OpenSource-Hub
O

open-code-review

SHA-256
11.8k stars·Developer Tools·SHA-256 checksum verified

AI code review CLI combining deterministic pipelines with LLM agents. Proven at Alibaba scale, provides precise line-level comments, built-in security rules, and supports OpenAI/Anthropic.

Smart Download

Download Download Version

v1.7.15 · 43.9 MB

Alibaba's battle-tested AI code review CLI with hybrid pipelines, low token cost, and high precision.

Core Features

  • Hybrid architecture: deterministic pipelines handle file selection and rule matching, LLM agent handles dynamic decisions and context retrieval
  • Precise line-level comments with external positioning and reflection modules
  • ~1/9 token consumption compared to generic agents, higher F1 score on benchmarks
  • Built-in fine-tuned rules for NPE, thread-safety, XSS, SQL injection
  • Multiple review modes: diff review, full-file scan, delegation mode

What It Can't Do

  • Requires a valid LLM API key (e.g., OpenAI, Anthropic); not suitable for fully offline environments. Reviewing large codebases may incur token costs. Git >= 2.41 is required, and the tool is primarily designed for projects with Git history (except full-file scan mode).

Use Cases

  • Automated PR review in CI/CD pipelines to reduce human review burden
  • Pre-commit local scanning to catch defects and security vulnerabilities

Detailed Introduction

Open Code Review is an AI-powered code review CLI tool developed by Alibaba Group. After two years of internal use serving tens of thousands of developers and catching millions of defects, it has been open-sourced. Unlike generic LLM agents like Claude Code that suffer from incomplete coverage and position drift, Open Code Review uses a hybrid architecture: deterministic pipelines (file selection, smart bundling, rule matching, external positioning) guarantee correctness, while an LLM agent handles dynamic decisions and context retrieval. The result is higher precision, lower false positives, and ~1/9 the token consumption. It supports Git diff review, full-file scan, and delegation mode for custom AI agents. Built-in rules target common vulnerabilities (NPE, thread-safety, XSS, SQL injection), and it works with OpenAI, Anthropic, and compatible providers.

Tags

code-reviewAILLMdeveloper-toolsstatic-analysis

Getting Started

1

Download installer

Click the button above to download the installer for your system

2

Install the software

Double-click the downloaded installer and follow the prompts

3

Install globally: npm install -g @alibaba-group/open-code-review

4

Configure LLM: run 'ocr config provider' to select a provider and enter API key, then 'ocr config model' to choose a model

5

Review code: run 'ocr review' in a Git repository and view line-level comments

Install Guide
  1. Install globally: npm install -g @alibaba-group/open-code-review
  2. Configure LLM: run 'ocr config provider' to select a provider and enter API key, then 'ocr config model' to choose a model
  3. Review code: run 'ocr review' in a Git repository and view line-level comments
File Integrity

SHA-256 checksum verified

Checksum extracted from GitHub official Release page

SHA256 Checksum

6a3009b2d6148ec228e4c7706714a7c56ba3a550227e03ac68a2e71be173789d

This checksum is extracted from the GitHub Release page. Verify file integrity after download.

All SHA-256 checksums on this platform are extracted from the project's official GitHub Release page, without any modification. You can independently verify them on the GitHub Releases page.

Open Source Transparency

View GitHub Source
Environment Guide

Uninstall Info

Run 'npm uninstall -g @alibaba-group/open-code-review' to remove the tool globally.

No Extra Dependencies

Ready to use after download. No additional runtime required.

Project Info
LicenseApache-2.0
Last Updated2026-07-24T05:30:40Z
GitHub RepositoryOfficial Website

Similar Projects