local only

Cortex

by danielblomma

Local repo context for coding assistants with semantic search and graph relationships.

159 installs/wk local only

Code Memory — questions

Answers built from our own checks of this server.

Why is there no uptime for Code Memory?

Code 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 code-memory was installed 216 times last week.

How do I connect Code Memory?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls code-memory straight from pypi; nothing to host, nothing to sign up for.

How many people use Code Memory?

The pypi package code-memory was installed 216 times in the last week. Week over week that is +17%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Code Memory open source?

Yes — it is published under the MIT licence, written in Python, 50 stars on GitHub and 3 open issues. The source link is on this page, so you can read exactly what it does with your data before you connect it.