@fullstackhouse/cerber weekly downloads statistics

cerber 🐕

AI code-review cockpit. Claude reviews your pull requests into local artifacts — a summary, a chaptered walkthrough of the changes, draft inline comments, and a verdict with a confidence score. You read it in a local web cockpit, keep or rewrite or drop each comment, then press Send when you agree with it.

Nothing reaches GitHub until you explicitly say so. Reviewing is 100% local and read-only; three things can write, each one a click you make — the Send button, opt-in daemon auto-send you turn on yourself, and handing a review to somebody else. A review only ever goes out under your own account because you decided it should: Send posts the one you vouched for, and a handoff posts the draft only if you ticked the box to send it along, always as a comment.

That gate is the whole point, and the reason this is not another review bot:

Reviewing pull requests with an AI model creates a specific danger: a system that can both draft opinions and hold GitHub credentials will eventually post one without a human deciding it should.

Named after Cerberus, the gatekeeper: cerber guards what gets merged.

Why it exists, and the four things I tried first: AI drafts the review. I decide what gets sent.

The whole loop in seventeen seconds — five PRs already drafted when you sit down, the one that isn't an approval, straight to its blocker, arguing with the reviewer until it rewrites its own finding, dropping the comment you disagree with, and sending what's left as your review:

A drafted review, as you read it — verdict and confidence beside the PR title, the walkthrough rail on the left, a summary written for someone who has not read the diff:

And the queue they arrive in — cerber serve polls GitHub for PRs awaiting your review and drafts one for each, so they are written by the time you get there:

Every screenshot in this README is cerber reviewing cerber's own pull requests.

Quick start

Requires Node 22+, an authenticated gh, git, and a logged-in claude CLI. No API keys, no config, no database. The cockpit wants a browser from 2024 on (Chrome/Edge 123, Safari 17.5, Firefox 120).

Claude Code is a hard requirement, and a paid one. Cerber drafts reviews by running claude as you: it rides your existing Claude Code login and draws on that plan's usage limits, so you need a Claude subscription that includes Claude Code. There is no ANTHROPIC_API_KEY path — not as a fallback, not at all. GitHub only; no GitLab or Bitbucket. Notifications are macOS and Linux.

Run cerber doctor first — it checks all three tools and tells you which one to fix, instead of letting a missing login turn into an empty cockpit later.

# Open the cockpit — this is the whole product
npx @fullstackhouse/cerber serve        # → http://127.0.0.1:4820

# Or review one PR from the terminal (writes a local artifact to ~/.cerber,
# nothing else)
npx @fullstackhouse/cerber review https://github.com/owner/repo/pull/123

# Review several
npx @fullstackhouse/cerber review owner/repo#123 owner/repo#124
npx @fullstackhouse/cerber review 123 124 --repo owner/repo

# See what's in the queue
npx @fullstackhouse/cerber list

serve does the whole loop by default: discover → draft → wait for you. Sending stays a human click. Tame it with --no-auto-review (list awaiting PRs, review on click) or --no-poll (no GitHub polling at all) — or flip those switches in the cockpit's Settings, which persist in ~/.cerber/config.json and apply on the next poll. Settings also takes per-repo exceptions (daemon.autoReviewRepos): keep a busy repo to the click while the rest are drafted, or draft one repo with auto-review otherwise off. And it can leave PRs that only a team of yours was asked to review to the click (daemon.autoReviewTeamRequests), while the ones naming you are still drafted.

Contents

• What a review looks like — what Claude writes and how you walk it
• The inbox — what the queue shows, what settles a row, the notifications
• Handing a review to somebody else
• It reviews the code, not just the diff
• Trusted PRs: reviews that can run things
• When the PR moves under you
• Arguing with the review before you send it
• Every row remembers what happened to it
• Status · Running on a VPS · How it works · Development

What a review looks like…