gait is both an executable binary that can be run, and a library that can be used in Rust programs.
Installing git-changelog git-message git-pr git-release-notes git-wire executables
Assuming you have Rust/Cargo installed , run this command in a terminal:
cargo install gait
It will make git-changelog git-message git-pr git-release-notes git-wire commands available in your PATH if you've allowed the PATH to be modified when installing Rust . cargo uninstall gait uninstalls.
Adding gait library as a dependency
Run this command in a terminal, in your project's directory:
cargo add gait
To add it manually, edit your project's Cargo.toml file and add to the [dependencies] section:
gait = "0.1.3"
The gait library will be automatically available globally.
Read the gait library documentation .
Back to the crate overview .
Readme
Git workflow
AI-powered Git toolkit that enhances workflow with intelligent commit messages, pull request generation, code reviews, changelogs, and more. It integrates with various LLM providers to automate and improve your development process.
Features
Smart Commit Messages : Generate meaningful commit messages based on your code changes
Commit Message Completion : Complete partially typed commit messages with AI assistance
History-Aware Generation : Use commit history for personalized and contextually appropriate messages
Pull Request Generation : Automatically create detailed PR descriptions with context
Changelogs : Generate release notes and changelogs from commit history
Multiple LLM Support : Works with OpenAI, Anthropic, Google, and other providers
Git Config Integration : Store configurations in Git config for project-specific settings
Wire Protocol Support : Efficient caching and synchronization for remote repositories
Research & Evaluation Tools : Built-in evaluation framework for commit message generation research
Research Features
This toolkit implements features from the paper "From Commit Message Generation to History-Aware Commit Message Completion" :
Commit Message Completion : Complete messages with configurable context ratios (0%, 25%, 50%)
History Integration : Incorporate author commit history for personalization
Evaluation Metrics : B-Norm, Edit Similarity, and Exact Match metrics
Dataset Filtering : Apply restrictive filters as used in previous CMG research
Batch Evaluation : Run comprehensive experiments comparing different approaches
License
Licensed under the MIT License. See LICENSE.md for details.