Alibaba open-sources OpenCodeReview, its internal AI code reviewer using ~1/9 the tokens of Claude Code
udmrzn · x · 2026-11-16
Alibaba open-sourced OpenCodeReview, an AI code reviewer it ran internally for two years across tens of thousands of developers, catching millions of defects. The project hit #1 on GitHub trending (day/week/month).
- Reviews Git changes line by line; detects NPEs, concurrency issues, XSS, SQL injection; can review whole repos, not just diffs
- Works with Claude Code, Codex, Cursor, Kimi Code; cross-platform; Apache-2.0, one-line npm install, bring your own OpenAI/Anthropic model
- On a benchmark of 200 real PRs across 50 repos validated by 80+ senior engineers, it used 1/9 the tokens of Claude Code with higher precision and fewer false alarms
Related event: Alibaba Open-Sources Internal AI Code Review Tool(4 posts)→
More from coding & agent
- A zero-AI chatbot: 1,000 DeepSeek agents wrote 300,000 if-else rules — victormustar · 2026-11-16
- Open-source Swamp compiles repeated agent skills into workflows: 8x fewer tokens, 2x faster — udmrzn · 2026-11-16
- 67k-star diagram-design skill makes AI coding tools draw editorial-grade diagrams — adnan_hashmi · 2026-11-16
- Dev's take on AI workflows: feed the right data and build verification loops — iamsahaj_xyz · 2026-11-16
- Every tool is becoming an API for AI agents: a field guide to the agent stack — DEVIL_QI · 2026-11-16
- Open-source CalDAV MCP Server lets AI assistants manage your iCloud Calendar — Weekly_Mountain2783 · 2026-11-16