← Discover
GitHub · DeusData/codebase-memory-mcp↑ +371 today

Fast indexing for AI coding agents

Codebase-memory-mcp offers high-performance code intelligence by transforming code bases into a permanent knowledge graph. Developed in C language, the tool supports 158 programming languages, reduces query times to below milliseconds and reduces token usage.

Updates

  • October 17, 2026: Stars 46,686 → 46,739, latest release v0.12.1 (October 16, 2026).
  • October 16, 2026: Stars 45,659 → 46,686, latest release v0.12.0 (October 15, 2026).
  • October 2, 2026: Stars 43,473 → 45,659, latest release v0.11.0 (September 15, 2026).
  • September 16, 2026: Stars 41,472 → 43,473, latest release v0.11.0 (September 15, 2026).

What you get

  • Converts codebase into knowledge graph in milliseconds
  • Natively supports 158 programming languages
  • Reduces coin usage by up to 120x

Installation

Global with npm
npm install -g codebase-memory-mcp

If you don't write code

Paste this into your AI agent (Claude Code · Codex · Antigravity)

Index this project to help you analyze my codebase and answer structured queries more efficiently. After indexing the project, I want you to provide in-depth information about my code base using relationships between functions, classes, and call chains.

Repository: https://github.com/DeusData/codebase-memory-mcp. Follow the official instructions in the README of this repository for setup and execution.

Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.

Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.

Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.

Related dictionary terms

Who it is forFor developers who want to analyze code bases faster and optimize token consumption of AI agents.
LicenseMIT

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-06-18: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.