Orvex reviews every pull request the moment it opens. Deterministic rules run first, then a multi-model AI ensemble weighs in, and it runs your code — not just the diff. It flags the bug an instant before merge.
// THE PIPELINE
Every PR runs the same route — cheapest checks first, most expensive last, nothing wasted. Different layers catch different bugs.
Cheap, exact checks run before any LLM token is spent. Config-as-code — your repo sets the rules in .orvex-review.yml.
✓ 0 tokens · instantUp to three independent models review one PR. Different models catch different bugs — the merged, deduped result is the differentiator.
A · B · C → mergedOrvex executes the change in a sandbox instead of only reading the diff — the runtime-proof moat. Add @orvex deep for critical PRs.
▶ sandbox execution// HEAD-TO-HEAD · 80 REAL PRs
Run side-by-side with Codex, CodeRabbit and Qodo on real pull requests. Different models catch different bugs — the ensemble surfaces what a single pass walks right past.
No single model catches everything — that's the whole point of the ensemble. Coverage = share of all issues flagged by any reviewer across 80 real PRs; “only Orvex” = clusters no other bot flagged.
// IT REMEMBERS
Push three times, get zero repeated nits. Orvex tracks what it already said and replies “Fixed” when you actually fix it. Roughly eight comments, max — signal, not noise.
// PRICING
Every account starts with 10 free reviews — no card required. Scale from a first repo to bring-your-own-LLM enterprise.
Every plan starts with 10 free reviews — no card required.
Install the GitHub App and your next pull request gets reviewed — before it merges.