← Discover
GitHub · tirth8205/code-review-graph↑ +74 today

Saving tokens in AI code review

Code-review-graph analyzes the code base and creates a locally focused code intelligence map for artificial intelligence tools. This structure makes artificial intelligence-supported code review processes more efficient by using context reduction methods in large projects.

Updates

  • September 19, 2026: Stars 30,676 → 31,601, latest release v2.3.9 (September 18, 2026).
  • August 22, 2026: Stars 29,487 → 30,676, latest release v2.3.8 (August 21, 2026).
  • August 9, 2026: Stars 28,041 → 29,487, latest release v2.3.7 (July 18, 2026).
  • August 2, 2026: Stars 19,852 → 28,041, latest release v2.3.7 (July 18, 2026).

What you get

  • Analyzes the code base and presents only relevant files to artificial intelligence
  • Significantly reduces token consumption in large projects
  • Automatically manages updates by analyzing the impact of changes

Installation

Basic Setup
pip install code-review-graph
Auto Configuration
code-review-graph install

Running it

Creating the Code Map
code-review-graph build

If you don't write code

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

This project has code-review-graph installed. Please create the code review graph of the project and have my AI assistant analyze the code changes by only reading the necessary context.

Repository: https://github.com/tirth8205/code-review-graph. 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

Code Intelligence GraphContext ReductionContextTokenArtificial Intelligence
Who it is forIt is suitable for developers who work on large code bases and want to reduce the token costs of artificial intelligence tools.
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 2026-07-18: 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.