OpenCodeReview

AI code review battle-tested at Alibaba's scale

Visit website →

About

OpenCodeReview is an open-source AI code review tool from Alibaba. It uses a hybrid architecture: deterministic pipelines for steps that must not fail, and an LLM agent for dynamic decisions and context retrieval.

It supports 10+ programming languages with built-in rules for common defects: null pointer exceptions, thread-safety issues, XSS, and SQL injection. Comments are precise at the line level with accurate positioning.

It uses only 1/9 the tokens of general-purpose agents like Claude Code, with higher precision. Available as agent skills for Claude Code, Codex, Cursor, and Kimi Code.

AI-assisted draft, human-reviewed before publishing — see how we choose & review tools.

Why we picked it

Code review from Alibaba, battle-tested at massive scale. The hybrid architecture is smart: deterministic where it must be right, AI where it helps. 53k stars.