๐ TL;DR: a CLI tool that fixes the missed files and drifting line numbers general-purpose AI agents tend to produce during code review, backed by a hybrid design battle-tested inside Alibaba.
Title: alibaba/open-code-review
URL:
๐ Highlights
โ๏ธ Hard constraints for precision-critical steps, AI only for dynamic judgment
๐ Generates structured, line-level review comments straight from Git diffs
๐ต๏ธ Full-file scan mode for auditing unfamiliar codebases
๐ก Built-in multi-language rules for NPE, thread-safety, XSS, SQL injection
๐ Plugs into Claude Code, Codex, Cursor, and other coding agents
๐ Beats Claude Code on Precision/F1 across 50 repos and 200 real PRs
๐ฐ Uses about 1/9 the tokens of comparable alternatives
Getting battle-tested precision from thousands of internal developers as an open-source CLI feels like a genuinely useful shortcut.
#
CodeReview# #
AIAgents#