taovc/pr-cockpit

Local AI PR workbench — Claude/Codex review in isolated git worktrees, human-gated GitHub comments

What it solves

PR Cockpit addresses the friction of managing pull requests (PRs) one by one in a terminal. It provides a centralized, AI-powered interface to review, fix, and manage an entire repository's PR queue locally without scattering work across multiple shells.

How it works

The application connects to your local GitHub CLI (gh) to pull PRs into an isolated, read-only git worktree. You can then use Claude or Codex to perform AI-assisted reviews, generate structured findings, and even apply fixes. All interactions are gated by you: the AI suggests changes or comments, but nothing is posted to GitHub or committed to your repository until you explicitly approve it in the web interface.

Who it’s for

It is designed for developers who want to streamline their code review process using AI while maintaining full control over their repository. It is ideal for those who prefer a local-first workflow where code never leaves their machine and who want a structured, safe way to gate AI-generated feedback and fixes.

Highlights

  • Local-First Security: Code stays on your machine; all GitHub interactions are performed via your local gh CLI.
  • Isolated Worktrees: AI review and development occur in isolated git worktrees, keeping your main repository clean.
  • Human-in-the-Loop: Every AI finding, comment, or code fix requires your explicit approval before being published to GitHub.
  • Project-Specific Configuration: Customize review methodology, AI providers (Claude or Codex), and effort levels on a per-project basis.
  • Integrated Assistant: Includes a project-aware assistant for ad-hoc troubleshooting, feature development, and directory-level chat.

Related

  • Project
    kodustech/kodus-ai

    An open-source AI code review tool that integrates with major Git providers to automate pull request analysis using customizable rules and a variety of LLMs.

  • Project
    pbakaus/agent-reviews

    A CLI and agent-skill framework that automates the triage, fixing, and resolution of GitHub pull request comments, specifically targeting the noise generated by AI review bots.

  • Project
    AnandChowdhary/continuous-claude

    A CLI tool that runs AI coding agents in a continuous loop to autonomously create, test, and merge pull requests for large-scale software projects.

  • Project
    anc95/ChatGPT-CodeReview

    An automated code review bot powered by ChatGPT that analyzes pull requests and provides feedback directly in the GitHub PR timeline.

  • Project
    The-PR-Agent/pr-agent

    PR‑Agent is an open‑source AI bot that automatically reviews pull‑requests (or issues) using LLMs. It can summarize changes, give a full code‑review, suggest improvements, or answer free‑form questions. The tool works with GitHub, GitLab, Bitbucket, Azure DevOps, and Gitea, and can be run as a GitHub Action, Docker container, or local CLI. Prompts are fully configurable, and it supports many LLM providers via LiteLLM. Self‑hosting keeps data private, and the project is community‑maintained with sponsorship from Qodo.