# Map your codebase to AI

Codegraph is a local knowledge graph tool that pre-indexes codebases and serves them to AI models. By automatically syncing code changes, it enables coding assistants like Claude Code or Cursor to use fewer tokens and tool calls.

- ★ 73,076
- C
- GitHub Trending · 2026-10-01

## Updates

- **October 3, 2026:** Stars 72,721 → 73,076, latest release v1.6.2 (October 3, 2026).
- **October 1, 2026:** Stars 72,718 → 72,721, latest release v1.6.1 (September 29, 2026).

## What you get

- Creates a local knowledge graph that enables AI models to consume fewer tokens while coding.
- Keeps the index always up to date by automatically syncing code changes in the background.
- Directly connects tools like the coding assistant Cursor with your project's architecture.

## Installation

**Global installation with the npm package manager**

```
npm i -g @colbymchenry/codegraph
```

## Running it

**Running and linking the tool directly with npx**

```
npx @colbymchenry/codegraph
```

## If you don't write code

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

Install the Codegraph tool in my project by running the command `npm i -g @colbymchenry/codegraph` via the npm package manager. Then, complete the process by running the command `npx @colbymchenry/codegraph` to configure AI assistants.

Repository: https://github.com/colbymchenry/codegraph. 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

- [Knowledge Graph](https://trescout.com/en/dictionary/knowledge-graph/)
- [Token](https://trescout.com/en/dictionary/token/)
- [Artificial Intelligence](https://trescout.com/en/dictionary/artificial-intelligence/)

- **Who it is for:** It is intended for developers who want AI-powered coding assistants to quickly understand complex codebases while spending fewer tokens.
- **License:** MIT

## Links

- [GitHub repository →](https://github.com/colbymchenry/codegraph)
- [Read in Turkish →](https://trescout.com/discover/codegraph/)

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-10-01: 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.

---
Source: TreScout Discover · https://trescout.com/en/discover/codegraph/