di-sukharev/opencommit
Opencommit
Opencommit is a command-line tool and automation suite that uses large language models to analyze staged changes and generate descriptive git commit messages. It functions as an AI-driven commit generator that can be integrated directly into the version control lifecycle.
The project distinguishes itself through support for both cloud-based AI providers and locally hosted models to ensure data privacy. It provides specialized automation via git hooks for real-time suggestions and GitHub Actions for refining commit messages during continuous integration workflows.
The tool includes capabilities for enforcing conventional commit standards, custom linting patterns, and language locale support. It features a configuration system for managing prompt templates and file analysis filters to exclude specific data from being processed by the model.
Features
- Commit Message Generators - Uses large language models to analyze staged changes and automatically generate descriptive git commit messages.
- AI Provider Integrations - Implements configuration interfaces to connect to various external or local large language model providers.
- Local Model Integrations - Integrates with locally hosted models to generate commit messages without requiring external network calls.
- Git History Generators - Uses locally hosted models via Ollama to generate version control history while maintaining data privacy.
- Commit Standards - Supports defining message formats based on conventional commit standards, linting specifications, and emoji patterns.
- AI-Driven Hooks - Integrates AI-powered message generation directly into the version control lifecycle via pre-commit hooks.
- Staged Change Extraction - Extracts raw git diffs of staged modifications to provide the necessary context for AI commit message generation.
- Prompt Templates - Uses customizable placeholders and style presets to format the input sent to the language model.
- Provider Abstraction Layers - Implements internal interfaces that standardize requests and responses across different cloud and local AI model providers.
- Runtime Provider Switching - Allows dynamic switching between different AI model providers and generation engines via a centralized configuration.
- Automated Commit Workflows - Provides a command line interface to bypass manual confirmation and commit generated messages immediately.
- CI/CD Workflow Integrations - Provides a GitHub Action to automatically refine and improve commit messages during the push process.
- Git Hook Managers - Provides a mechanism to install the tool as a git hook for automatic message suggestions.
- Git Hooks - Integrates generation logic directly into the version control lifecycle via client-side pre-commit hooks.
- Prompt Templates - A formatting system using custom placeholders and patterns to ensure generated messages follow project naming conventions.
- GitHub Actions - Implements a continuous integration workflow to intercept pushes and improve commit messages via GitHub Actions.
- 命令行界面 - Auto-generates git commit messages via CLI.
- Programming Tools - Git commit message generator using AI analysis.
