open-code-review
An open-source code review tool that combines deterministic engineering with LLM agents to deliver precise line-level feedback.
- Type
- Agent Skill
- Open source
- Yes
- GitHub Stars
- ★ 9.3k
- Source
- skill-github
- Repository
- github.com/alibaba/open-code-review
Overview
Open Code Review is an AI-powered code review tool incubated within Alibaba Group. By integrating deterministic engineering with LLM agents, it provides accurate line-level code reviews. The tool reads Git diffs, sends changed files to a configurable LLM, and generates structured review comments. It comes with a finely tuned rule set (e.g., NPE, thread safety, XSS, SQL injection) and supports models from OpenAI and Anthropic. Ideal for developers and teams requiring high-quality code reviews.
Capabilities
- ▪Precise line-level code comments
- ▪Built-in fine-tuned rule set
- ▪Supports multiple programming languages
- ▪Low API cost
Use cases
Setup
npm install @alibaba-group/open-code-review
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How do I get started with Open Code Review?
After installation, configure the model endpoint and you can start using it immediately.
Which programming languages are supported?
Supports multiple programming languages, including Java, Python, and more.
Related skills
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
private-gpt
Provides a complete API layer for local models, supporting RAG, skills, tools, and more.
planning-with-files
File-based persistent planning skill, ideal for AI coding agents and long-running tasks.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.