A CLI tool for generating editable commit messages with local AI models
Project description
A lightweight CLI tool that automatically generates meaningful commit messages using small, efficient AI models locally. AutoCommitt leverages Ollama's Llama model (3B parameters) to create concise, context-aware commit messages while keeping resource usage minimal.
✨ Features
- Local AI-Powered: Generates commit messages using a small 3B parameter model
- Flexible Editing: Review and edit generated messages before committing
- Privacy-First: All operations performed locally, ensuring data privacy
- Git Integration: Seamlessly works with your existing Git workflow
🚀 Quick Start
Prerequisites
- Python 3.8 or higher
- Git installed and configured
- Ollama installed locally
- Minimum 8GB RAM
Installation
pip install autocommitt
Usage
Just three simple steps:
-
Stage your files:
git add your_file_name
-
Generate and edit commit message:
ac
This will generate a commit message based on your changes. Edit it if needed.
-
Press Enter to commit your changes.
That's it! 🎉
🔜 Coming Soon
- Git hooks integration: Compatible with all pre-commit hooks
- Cross-Platform: Enhanced support for Windows, macOS, and Linux
- Custom Templates: Support for user-defined commit message templates
- Interactive Mode: Enhanced CLI interface for better user experience
🐛 Need Help?
- Found a bug? Open an issue
- Have questions? Check our discussions
- Want to contribute? Check out our Contributing Guidelines
📊 Project Status
- Basic commit message generation
- Local AI model integration (3B parameters)
- Python package release
- Cross-platform testing
- Interactive mode
- Custom template support
📄 License
Licensed under the Apache License 2.0 - see the LICENSE file for details.
👩💻 For Developers
Interested in contributing to AutoCommitt? We'd love your help! Check out our Contributing Guidelines for:
- Setting up the development environment
- Building from source
- Pull request process
- Development roadmap
- Code style guidelines
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file autocommitt-0.1.6.tar.gz
.
File metadata
- Download URL: autocommitt-0.1.6.tar.gz
- Upload date:
- Size: 10.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/5.1.1 CPython/3.12.7
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 824cb4cd80225a3632967afda6d63e83a44b4479f2bbef72e72dd3ba0c39fe64 |
|
MD5 | 9a8a1a5d8c02810dfd409c2497a77e7d |
|
BLAKE2b-256 | 5d58523caad61107a3d9f7933aa42deefd0985a9133018ab8af54d48ed7c0d52 |
Provenance
The following attestation bundles were made for autocommitt-0.1.6.tar.gz
:
Publisher:
release.yaml
on Spartan-71/AutoCommitt
-
Statement type:
https://in-toto.io/Statement/v1
- Predicate type:
https://docs.pypi.org/attestations/publish/v1
- Subject name:
autocommitt-0.1.6.tar.gz
- Subject digest:
824cb4cd80225a3632967afda6d63e83a44b4479f2bbef72e72dd3ba0c39fe64
- Sigstore transparency entry: 150462149
- Sigstore integration time:
- Predicate type:
File details
Details for the file autocommitt-0.1.6-py3-none-any.whl
.
File metadata
- Download URL: autocommitt-0.1.6-py3-none-any.whl
- Upload date:
- Size: 10.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/5.1.1 CPython/3.12.7
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 3ca582d19d795ec3c049ffe6e5bad4d633026afe5d6a9d7a05248fdd7485dfa8 |
|
MD5 | c35b62cb72b6e4ea0dcb227131713366 |
|
BLAKE2b-256 | 7035f5736054232f2aa357f33345172f37f48de47e0d574cbcd54b41d0f422a8 |
Provenance
The following attestation bundles were made for autocommitt-0.1.6-py3-none-any.whl
:
Publisher:
release.yaml
on Spartan-71/AutoCommitt
-
Statement type:
https://in-toto.io/Statement/v1
- Predicate type:
https://docs.pypi.org/attestations/publish/v1
- Subject name:
autocommitt-0.1.6-py3-none-any.whl
- Subject digest:
3ca582d19d795ec3c049ffe6e5bad4d633026afe5d6a9d7a05248fdd7485dfa8
- Sigstore transparency entry: 150462150
- Sigstore integration time:
- Predicate type: