Getting Started

Get up and running with CorgReview in under a minute.

What is CorgReview?

CorgReview is a local-first code review tool designed for AI-generated code. It gives you a GitHub PR-like interface for reviewing commits made by AI agents — with structured feedback your agent can actually act on.

It works with Claude Code, Cursor, Windsurf, Codex, and OpenCode. No cloud, no account, no data leaving your machine.

Installation

CorgReview is a single binary. Download it and you're done.

After purchasing, you'll receive download links via email. Place the binary somewhere on your PATH and you're ready to go.

Supported platforms

OS Architecture
macOSarm64, amd64
Linuxamd64, arm64

macOS users: Right-click the binary and select "Open" on first run (standard for unsigned binaries).

Quick start

1. Set up your AI agent

Run corg init in your project directory. CorgReview auto-detects your AI agent and installs the appropriate skill.

$ cd your-project
$ corg init
Detected agents:
  1. Claude Code
  2. Cursor
Select agent [1]: 1
✓ Installed skill for Claude Code

2. Review code

After your AI agent makes changes and commits, review them:

# Review the current feature branch
$ corg review

# Or review specific commits
$ corg review HEAD~3..HEAD

Your browser opens to a review UI showing the diff. Add line comments, tag issues as blockers or suggestions, and submit your review.

3. Your AI reads the feedback

When you submit, CorgReview saves your review as structured markdown in .corg/reviews/. Your AI agent receives the results — blocker count, comments, and your summary — and addresses the feedback.

Next steps