AI協調開発支援Python CLIツール - 箱庭での開発を支援
Project description
Haconiwa (箱庭) 🚧 Under Development
Haconiwa (箱庭) is an AI collaborative development support Python CLI tool. This next-generation tool integrates tmux session management, git-worktree integration, task management, and AI agent coordination to provide an efficient development environment.
⚠️ Note: This project is currently under active development. Features and APIs may change frequently.
✨ Key Features (In Development)
- 🤖 AI Agent Management: Create and monitor Boss/Worker agents
- 📦 World Management: Build and manage development environments
- 🖥️ tmux Session Integration: Efficient development space management
- 📋 Task Management: Task management system integrated with git-worktree
- 📊 Resource Management: Efficient scanning of databases and file paths
- 👁️ Real-time Monitoring: Progress monitoring of agents and tasks
🚀 Installation
pip install haconiwa
📝 Development Note: The package is available on PyPI but many features are still in development.
⚡ Quick Start
🎭 Important: All commands shown below are demonstration purposes only. These commands currently display help information and basic structure, but the actual functionality is under development. We are actively working on implementing the full features.
1. View Available Commands
haconiwa --help
2. Initialize Project
haconiwa core init
3. Create Development World
haconiwa world create local-dev
4. Launch AI Agents
# Create boss agent
haconiwa agent spawn boss
# Create worker agent
haconiwa agent spawn worker-a
5. Task Management
# Create new task
haconiwa task new feature-login
# Assign task to agent
haconiwa task assign feature-login worker-a
# Monitor progress
haconiwa watch tail worker-a
📖 Command Reference
🔧 Development Note: The commands listed below are currently for demonstration and testing purposes. While the CLI structure is functional, most commands will show help information or placeholder responses. We are actively developing the underlying functionality for each command group.
The CLI tool provides 7 main command groups:
agent - Agent Management Commands
Manage AI agents (Boss/Worker) for collaborative development
haconiwa agent spawn <type>- Create agenthaconiwa agent ps- List agentshaconiwa agent kill <name>- Stop agent
core - Core Management Commands
Core system management and configuration
haconiwa core init- Initialize projecthaconiwa core status- Check system statushaconiwa core upgrade- Upgrade system
resource - Resource Management
Scan and manage project resources (databases, files, etc.)
haconiwa resource scan- Scan resourceshaconiwa resource list- List resources
space - Manage tmux Spaces and Sessions
Efficient development workspace management via tmux
haconiwa space create <name>- Create tmux sessionhaconiwa space list- List sessionshaconiwa space attach <name>- Attach to session
task - Task Management Commands
Task management integrated with git-worktree
haconiwa task new <name>- Create new taskhaconiwa task assign <task> <agent>- Assign taskhaconiwa task status- Check task status
watch - Monitoring Commands
Real-time monitoring of agents and tasks
haconiwa watch tail <target>- Real-time monitoringhaconiwa watch logs- View logs
world - World Management
Development environment and world management
haconiwa world create <name>- Create new development worldhaconiwa world list- List worldshaconiwa world switch <name>- Switch world
🛠️ Development Status
🎬 Current Phase: Demonstration & Prototyping
Most CLI commands are currently demonstration placeholders that show the intended structure and help information. We are actively developing the core functionality behind each command.
✅ Completed Features
- Basic CLI structure with 7 command groups
- PyPI package distribution and installation
- Core project initialization framework
- Help system and command documentation
- Command group organization and routing
🚧 In Development
- AI agent spawning and management (placeholder → real implementation)
- tmux session integration (placeholder → real implementation)
- Task management with git-worktree (placeholder → real implementation)
- Resource scanning functionality (placeholder → real implementation)
- Real-time monitoring system (placeholder → real implementation)
- World/environment management (placeholder → real implementation)
📋 Planned Features
- Advanced AI agent coordination
- Integration with popular development tools
- Plugin system for extensibility
- Web-based monitoring dashboard
🛠️ Development Environment Setup
git clone https://github.com/dai-motoki/haconiwa.git
cd haconiwa
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
pip install -e .[dev]
Running Tests
pytest tests/
📝 License
MIT License - see the LICENSE file for details.
🤝 Contributing
We welcome contributions to the project! Since this is an active development project, please:
- Check existing issues and discussions
- Fork this repository
- Create a feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Create a Pull Request
📞 Support
- GitHub Issues: Issues
- Email: kanri@kandaquantum.co.jp
⚠️ Disclaimer
This project is in early alpha development and demonstration phase. Current CLI commands are primarily placeholders showing the intended interface design. Most functionality is under active development and not yet implemented.
What works now:
- CLI installation and command structure
- Help system and documentation
- Basic command routing
What's coming:
- Full implementation of all advertised features
- AI agent coordination functionality
- Integration with development tools
- Real task and session management
Use in production environments is not recommended at this time. This is a development preview showcasing the intended user experience.
Haconiwa (箱庭) - The Future of AI-Collaborative Development 🚧
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file haconiwa-0.1.2.tar.gz.
File metadata
- Download URL: haconiwa-0.1.2.tar.gz
- Upload date:
- Size: 32.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.0.1 CPython/3.11.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
787a1aea2e675651747140bc7ffb1b91493727108f251a78e0eae897b6cf4474
|
|
| MD5 |
83694aafdb40585fc1c5fc92c4720214
|
|
| BLAKE2b-256 |
a842d2a732a8c724c1715b329f8ee883123982bc76afb7e574fdc993779d8abe
|
File details
Details for the file haconiwa-0.1.2-py3-none-any.whl.
File metadata
- Download URL: haconiwa-0.1.2-py3-none-any.whl
- Upload date:
- Size: 39.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.0.1 CPython/3.11.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ada18cb12c492d0c6e16060c49cc36fe5da11f74d9d2a9d434fd87d9cbbc9356
|
|
| MD5 |
31ab6b096b1e7be7f8f2aa5fd6415e82
|
|
| BLAKE2b-256 |
68c3ef5ebd9c08a8220a877170b56f5553007a7f38b4c2c21177dc561e80af60
|