Technical articles, tutorials, and insights
Alibaba open-sources its internal AI code review tool, battle-tested across tens of thousands of engineers and millions of detected defects before public release. Core: a hybrid architecture pairing deterministic engineering pipelines (file selection, bundling, rule matching) with an LLM agent (dynamic judgment). Same underlying model as Claude Code — higher precision and F1, roughly 1/9 the token usage. Supports review (git diff) and scan (full-file audit) modes, delegation mode for your own agent, and GitHub Actions / GitLab CI / Gerrit integration. 18.1k Stars, Apache 2.0.