lumen  by jnsahaj

CLI tool for AI-powered Git commit messages and change explanations

created 9 months ago
895 stars

Top 41.3% on sourcepulse

GitHubView on GitHub
Project Summary

Lumen is a command-line tool designed to enhance Git workflows by leveraging AI for tasks like generating commit messages and explaining code changes. It targets developers seeking to streamline their version control processes without the need for API keys, offering a zero-configuration experience with Phind as the default AI provider.

How It Works

Lumen integrates with local Git repositories and communicates with various AI providers, including Phind, Groq, OpenAI, Claude, Ollama, OpenRouter, and DeepSeek. It analyzes staged changes, commit history, or specified diffs to generate human-readable summaries, conventional commit messages, or even Git commands based on natural language prompts. The tool prioritizes user experience with features like interactive commit searching (via fzf) and rich, Markdown-formatted output (via mdcat).

Quick Start & Requirements

  • Install via Homebrew (brew install jnsahaj/lumen/lumen) or Cargo (cargo install lumen).
  • Prerequisites: git. Optional: fzf for lumen list, mdcat for pretty output.
  • Official Docs: https://github.com/jnsahaj/lumen

Highlighted Details

  • No API key required for default Phind provider.
  • Supports multiple AI providers and models, configurable via CLI, environment variables, or config files.
  • Generates conventional commit messages and Git commands from natural language.
  • Interactive commit search and change explanation capabilities.

Maintenance & Community

  • Project maintained by jnsahaj.
  • Community links not explicitly mentioned in the README.

Licensing & Compatibility

  • License not specified in the README.
  • Compatibility for commercial use or closed-source linking is not detailed.

Limitations & Caveats

The README does not specify the project's license, which is crucial for determining commercial use and compatibility with closed-source projects. The optional dependencies fzf and mdcat are required for certain features, meaning users may need to install additional tools for the full experience.

Health Check
Last commit

1 month ago

Responsiveness

1 day

Pull Requests (30d)
0
Issues (30d)
1
Star History
157 stars in the last 90 days

Explore Similar Projects

Starred by Chip Huyen Chip Huyen(Author of AI Engineering, Designing Machine Learning Systems), Jeff Hammerbacher Jeff Hammerbacher(Cofounder of Cloudera), and
3 more.

AutoPR by irgolic

0.1%
1k
AI-powered workflows for codebase automation
created 2 years ago
updated 1 year ago
Feedback? Help us improve.