Alibaba open-sources Open Code Review: hybrid deterministic + LLM agent code reviewer
bibryam · x · 2026-09-10
Alibaba open-sourced Open Code Review, a code review tool already at 22.2k GitHub stars. It wraps an LLM agent with deterministic controls—file selection, rule matching, line positioning, and independent reflection—letting the model focus on dynamic context and review reasoning. The hybrid architecture ships a multi-language ruleset (NPE, thread-safety, XSS, SQL injection), precise line-level comments, OpenAI/Anthropic-compatible APIs, a VS Code extension, and is battle-tested at Alibaba's scale.
More from coding & agent
- Dev asks: hundreds of AI agents share one API key — is per-agent identity worth it? — SheepherderFree3931 · 2026-09-10
- Stripe Built an SDK Prototype in 2 Days Instead of 3 Weeks by Delegating to AI Agents Spec-First — dl_weekly · 2026-09-10
- Veteran dev: agentic coding loops 8 times, burns 100k tokens, and wrecks mature codebases — cgouguen · 2026-09-10
- Replacing smolagents' VisitWebpageTool with a custom fetch layer to beat anti-bot pages — InsideDebt6345 · 2026-09-10
- AI agents don't know their code makes codebases harder to work with — _Stocko_ · 2026-09-10
- Hy4 preview tested: playable 3D survival game from a single prompt in WorkBuddy — mhdfaran · 2026-09-10