Skip to main content

A tool for streamlined commit messaging using AI

Project description

Cactus: AI-Powered Commit Message Generator

Cactus is an innovative command-line tool that leverages AI to automate and enhance the process of creating Git commit messages. By analyzing staged changes, Cactus generates meaningful, conventional commit messages, streamlining your version control workflow.

Demo

Demo

Features

  • AI-Powered Commit Generation: Utilizes OpenAI's GPT models or Google's Gemini models to analyze code changes and generate appropriate commit messages.
  • Customizable Commit Grouping: Allows specifying the number of commits to generate, intelligently grouping related changes.
  • Interactive Changelog Creation: Generates comprehensive changelogs between specified Git commits.
  • Multi-Model Support: Compatible with various AI models, including GPT-3.5, GPT-4, and Gemini.
  • Conventional Commits: Adheres to the Conventional Commits standard for consistent, readable commit histories.

Installation

Install Cactus using pip:

$ pip install cactus-commit

Set up your API key(s):

$ cactus setup OpenAI  # For OpenAI API
# or
$ cactus setup Gemini  # For Google Gemini API

Usage

Generate Commit Messages

Add the files you want to create commits for to the staging area:

$ git add myfile1.py myfile2.py

Anything left unstaged will be ignored when generating commit messages.

Run cactus to generate commit messages:

$ cactus

If you want to force a specific number of commits, pass the number as an argument:

cactus 3 # Will generate 3 commits

Create a Changelog

cactus changelog [SHA] [-p PATHSPEC]
  • SHA: The starting commit hash for the changelog.

Additional Options

  • -d, --debug: Enable debug logging.
  • -c, --context-size: Set the context size for git diff (default: 1).
  • -m, --model: Specify the AI model to use (e.g., "gpt-4", "gemini-1.5-pro").

How It Works

  1. Cactus analyzes staged Git changes.
  2. It uses AI to understand the context and significance of the changes.
  3. Based on the analysis, it generates commit messages or changelogs.
  4. Users can interactively accept, regenerate, or adjust the number of commits.

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

cactus_commit-4.2.0.tar.gz (16.7 kB view details)

Uploaded Source

Built Distribution

cactus_commit-4.2.0-py3-none-any.whl (18.1 kB view details)

Uploaded Python 3

File details

Details for the file cactus_commit-4.2.0.tar.gz.

File metadata

  • Download URL: cactus_commit-4.2.0.tar.gz
  • Upload date:
  • Size: 16.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.6

File hashes

Hashes for cactus_commit-4.2.0.tar.gz
Algorithm Hash digest
SHA256 64c046a333eb03c8843152ecc8837bc66c22d69023d1ad27cc87dffbba1a49b3
MD5 ad96f25f4237a0949b8786a2ef0509f7
BLAKE2b-256 0933b5db86010ff52d01b7ac74d62ee69aa6c7c37ee0ed46ccc1145976c96f5e

See more details on using hashes here.

File details

Details for the file cactus_commit-4.2.0-py3-none-any.whl.

File metadata

File hashes

Hashes for cactus_commit-4.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 175116e67dfa8eb950775371797538074e072cacbb02115b75c913aac58b091a
MD5 31f69bccc295a107833feb3aa8d564a2
BLAKE2b-256 fe65cbb54474a94d2ad5978fd37f38b91d44fe437055d9876b02f4e5126fbd93

See more details on using hashes here.

Supported by

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