Alibaba Open-Sources Code Reviewer That Beats Claude Code on F1 Using 1/9 the Tokens
techNmak · x · 2026-09-13
Alibaba open-sourced Open Code Review, its internally battle-tested code review tool that has served tens of thousands of developers and found millions of defects. It uses a hybrid architecture: deterministic pipelines handle file coverage, bundling, rule matching and comment positioning, while the agent only handles reasoning and repo context. On a 200-PR benchmark across 50 open-source repos, Alibaba reports higher precision and F1 than Claude Code with the same model at roughly 1/9 the tokens, trading off lower recall. It ships multi-language rulesets (NPE, thread-safety, XSS, SQL injection), is OpenAI/Anthropic compatible, and has 23k GitHub stars.
Related event: Alibaba Open-Sources Code Review Tool Using 1/9 the Tokens of Claude Code(2 posts)→
More from coding & agent
- krishnan on autonomous lab agents: criticism changed the next search, not just verdicts — krishnan · 2026-10-31
- Testing agents with explicit rejection records: a cheaper path to verified troubleshooting answers — krishnan · 2026-10-31
- krishnan proposes logging ruled-out troubleshooting hypotheses for future reopening — krishnan · 2026-10-31
- Multi-agent AI lab autonomously researches quantum spins in diamond, revises drifting experiments — krishnan · 2026-10-31
- PI agent rejected 75 proposals in 30 hours; manager banned recurring bad ideas — krishnan · 2026-10-31
- Next 9 proposals explored 7 new directions: rejection became information — krishnan · 2026-10-31