alibaba/open-code-review

#9dailyJul 28, 2026OpenAI

Open on GitHub

Summary

alibaba/open-code-review — Hybrid LLM-driven code review (Go)

The generated summary body for the selected provider.

OpenAImodel: gpt-5-mini

Highlights

1Hybrid deterministic pipelines + LLM Agent
2Built-in rules for NPE, thread-safety, XSS, SQL injection
3Precise line-level comments; OpenAI & Anthropic compatible

go code-review llm security ci static-analysis agent

Overview

alibaba/open-code-review is an open-source, battle-tested code review platform implemented in Go that combines deterministic pipelines with an LLM Agent. The project produces precise line-level comments and ships a built-in fine-tuned ruleset covering specific issues such as NPE (null-pointer exceptions), thread-safety, XSS, and SQL injection. It is explicitly compatible with OpenAI and Anthropic models and is designed for large-scale use (battle-tested at Alibaba's scale).

Translation

Translated body generated separately from the summary.

No translation available yet.

README

Captured original README content.

Open-source & free — Battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in fine-tuned ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.

This repository is trending now (ranked #9, +979 stars today) because it pairs deterministic review pipelines with an LLM Agent to give actionable, line-specific feedback while also providing a curated ruleset for common security and concurrency issues. The combination of battle-tested scalability, concrete rule coverage (NPE, thread-safety, XSS, SQL injection), and OpenAI/Anthropic compatibility makes it attractive for teams looking to integrate LLM-driven reviews into enterprise CI workflows.

Who it's for

Why It Matters

Quick facts