Alibaba Open Sources OpenCodeReview for AI-Assisted Code Review
Alibaba recently open-sourced OpenCodeReview, an AI-powered code review CLI that combines deterministic pipelines for file selection, bundling, and rule matching with an LLM agent for dynamic code analysis. It supports built-in checks for issues such as null-pointer exceptions, thread safety, XSS, and SQL injection. By Renato Losio
Alibaba has open-sourced OpenCodeReview, an AI-powered code review CLI that combines deterministic pipelines with an LLM agent for dynamic code analysis. The project avoids using AI for deterministic tasks such as file selection, tool choice, and comment validation. It is written in Go and can review Git diffs, branches, or entire files using compatible models from OpenAI and Anthropic.
Alibaba claims it performs better than Claude Code while using roughly ninth the tokens, but an independent benchmark showed lower precision. The open-source project breaks the review process into stages, each with a different level of determinism. Early reactions focus on its architecture, particularly the decision to keep certain components deterministic.
OpenCodeReview can run locally or integrate with various platforms, promising to achieve 2.17 times the review quality at a fraction of the token cost.
Written by urgent.news from InfoQ's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
