#66th of 8 in Code review and testing
chatgpt-codereview
GitHub bot and Action that reviews pull request diffs with an LLM
Live demo ↗
(opens in a new tab)Documentation ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 4.5k
- License
- ISC
- Last commit
- Aug 2026
- Last release
- Jul 2026
- Language
- JavaScript
Missed the latest GitHub check; these facts may be older.
Overview
Probot-based GitHub app that reviews pull requests with OpenAI-compatible models and posts comments in the PR timeline and file changes. It re-reviews changed files after each push. It runs as a GitHub Action, a self-hosted Node app under pm2, or a Docker container, and supports OpenAI, Azure deployments and GitHub Models.
Who it is for: Teams on GitHub wanting automated LLM review comments on pull requests
Strengths
- Runs as a GitHub Action with a short workflow file, or as a self-hosted Probot app
- Supports OpenAI endpoints, Azure deployments and GitHub Models
- Filters files with IGNORE_PATTERNS and INCLUDE_PATTERNS; skips diffs over MAX_PATCH_LENGTH
- Review language, prompt, temperature and max_tokens set through environment variables
Weaknesses
- Hosted bot is test-only and rate-limited on AWS Lambda; README advises self-deploying
- Sends diffs to an external LLM API, so an API key and usage cost are required
- GitHub only; no GitLab or other platform support mentioned
- Docker section lists no exposed port or full env list; relies on .env.example
What it needs
- no GPU
- Docker
- Needs GitHub App or GitHub Actions, OpenAI-compatible API, Azure OpenAI or GitHub Models, Node.js, pm2 (self-hosting)
- Models: OpenAI GPT models, Azure OpenAI deployments, GitHub Models
Also in Code review and testing
See all 8| Rank | Project | Score |
|---|---|---|
| 1 | open-code-reviewCLI that reviews Git diffs with an LLM agent and line-level comments | 79 out of 100 |
| 2 | no-mistakesLocal git proxy that runs AI review, tests and lint before opening a PR | 71 out of 100 |
| 3 | pr-agentLLM pull request reviewer that comments via /review, /describe and /improve | 69 out of 100 |
| #4 | e2eAI-driven end-to-end testing framework for web and mobile apps | 67 out of 100 |
| #5 | front-end-checklistFront-end rules checklist with an MCP server for agent code review | 64 out of 100 |