Back to browse
GitHub Repository

r3 - Review. Revise. Resolve. A code review tool that runs on your machine and sparks joy ✨ when reviewing AI-generated code and docs.

0 starsTypeScript

R3 – A Local Code Review Tool for You and Your AI Agent

by rickye26·Jul 10, 2026·1 point·0 comments

AI Analysis

●●SolidSolve My ProblemShip ItNiche Gem

Replaces chaotic chat threads with line-anchored feedback loops for AI agents.

Strengths
  • CLI `watch` command blocks execution until human feedback is submitted, enforcing a strict review loop.
  • Feedback is anchored to specific lines or quotes, solving the context-loss problem in long chat histories.
  • Fully local execution ensures sensitive design docs and proprietary code never leave the machine.
Weaknesses
  • Requires manual CLI handshakes (`create`, `watch`, `reply`) rather than deep IDE or agent-native integration.
  • No Windows support listed, limiting adoption for developers on that platform.
Target Audience

Developers using AI coding agents (Cursor, Copilot, Claude) for large refactors

Similar To

GitHub Pull Requests · Phabricator · Review Board

Post Description

I built r3 to scratch my own itch when reviewing long design doc and planning doc from AI. The chat interface is inherently bad at tracking multiple pieces of feedback across different parts of a document, so I created a lightweight local web UI to organize the review process.

I have been using it on my own projects for one week, and it has made giving structured feedback to AI much easier. I thought others working with AI coding agents might find it useful too.

I'd love to hear what you think and any feedback you have!

Similar Projects