Showcase · ReviewPilot

A code review on every pull request.

Install the GitHub App and every PR gets a concrete, friendly review within minutes: what the PR does, what is actually broken, what you might consider. No noise, no flattery — and free for open source. The diff automatically goes to the cheapest model that can handle it, and every review is traceable down to the cent.

~2 min
from PR open to review
100%
end-to-end tested against the real GitHub API
2
models, chosen automatically by diff size
read-only
the App fetches only the diff
Architecture

From webhook to review, with a guardrail up front

GitHub knocks, ReviewPilot verifies the signature first and only then does anything happen. The diff determines which model does the work; the answer comes back as one comment. Underneath runs the same correlation thread as through the rest of the lab: every review is a cost line.

GitHub PR opened / synchronize webhook + signature HMAC verification valid secret? tier check otherwise 401, nothing happens Model router diff size → model Flash or Pro PR comment one review, with source file · line Log + cost register — one correlation id per review cid · repo · PR · tier · model · tokens in/out · cost — via Sentinel & AgentLedger
How it works

Seven steps, one comment

From PR to review

  1. GitHub sends a webhook the moment a pull request opens or updates
  2. The signature (HMAC-SHA256) is verified — no valid secret, no review
  3. Public repo → review right away; private repo → review on your own code
  4. A GitHub App token fetches the diff, read-only and per installation
  5. Diff size determines the model: small → DeepSeek V4 Flash, large → DeepSeek V4 Pro
  6. The review comes back as one clean PR comment, referencing file and line
  7. Every call gets a correlation id, so AgentLedger records the cost per review
What a review looks like

Concrete, specific, and short where it can be

Every review follows the same shape: summary, what is really broken, what you should consider, and a few minor points. It never invents line numbers; if the diff is trivial, it says so in two lines instead of forcing feedback.

ReviewPilot · PR #42 — add rate limiting to /login

Summary. Adds a fixed-window rate limiter to the login route. Sensible approach; two edge cases need attention before merge.

Must fix.

  • auth.js:38 — the counter is keyed on username only, so an attacker rotating usernames bypasses the limit. Key on IP + username.
  • auth.js:51 — the window resets with Date.now() per request instead of per window, so the limit never actually triggers.

Should consider. Return 429 with a Retry-After header; add a test for the 11th attempt.

— 🧾 Review by ReviewPilot · free for open source · review.neuralex.nl

Example to illustrate the format; the content differs per PR.

Costs

Every review is logged with its cost

Each review carries a correlation id, so AgentLedger records per review which route the model took, what it cost and where it went — visible in the ledger, not a black box.

Why developers value it

Not another bot

Right after it opens

Feedback within ~2 minutes of a PR — no queue, no manual work.

Smart routing

Small diffs to a fast, cheap model; large diffs to a stronger model. Always the cheapest one that fits.

Privacy first

No data retention, no training on your code. The review is ephemeral: used and gone.

Works on public repos too

Public repositories get a full review on every PR — verifiable on a public test repo anyone can check.

Transparent costs

Every review is logged with its call cost via AgentLedger — no black box.

No vendor lock-in

Runs on our own model router. No dependency on a single American API.

Where it stands now

ReviewPilot runs in dogfood: the chain is built and tested, and reviews our own repos. The amounts and times above are design targets — not production measurements. As soon as the test week is done, we replace them with real numbers from the register, just like with AgentLedger.

Built with GitHub Appn8nHMAC-SHA256Bifrost model-routerDeepSeek V4Cloudflare WorkerAgentLedger
Early access

Proof, not promises

ReviewPilot installs as a GitHub App and posts back a substantiated review from the very first PR — verifiable on a public test repo, with every call logged in AgentLedger.