Skip to main content

AI-powered git commit message generator

Project description

gitme-ai

AI-powered git commit message generator. Reads your staged changes and generates a well-formatted Conventional Commits message using a local or cloud LLM.

Local-first and privacy-friendly by default — your diffs never leave your machine unless you choose a cloud provider.


Requirements

  • Python 3.11 or higher
  • Git

Installation

pip install gitme-ai

Quick Start

Stage your changes as you normally would, then run gitme:

git add .
gitme

That's it. gitme reads your staged diff, sends it to the AI, and prints a suggested commit message in your terminal.

By default it uses Ollama with llama3.2 running locally. See Providers below to set up Ollama or switch to a cloud provider.


Usage

Basic

gitme

Copy to clipboard

gitme --copy

The message is printed to the terminal and copied to your clipboard. You can then paste it directly into git commit -m "...".

Add extra context

gitme --context "this is a hotfix for the login bug in production"

The context is appended to the prompt so the model has more information to work with. Useful when the diff alone doesn't tell the full story.


Providers

gitme supports three providers. You set your preferred one once and it applies to every future run.

Ollama (default — local, free, private)

Ollama runs models on your own machine. No API key needed, no data leaves your computer.

1. Install Ollama

Download from ollama.com and open the app. You'll see it in your menu bar when it's running.

2. Pull the model

ollama pull llama3.2

3. Run gitme

gitme

Ollama is already the default — nothing else to configure.

To use a different Ollama model:

gitme-config set model mistral

OpenAI (cloud, best quality)

Uses the OpenAI API. You need an API key and credit — gpt-4o-mini is cheap and works well for commit messages.

1. Set your API key

gitme-config set openai_api_key YOUR_API_KEY
gitme-config set provider openai
gitme-config set model gpt-4o-mini

2. Run gitme

gitme

Your API key is stored locally in ~/.gitme.toml and never shared.


OpenRouter (cloud, free tier available)

OpenRouter provides access to many models including free ones. No credit card required for the free tier.

Get a free API key at openrouter.ai.

1. Set your API key

gitme-config set openrouter_api_key YOUR_API_KEY
gitme-config set provider openrouter
gitme-config set model "nvidia/nemotron-3-nano-30b-a3b:free"

2. Run gitme

gitme

Configuration

Configuration is stored in ~/.gitme.toml and shared across all your projects.

View current config

gitme-config show

Output:

provider: ollama
model: llama3.2
style: conventional

Set a value

gitme-config set <key> <value>

Available keys:

Key Description Default
provider Which provider to use: ollama, openai, or openrouter ollama
model Model name for the active provider llama3.2
style Commit style (currently conventional) conventional
openai_api_key Your OpenAI API key
openrouter_api_key Your OpenRouter API key

Examples

# Switch to OpenAI
gitme-config set provider openai
gitme-config set model gpt-4o-mini
gitme-config set openai_api_key sk-...

# Switch back to Ollama
gitme-config set provider ollama
gitme-config set model llama3.2

Commit Format

gitme follows the Conventional Commits specification:

type(scope): short description

- optional body explaining why the change was made

Fixes #123  (optional footer)

Commit types:

Type When to use
feat New feature or capability
fix Bug fix
refactor Code restructured without changing behaviour
docs Documentation changes only
style Formatting or whitespace, no logic changes
test Adding or updating tests
chore Maintenance, config changes, dependency updates

License

MIT

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

gitme_ai-0.1.2.tar.gz (9.1 kB view details)

Uploaded Source

Built Distribution

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

gitme_ai-0.1.2-py3-none-any.whl (10.3 kB view details)

Uploaded Python 3

File details

Details for the file gitme_ai-0.1.2.tar.gz.

File metadata

  • Download URL: gitme_ai-0.1.2.tar.gz
  • Upload date:
  • Size: 9.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.2

File hashes

Hashes for gitme_ai-0.1.2.tar.gz
Algorithm Hash digest
SHA256 68a6b94912c1e1a5e0f0294cde55f440486aabe6baa938e0b9f768c840221bd9
MD5 2be0b7bdfd66dcb78b65fa4b54619ae0
BLAKE2b-256 38b38b50eeed1a9bac393cd1eda17b44a73f294e1ff1d2a4f66d6bf58961c52e

See more details on using hashes here.

File details

Details for the file gitme_ai-0.1.2-py3-none-any.whl.

File metadata

  • Download URL: gitme_ai-0.1.2-py3-none-any.whl
  • Upload date:
  • Size: 10.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.2

File hashes

Hashes for gitme_ai-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 566d8c50d0542f36eceed629422f6dee0915b5f934ac99f9fb99a5edcae95c90
MD5 21dafe59cc309b30efce67934fe2cc9f
BLAKE2b-256 bee30dc86db063903990d508c9b9f2db2d8ffc7f11ba04c3229dab96ed4e9d7d

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page