Version updated for https://github.com/wanghenan/codereview-agent to version v1.

• This action is used across all versions by ? repositories.

Action Type

This is a Composite action.

Go to the GitHub Marketplace to find the latest changes.

Action Summary

The “CodeReview Agent” is an AI-powered GitHub Action that automates the code review process by identifying security risks, such as vulnerabilities, SQL injections, and hardcoded keys, in pull requests. It provides automated risk assessments with confidence scores and integrates with multiple large language model (LLM) providers for enhanced analysis. This tool streamlines code auditing, reducing the need for manual reviews while ensuring code quality and security.

Release notes

CodeReview Agent

🤖 AI 驱动的 CodeReview 智能体，帮助程序员自动识别哪些代码可提交、哪些需要人工审核。

✨ 特性

• 🔍 智能风险识别 - 自动检测安全漏洞、SQL注入、硬编码密钥等问题
• 📊 置信度评分 - 基于问题严重程度计算 0-100% 置信度
• 🤖 基于 LangChain + LangGraph - 模块化、易扩展
• 🌐 6 大 LLM Provider - OpenAI、Anthropic、智谱AI、MiniMax、阿里云、DeepSeek
• 🚀 三种使用方式 - GitHub Action / Docker / CLI

• wanghenan
• GitHub Actions