Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.
Open Code Review is an AI-assisted command-line tool that examines code changes or entire files and produces structured comments tied to specific lines. Developers use it for repository-level reviews, code auditing, and checks such as security, null safety, and thread safety.
Latest release v1.13.0 · 13 Oct 2026
2 files for Codex, OpenCode and Claude Code: open-code-review AGENTS.md, open-code-review CLAUDE.md — 1,392 tokens loaded in every session.
AGENTS.md A 1,387 tok CLAUDE.md A 5 tok These files are alibaba/open-code-review's own configuration — they tell Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.