Alibaba Open-Sources Code Review Tool: Deterministic Pipeline Plus LLM Agent Hybrid
blaizedsouza · x · 2026-09-13
Alibaba has open-sourced its open-code-review tool on GitHub (22.6k stars, 1.7k forks so far), claiming it's battle-tested at Alibaba's scale.
Key features:
- Hybrid architecture: combines a deterministic rule pipeline with an LLM Agent for both precision and flexibility
- Line-level precise comments that cut down noise
- Built-in, multilingual fine-tuned rule sets covering common defects like NPE, thread safety, XSS, and SQL injection
- Compatible with OpenAI and Anthropic APIs, with swappable models
- Ships a VS Code extension, a Claude plugin and skills, with multilingual docs
More from coding & agent
- Grok Build ships v1.0.29/30: tmux lag fix, Ctrl+G dock toggle, multi-agent crash fixes — XFreeze · 2026-09-13
- Codex harness burns tokens polling idle loops; workaround: disable polling or delegate — brandon_galang · 2026-09-13
- Same LLM eval, different scores: a method to tell real regressions from noise — bgoncalves · 2026-09-13
- Spend 20% of your time having AI build your app, 80% using it — Daniel_Farinax · 2026-09-13
- OpenAI shows off GPT-6 Astra community builds, from 3D anatomy to Unity air traffic sims — OpenAIDevs · 2026-09-13
- GitHub repo curates 500+ agentic AI projects for ideas and implementation study — Roger_M_Taylor · 2026-09-13