# vercel-labs/openreview

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

Repository: https://github.com/vercel-labs/openreview
Canonical: https://ross.abutalabs.com/products/openreview
Homepage: https://openreview.labs.vercel.dev
Language: TypeScript
License Family: other
Topics: aisdk, codereview, vercel
Last push: 2026-03-06T16:44:33+00:00

## Health v2 (maintenance only)
Score: 46/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 70, release rhythm 35, longevity 13
- inputs: {"age_days": 185, "days_push": 180, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1516, forks 105 (observed 2026-08-28T04:04:56.493362+00:00)

## What it is
OpenReview is an open-source, self-hosted AI code review bot that deploys to Vercel and connects to GitHub via a GitHub App. Mentioning @openreview in a pull request triggers a Claude-powered agent that reviews diffs in a sandboxed environment, posts inline suggestions, and can commit fixes directly to the PR branch.

## Use cases
- automate code review on pull requests
- self-host an AI reviewer for my GitHub repos
- get inline AI suggestions on PRs with one-click fixes
- have a bot run linters and tests during PR review
- auto-fix formatting and lint errors on PR branches
- customize AI review behavior with custom skills

## When to choose
- you want an on-demand, self-hosted AI code reviewer integrated with GitHub
- you already deploy on Vercel and can use Vercel Sandbox and Workflow
- you want the bot to run project tooling and push automated fixes
- you need extensible review behavior via custom skills

## When to avoid
- you need a fully stable, production-hardened tool (it is beta with breaking changes)
- you don't use Vercel or GitHub for your workflow
- you require a permissive license (the repo currently has none)
- you want fully automatic reviews on every PR without mentioning the bot

## Facets
- artifact type: application
- maturity: experimental
- function: code-review, agent-framework, llm-inference, webhook, workflow-automation, developer-tools
- domain: developer-tools, version-control, artificial-intelligence
- platform: self-hosted, cloud
- tags: ai-code-review, github-app, vercel, claude, pull-requests, beta, ai-agents, automation, web-server, nodejs

## Member repositories
- vercel-labs/openreview (main) score 46

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:56.493362+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:32:07.869274+00:00, confidence not recorded.
  - readme: https://github.com/vercel-labs/openreview (fetched 2026-08-28T04:04:56.493362+00:00, sha e26a61ccfaf4)
  - homepage: https://openreview.labs.vercel.dev (fetched 2026-08-29T11:35:49.048805+00:00, sha b2ec0e7173a8)
- Data as of 2026-08-30T08:39:29.467469+00:00.