sunmh207/AI-Codereview-Gitlab

基于大模型(DeepSeek,OpenAI等)的 GitLab 自动代码审查工具；支持钉钉/企业微信/飞书推送消息和生成日报；支持Docker部署；可视化 Dashboard。

What it solves

This project provides an automated AI-powered code review system for development teams. It eliminates the manual effort of initial code audits by automatically analyzing Merge Requests and commits in GitLab, ensuring higher code quality and faster feedback loops.

How it works

The system integrates with GitLab via webhooks. When a developer pushes code or creates a Merge Request, GitLab triggers the system's API. The tool then uses a Large Language Model (LLM) to analyze the code changes (diffs) and posts the review results directly back to the GitLab Merge Request or commit notes. It supports multiple LLM providers (DeepSeek, OpenAI, Anthropic, etc.) and can send notifications to DingTalk, Lark, or WeChat Work.

Who it’s for

Development teams using GitLab, GitHub, or Gitea who want to automate their code review process and integrate AI-driven feedback into their existing CI/CD workflow.

Highlights

  • Agentic Review Mode: An optional advanced mode where the LLM can use tools like read_file and a sandboxed shell to explore the codebase locally for more comprehensive reviews.
  • Customizable Review Styles: Offers multiple personas for feedback, including Professional, Sarcastic, Gentleman, and Humorous.
  • Multi-Model Support: Compatible with a wide range of providers including DeepSeek, ZhipuAI, OpenAI, Anthropic, and Ollama.
  • Integrated Dashboard: A visualization tool to track review records, project statistics, and developer performance.
  • Automated Daily Reports: Generates daily development progress reports based on commit history.

Related

  • Project
    Nikita-Filonov/ai-review

    An AI-powered code review tool that integrates into CI/CD pipelines to provide inline comments, summaries, and context-aware feedback using various LLM providers.

  • Project
    The-PR-Agent/pr-agent

    PR‑Agent is an open‑source AI bot that automatically reviews pull‑requests (or issues) using LLMs. It can summarize changes, give a full code‑review, suggest improvements, or answer free‑form questions. The tool works with GitHub, GitLab, Bitbucket, Azure DevOps, and Gitea, and can be run as a GitHub Action, Docker container, or local CLI. Prompts are fully configurable, and it supports many LLM providers via LiteLLM. Self‑hosting keeps data private, and the project is community‑maintained with sponsorship from Qodo.

  • Project
    hustcer/deepseek-review

    An automated code review tool that uses DeepSeek AI to analyze GitHub Pull Requests and local Git changes for bugs and security issues.

  • Project
    Nayjest/Gito

    An open-source AI code reviewer that provides instant feedback on pull requests and local changes using any LLM provider.

  • Project
    alibaba/open-code-review

    An AI-powered code review CLI tool that combines deterministic engineering with an AI agent to provide high-precision, token-efficient reviews of Git diffs and full files.