[GitHub Trending] alibaba/open-code-review
Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.
Alibaba's open-source code review tool with LLM agent integration is technically deep, actionable, and directly relevant to AI-assisted development.
Alibaba open-sourced Open Code Review, an AI-powered CLI that reads Git diffs via an agent with tool-use for line-level comments, achieving higher precision and F1 than Claude Code while consuming ~1/9 the tokens. Its deterministic-engineering-and-agent hybrid uses template-engine rule matching and external positioning modules to avoid incomplete coverage and position drift. The tool includes an "ocr scan" mode for auditing full codebases and was validated on a real-world benchmark of 50 repos, 200 PRs, 10 languages, with 80+ engineers.
alibaba