CodeGPT  by appleboy

CLI tool for commit messages/code reviews using ChatGPT

created 2 years ago
1,444 stars

Top 28.9% on sourcepulse

GitHubView on GitHub
Project Summary

CodeGPT is a Go-based CLI tool designed to automate the generation of Git commit messages and code review summaries using AI models like GPT-4o. It targets developers seeking to streamline their Git workflow and improve commit message quality, offering integration with Git hooks for seamless operation.

How It Works

CodeGPT leverages large language models (LLMs) to process code diffs and generate human-readable summaries. It supports various AI providers including OpenAI, Azure OpenAI, Gemini, Anthropic, Groq, and Ollama, allowing users to choose their preferred backend. The tool can be configured to adhere to conventional commit specifications, customize prompt templates, and control the context lines included in diff analysis.

Quick Start & Requirements

  • Install via Homebrew (brew install codegpt), Chocolatey (choco install codegpt), or download pre-compiled binaries.
  • Source installation requires Go.
  • Configuration involves setting API keys and optionally configuring proxy settings or custom prompt folders.
  • Official documentation: https://github.com/appleboy/CodeGPT

Highlighted Details

  • Supports multiple AI providers: OpenAI, Azure OpenAI, Gemini, Anthropic, Groq, Ollama, OpenRouter.
  • Integrates with Git prepare-commit-msg hook for automatic commit message generation.
  • Customizable commit message templates and prompt variables.
  • Supports conventional commits specification.
  • Can generate code review summaries.
  • Offers translation of commit messages and reviews into multiple languages.

Maintenance & Community

The project is actively maintained by appleboy. Community support channels are not explicitly mentioned in the README.

Licensing & Compatibility

The project is released under the MIT License, permitting commercial use and integration with closed-source projects.

Limitations & Caveats

The README does not detail specific performance benchmarks or known limitations regarding model accuracy or handling of very large codebases. Users must manage their own API keys and associated costs for the AI services used.

Health Check
Last commit

20 hours ago

Responsiveness

Inactive

Pull Requests (30d)
0
Issues (30d)
0
Star History
63 stars in the last 90 days

Explore Similar Projects

Feedback? Help us improve.