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
Related event: Alibaba Open-Sources Code Review Tool Using 1/9 the Tokens of Claude Code(2 posts)→
More from coding & agent
- Models already understand harnesses: a minimal agent harness takes hours, but customization still needs you — omarsar0 · 2026-10-31
- krishnan on autonomous lab agents: criticism changed the next search, not just verdicts — krishnan · 2026-10-31
- krishnan proposes logging ruled-out troubleshooting hypotheses for future reopening — krishnan · 2026-10-31
- PI agent rejected 75 proposals in 30 hours; manager banned recurring bad ideas — krishnan · 2026-10-31
- Multi-agent AI lab autonomously researches quantum spins in diamond, revises drifting experiments — krishnan · 2026-10-31
- Build your own agent harness: omarsar argues vendor harnesses will quietly constrain users — dair_ai · 2026-10-31