agent-gitv1 0.1.2

AI-powered Git CLI using MCP + OpenAI, Gemini, or Ollama for commit workflows

agent-gitv1

AI-powered Git CLI that uses Model Context Protocol (MCP) plus your configured LLM provider to automate commit workflows.

Supported providers:

• Google Gemini
• OpenAI
• Ollama (local or same-network)

Features

• agent config to set provider and model
• agent commit to generate commit messages from git diff
• Multiple commit suggestions (--suggestions)
• History-aware commit message generation (uses recent commit subjects)
• Ollama model auto-detection on local network (/24, port 11434)
• agent push to push to remote

Prerequisites

• Python 3.10+
• uvx (pip install uv)
• Git
• Provider credentials (Gemini/OpenAI) or running Ollama server

Installation

cd "d:\Vijay Projects\Agent_bhai"
pip install -e .

After install, use command:

agent --help

Configuration

Start with:

agent config

Provider notes:

• Gemini: use GEMINI_API_KEY or save key in config
• OpenAI: use OPENAI_API_KEY or save key in config
• Ollama: can auto-detect servers like http://192.168.1.35:11434

Commands

agent --help

Shows all available commands and options.

agent config

Configure provider and model.

agent commit

Stage changes, generate suggestions, choose a message, and commit.

Examples:

agent commit
agent commit --repo /path/to/repo
agent commit --suggestions 3
agent commit --verbose

agent push

Push commits to remote.

Examples:

agent push
agent push --remote origin --branch main

Environment Variables

• GEMINI_API_KEY (Gemini)
• OPENAI_API_KEY (OpenAI)

Publish to PyPI

1. Bump version in pyproject.toml and agent.py
2. Build and validate:

python -m pip install --upgrade build twine
python -m build
python -m twine check dist/*

3. Upload:

python -m twine upload dist/*

Project Structure

Agent_bhai/
|- agent.py
|- pyproject.toml
|- README.md

License

MIT