Skip to main content

🤖 auto_commit

Local-first Git Commit Message Generator powered by Ollama

auto_commit is a lightweight CLI tool that leverages local LLMs (via Ollama) to analyze your git diff and automatically generate high-quality commit messages following the Conventional Commits standard.

Since it runs entirely on your local machine, no API keys (such as OpenAI) are required. Your source code remains 100% private and never leaves your environment.


✨ Key Features

  • 🔒 100% Local & Private: Powered by local LLMs via Ollama. No code or data is sent to third-party servers.
  • 📝 Conventional Commits: Automatically outputs structured messages using standard prefixes like feat:, fix:, docs:, and refactor:.
  • Lightweight & Fast: Built using standard Python libraries with zero heavy external dependencies.
  • ✏️ Interactive CLI: Preview the AI-generated commit message and decide whether to accept (y), reject (n), or edit (e) it before committing.

📋 Prerequisites

To run this tool, you need Python and Ollama installed on your system:

  1. Python 3.8+
  2. Ollama: Download and install from ollama.com
  3. LLM Model: Pull a recommended lightweight model
    ollama pull qwen2.5:3b
    # or
    ollama pull llama3.2
    

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

auto_commit_ollama-0.1.0.tar.gz (3.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

auto_commit_ollama-0.1.0-py3-none-any.whl (4.5 kB view details)

Uploaded Python 3

File details

Details for the file auto_commit_ollama-0.1.0.tar.gz.

File metadata

  • Download URL: auto_commit_ollama-0.1.0.tar.gz
  • Upload date:
  • Size: 3.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.12.10

File hashes

Hashes for auto_commit_ollama-0.1.0.tar.gz
Algorithm Hash digest
SHA256 a0b4ca8c3f79542ff99ab0edb042b56eefd22fd24ecddbda1527e37fed57de38
MD5 d8132dd78c16f13b9d22392f8f87a959
BLAKE2b-256 fe9e1c504804de389ed42b23a512b1967180711f8f433d23ffbc40cf93f28a9d

See more details on using hashes here.

File details

Details for the file auto_commit_ollama-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for auto_commit_ollama-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 7403a50d4f0f64bd6f401611e5890d6d5d5b0aca95dd08eb973f0b68a1b47a31
MD5 307a74a01f6079bbffd4a6686e5036b8
BLAKE2b-256 a833f222dfc3388b2b7029e321c8dcbf634e9f66b8023761ccb9b4dd08be265e

See more details on using hashes here.

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page