Runs 100% in your browser · no server · no API key

A panel of agents reviews your code.

Quorum routes a diff to specialist reviewers — security, performance, correctness, tests, style — in parallel, then a synthesizer consolidates everything into one verdict. Try it live below; it's running the pure-Python engine in WebAssembly.

app/handler.py · unified diff
Booting Python runtime…

Multi-agent

Each concern gets its own focused reviewer running concurrently — not one model spread thin.

Provider-agnostic

Mock, Claude, OpenAI, or local Ollama — with native structured output and a tolerant fallback.

Measured

A detection benchmark scores recall on planted defects and false alarms on clean code.