Skip to content
Back to search

openreview

An open-source, self-hosted AI code review bot powered by Vercel.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/vercel-labs-openreview/badge.svg)](/listings/vercel-labs-openreview)

HTML

<a href="/listings/vercel-labs-openreview"><img src="/api/listings/vercel-labs-openreview/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

1. Deploy to Vercel

Click the button above or clone this repo and deploy it to your Vercel account.

2. Create a GitHub App

Create a new [GitHub App](https://github.com/settings/apps/new) with the following configuration:

**Webhook URL**: `https://your-deployment.vercel.app/api/webhooks`

**Repository permissions**:

- Contents: Read & write - Issues: Read & write - Pull requests: Read & write - Metadata: Read-only

**Subscribe to events**:

- Issue comment - Pull request review comment

Generate a private key and webhook secret, then note your App ID and Installation ID.

3. Configure environment variables

Add the following environment variables to your Vercel project:

| Variable | Description | | ---------------------------- | ---------------------------------------------------------------------- | | `ANTHROPIC_API_KEY` | API key for Claude | | `GITHUB_APP_ID` | The ID of your GitHub App | | `GITHUB_APP_INSTALLATION_ID` | The installation ID for your repository | | `GITHUB_APP_PRIVATE_KEY` | The private key generated for your GitHub App (with `\n` for newlines) | | `GITHUB_APP_WEBHOOK_SECRET` | The webhook secret you configured | | `REDIS_URL` | (Optional) Redis URL for persistent state, falls back to in-memory |

