A CLI tool for generating editable commit messages with local AI models
Project description
AutoCommitt is a lightweight CLI tool that automatically generates meaningful commit messages using small, efficient AI models locally. It 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
- Resource Efficient: Minimal RAM and CPU usage with optimized model size
- Privacy-First: All operations performed locally, ensuring data privacy
- Flexible Editing: Review and edit generated messages before committing
- Git Integration: Seamlessly works with your existing Git workflow
🚀 Coming Soon
- Git hooks integration: Compatible with all pre-commit hooks
- Cross-Platform: Support for Windows, macOS, and Linux
🛠️ Installation
Prerequisites
- Python 3.8 or higher
- Git installed and configured
- Ollama installed locally
- Minimum 8GB RAM
Steps
-
Clone the Repository
git clone https://github.com/yourusername/AutoCommit.git cd AutoCommit
-
Install Dependencies
pip install -r requirements.txt
-
Verify Installation
python -m autocommitt --version
📖 Usage
python main.py
🤝 Contributing
We welcome contributions! Here's how you can help:
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature
) - Commit your changes (
git commit -m 'Add amazing feature'
) - Push to the branch (
git push origin feature/amazing-feature
) - Open a Pull Request
Please read our Contributing Guidelines for more details.
📊 Project Status
Current Version: 0.1.0 (Alpha)
- 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.
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-0.1.4.tar.gz
.
File metadata
- Download URL: autocommitt-0.1.4.tar.gz
- Upload date:
- Size: 8.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/5.1.1 CPython/3.12.7
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | a555369d6b3db3d0136de23b89e2a07e3e3fb3879c4dba65c01d49b908cdfb15 |
|
MD5 | 7c197594243eefdb2c2831a7d21fd107 |
|
BLAKE2b-256 | d326d4168430c57e4dcf5eb6bf70551ff03e74b132f9bb9c25d7e0b2cc0a05bc |
Provenance
The following attestation bundles were made for autocommitt-0.1.4.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-0.1.4.tar.gz
- Subject digest:
a555369d6b3db3d0136de23b89e2a07e3e3fb3879c4dba65c01d49b908cdfb15
- Sigstore transparency entry: 149970766
- Sigstore integration time:
- Predicate type:
File details
Details for the file autocommitt-0.1.4-py3-none-any.whl
.
File metadata
- Download URL: autocommitt-0.1.4-py3-none-any.whl
- Upload date:
- Size: 9.0 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 | d8ab6a45a54b311998de45e9bc1fc41f9fe3b6255b84deba6c5f5aa923ad2a65 |
|
MD5 | 7cfa2cd4ba1e869473ed5b2e851a852f |
|
BLAKE2b-256 | ce2497c93d1e13ff29e6383d848e93e64d5ac5a07685dfefc0cd09fed0229a5b |
Provenance
The following attestation bundles were made for autocommitt-0.1.4-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-0.1.4-py3-none-any.whl
- Subject digest:
d8ab6a45a54b311998de45e9bc1fc41f9fe3b6255b84deba6c5f5aa923ad2a65
- Sigstore transparency entry: 149970768
- Sigstore integration time:
- Predicate type: