Haconiwa is a Python CLI tool designed to support AI collaborative development by integrating tmux session management, Git worktree integration, and AI agent coordination. It aims to provide an efficient, structured development environment for teams working with AI agents, currently targeting developers and researchers.

How It Works

Haconiwa utilizes a CRD (Custom Resource Definition) based architecture, defining organizational structures, development spaces, and tasks in YAML files. It maps these definitions to tmux sessions and windows, creating isolated development environments for each task using Git worktrees. AI agents are then spawned within these environments, with planned features for role-specific prompts and permission controls.

Quick Start & Requirements

• Install: pip install haconiwa --upgrade
• Prerequisites: Python 3.8+, tmux, Anthropic Claude Code setup (API key required).
• Setup: Clone the repository and install with pip install -e .[dev].
• Docs: https://github.com/dai-motoki/haconiwa

Highlighted Details

• Declarative environment management via YAML configuration.
• Task isolation using Git worktrees, branching from a specified defaultBranch.
• Hierarchical structure mapping (Nation > City > Village > Company > Room) to tmux sessions/windows.
• AI model search and analysis capabilities via the scan command.
• Planned "Law CRD" for hierarchical rule inheritance and permission management.

Maintenance & Community

The project is under active development, with recent updates focusing on task branch fixes and CRD inheritance. Community support is available via GitHub Issues and email.

Licensing & Compatibility

The project is released under the MIT License, permitting commercial use and integration with closed-source projects.

Limitations & Caveats

Haconiwa is in early alpha and demonstration phase. Most CLI commands are placeholders, and core functionality is under active development. Production use is not recommended. Features and APIs are subject to frequent changes.