4. Install the GitHub App

Install the GitHub App on the repositories you want OpenReview to monitor. Once installed, mention `@openreview` in any PR comment to trigger a review.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 179 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # OpenReview
  2. An open-source, self-hosted AI code review bot. Deploy to Vercel, connect a GitHub App, and get on-demand PR reviews powered by Claude.
  3. > **Beta**: OpenReview is currently in beta. It was built as an internal project to help the Vercel team test their technologies together. Expect rough edges and breaking changes.
  4. [![Deploy with Vercel](https://vercel.com/button)](https://vercel.com/new/clone?demo-description=An+open-source%2C+self-hosted+AI+code+review+bot.+Deploy+to+Vercel%2C+connect+a+GitHub+App%2C+and+get+automated+PR+reviews+powered+by+Claude.&demo-image=https%3A%2F%2Fopenreview.labs.vercel.dev%2Fopengraph-image.png&demo-title=openreview.labs.vercel.dev&demo-url=https%3A%2F%2Fopenreview.labs.vercel.dev%2F&from=templates&project-name=OpenReview&repository-name=openreview&repository-url=https%3A%2F%2Fgithub.com%2Fvercel-labs%2Fopenreview&env=GITHUB_APP_ID%2CGITHUB_APP_INSTALLATION_ID%2CGITHUB_APP_PRIVATE_KEY%2CGITHUB_APP_WEBHOOK_SECRET&products=%5B%7B%22integrationSlug%22%3A%22upstash%22%2C%22productSlug%22%3A%22upstash-kv%22%2C%22protocol%22%3A%22storage%22%2C%22type%22%3A%22integration%22%7D%5D&skippable-integrations=0)
  5. ## Features
  6. - **On-demand reviews** — Mention `@openreview` in any PR comment to trigger a review. Powered by [Chat SDK](https://chat-sdk.dev)
  7. - **Sandboxed execution** — Runs in an isolated [Vercel Sandbox](https://vercel.com/docs/sandbox) with full repo access, including the ability to run linters, formatters, and tests
  8. - **Inline suggestions** — Posts line-level comments with GitHub suggestion blocks for one-click fixes
  9. - **Code changes** — Can directly fix formatting, lint errors, and simple bugs, then commit and push to your PR branch
  10. - **Reactions** — React with 👍 or ❤️ to approve suggestions, or 👎 or 😕 to skip
  11. - **Durable workflows** — Built on [Vercel Workflow](https://vercel.com/docs/workflow) for reliable, resumable execution
  12. - **Extensible skills** — Ships with built-in review [skills](https://skills.sh) and supports custom skills via `.agents/skills/`
  13. - **Powered by Claude** — Uses Claude Sonnet 4.6 via the [AI SDK](https://sdk.vercel.ai) for high-quality code analysis
  14. - **Simple route handler** — Easily define route handlers using [Next.js Route Handlers](https://nextjs.org/docs/app/building-your-application/routing/route-handlers) for custom API endpoints and webhooks
  15. ## How it works
  16. ```mermaid
  17. sequenceDiagram
  18. participant U as Developer
  19. participant GH as GitHub
  20. participant WH as Webhook Handler
  21. participant WF as Vercel Workflow
  22. participant SB as Vercel Sandbox
  23. participant AI as Claude Agent
  24. U->>GH: @openreview in PR comment
  25. GH->>WH: Webhook event
  26. WH->>WF: Start workflow
  27. WF->>GH: Check push access
  28. WF->>SB: Create sandbox
  29. SB->>SB: Clone repo on PR branch
  30. SB->>SB: Install dependencies
  31. SB->>SB: Configure git
  32. WF->>AI: Run agent with PR context
  33. AI->>SB: Read files, run linters, explore code
  34. SB-->>AI: Command output
  35. AI->>GH: Post inline comments & suggestions
  36. AI-->>WF: Agent complete
  37. WF->>SB: Check for uncommitted changes
  38. alt Changes made
  39. WF->>SB: Commit & push to PR branch
  40. SB->>GH: Push changes
  41. end
  42. WF->>SB: Stop sandbox
  43. U->>GH: React 👍 or ❤️ on suggestion
  44. GH->>WH: Reaction event
  45. WH->>WF: Start new workflow run
  46. ```
  47. 1. Mention `@openreview` in a PR comment (optionally with specific instructions)
  48. 2. OpenReview spins up a sandboxed environment and clones the repo on the PR branch
  49. 3. A Claude-powered agent reviews the diff, explores the codebase, and runs project tooling
  50. 4. The agent posts its findings as PR comments with inline suggestions
  51. 5. If changes are made (formatting fixes, lint fixes, etc.), they're committed and pushed to the branch
  52. 6. The sandbox is cleaned up
  53. ## Setup
  54. ### 1. Deploy to Vercel
  55. Click the button above or clone this repo and deploy it to your Vercel account.
  56. ### 2. Create a GitHub App
  57. Create a new [GitHub App](https://github.com/settings/apps/new) with the following configuration:
  58. **Webhook URL**: `https://your-deployment.vercel.app/api/webhooks`
  59. **Repository permissions**:
  60. - Contents: Read & write
  61. - Issues: Read & write
  62. - Pull requests: Read & write
  63. - Metadata: Read-only
  64. **Subscribe to events**:
  65. - Issue comment
  66. - Pull request review comment
  67. Generate a private key and webhook secret, then note your App ID and Installation ID.
  68. ### 3. Configure environment variables
  69. Add the following environment variables to your Vercel project:
  70. | Variable | Description |
  71. | ---------------------------- | ---------------------------------------------------------------------- |
  72. | `ANTHROPIC_API_KEY` | API key for Claude |
  73. | `GITHUB_APP_ID` | The ID of your GitHub App |
  74. | `GITHUB_APP_INSTALLATION_ID` | The installation ID for your repository |
  75. | `GITHUB_APP_PRIVATE_KEY` | The private key generated for your GitHub App (with `\n` for newlines) |
  76. | `GITHUB_APP_WEBHOOK_SECRET` | The webhook secret you configured |
  77. | `REDIS_URL` | (Optional) Redis URL for persistent state, falls back to in-memory |
  78. ### 4. Install the GitHub App
  79. Install the GitHub App on the repositories you want OpenReview to monitor. Once installed, mention `@openreview` in any PR comment to trigger a review.
  80. ## Usage
  81. **Trigger a review**: Comment `@openreview` on any PR. You can include specific instructions:
  82. ```
  83. @openreview check for security vulnerabilities
  84. @openreview run the linter and fix any issues
  85. @openreview explain how the authentication flow works
  86. ```
  87. **Reactions**: React with 👍 or ❤️ on an OpenReview comment to approve and apply its suggestions. React with 👎 or 😕 to skip.
  88. ## Skills
  89. OpenReview uses a progressive skill system — the agent only loads specialized instructions when relevant, keeping context focused and reviews thorough. Skills are discovered from `.agents/skills/` at runtime.
  90. ### Built-in skills
  91. | Skill | Description |
  92. | ----------------------------- | ------------------------------------------------------------------------------------- |
  93. | `next-best-practices` | File conventions, RSC boundaries, data patterns, async APIs, metadata, error handling |
  94. | `next-cache-components` | PPR, `use cache` directive, `cacheLife`, `cacheTag`, `updateTag` |
  95. | `next-upgrade` | Upgrade Next.js following official migration guides and codemods |
  96. | `vercel-composition-patterns` | React composition patterns that scale for component refactoring |
  97. | `vercel-react-best-practices` | React and Next.js performance optimization guidelines |
  98. | `vercel-react-native-skills` | React Native and Expo best practices for performant mobile apps |
  99. | `web-design-guidelines` | Review UI code for Web Interface Guidelines and accessibility compliance |
  100. ### Adding custom skills
  101. Create a folder in `.agents/skills/` with a `SKILL.md` file containing YAML frontmatter:
  102. ```
  103. .agents/skills/
  104. └── my-custom-skill/
  105. └── SKILL.md
  106. ```
  107. ```markdown
  108. ---
  109. name: my-custom-skill
  110. description: When to use this skill — the agent reads this to decide whether to load it.
  111. ---
  112. # My Custom Skill
  113. Your specialized review instructions here...
  114. ```
  115. The agent sees only skill names and descriptions in its system prompt. When a request matches a skill, it calls `loadSkill` to get the full instructions — keeping the context window clean.
  116. ## Tech stack
  117. - [Next.js](https://nextjs.org) — App framework
  118. - [Vercel Workflow](https://vercel.com/docs/workflow) — Durable execution
  119. - [Vercel Sandbox](https://vercel.com/docs/sandbox) — Isolated code execution
  120. - [AI SDK](https://sdk.vercel.ai) — AI model integration
  121. - [Chat SDK](https://www.npmjs.com/package/chat) — GitHub webhook handling
  122. - [Octokit](https://github.com/octokit/octokit.js) — GitHub API client
  123. ## Development
  124. ```bash
  125. bun install
  126. bun dev
  127. ```
  128. ## License
  129. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.