Skip to content

[GitHub Trending] alibaba/open-code-review

8.2 relevance
Score Breakdown
technical depth
8
novelty
8
actionability
9
community
7
strategic
8
personal
9

Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.

Open-source code review tool with LLM agent, highly relevant to SDLC and AI integration.

AI/ML github.com
Open-source & free — Battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in fine-tuned ruleset (N...
Summary

Alibaba open-sourced Open Code Review, an AI CLI tool that reads Git diffs and uses a configurable LLM agent with tool-use to generate line-level comments. Its hybrid architecture combines deterministic engineering (precise file selection, smart bundling, rule matching) with an agent, achieving higher precision and F1 than Claude Code on a benchmark of 200 PRs from 50 repos across 10 languages, while consuming ~1/9 the tokens. The tool, validated internally on millions of defects, also offers 'ocr scan' for full-file auditing and deliberately trades recall for lower noise.

Author

alibaba