Skip to main content

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

PyPI version Python License: MIT Development Status

Haconiwa (箱庭) is an AI collaborative development support Python CLI tool. This next-generation tool integrates tmux company 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.

🇯🇵 日本語版 README

📋 Version Management

This project follows Semantic Versioning.

  • 📄 Changelog: CHANGELOG.md - All version change history
  • 🏷️ Latest Version: 0.2.0
  • 📦 PyPI: haconiwa
  • 🔖 GitHub Releases: Releases

🚀 Ready-to-Use Features

tmux Multi-Agent Environment (Implemented)

Create and manage a 4x4 grid multi-agent development environment right now:

# 1. Installation
pip install haconiwa

# 2. Create multi-agent environment (4 organizations × 4 roles = 16 panes)
haconiwa company multiagent --name my-project \
  --base-path /path/to/desks \
  --org01-name "Frontend Development" --task01 "UI Design" \
  --org02-name "Backend Development" --task02 "API Development" \
  --org03-name "Database Team" --task03 "Schema Design" \
  --org04-name "DevOps Team" --task04 "Infrastructure"

# 3. List companies
haconiwa company list

# 4. Attach to existing company
haconiwa company attach my-project

# 5. Update company settings (rename existing company)
haconiwa company multiagent --name my-project \
  --base-path /path/to/desks \
  --org01-name "New Frontend Team" --task01 "React Development" \
  --no-attach

# 6. Terminate company
haconiwa company kill my-project

📁 Auto-created Directory Structure:

/path/to/desks/
├── org-01/
│   ├── 01boss/          # PM desk
│   ├── 01worker-a/      # Worker-A desk
│   ├── 01worker-b/      # Worker-B desk
│   └── 01worker-c/      # Worker-C desk
├── org-02/
│   ├── 02boss/
│   ├── 02worker-a/
│   ├── 02worker-b/
│   └── 02worker-c/
├── org-03/ (same structure)
└── org-04/ (same structure)

✅ Actually Working Features:

  • 🏢 Multi-Agent Environment: 4x4 (16 panes) organizational tmux layout
  • 🏗️ Auto Directory Structure: Automatic desk creation by organization/role
  • 🏷️ Custom Organization & Task Names: Dynamic title configuration
  • 🔄 Company Updates: Safe configuration changes for existing companies
  • 🏛️ Company Management: Complete support for create/list/attach/delete
  • 📄 Auto README Generation: Automatic README.md creation in each desk

✨ Key Features (In Development)

  • 🤖 AI Agent Management: Create and monitor Boss/Worker agents
  • 📦 World Management: Build and manage development environments
  • 🖥️ tmux Company 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

🏗️ Architecture Concepts

tmux ↔ Haconiwa Concept Mapping

tmux Concept Haconiwa Concept Description
Session Company Top-level management unit representing entire project
Window Room Functional work areas for specific roles and functions
Pane Desk Individual workspaces for concrete task execution

Logical Hierarchy Management

Company
├── Building         ← Logical management layer (tmux-independent)
│   └── Floor        ← Logical management layer (tmux-independent)
│       └── Room     ← tmux Window
│           └── Desk ← tmux Pane

Logical Management Layer Features:

  • Building: Major project categories (Frontend Building, Backend Building, etc.)
  • Floor: Functional classifications (Development Floor, Testing Floor, Deploy Floor, etc.)
  • These layers are managed logically within haconiwa without direct tmux company mapping

Organization Structure Model

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

haconiwa-0.2.0.tar.gz (33.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

haconiwa-0.2.0-py3-none-any.whl (40.6 kB view details)

Uploaded Python 3

File details

Details for the file haconiwa-0.2.0.tar.gz.

File metadata

  • Download URL: haconiwa-0.2.0.tar.gz
  • Upload date:
  • Size: 33.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.11.5

File hashes

Hashes for haconiwa-0.2.0.tar.gz
Algorithm Hash digest
SHA256 b8cba717372fc3729bfefc360ae3ca4f3f943821ff024cf4c94b48215ef73b9c
MD5 b22202362eb31d050b2805ef872c0948
BLAKE2b-256 1377a2cbfc54bb2f59f64eaf3af850f0534ef67e8d0e61e3790e9819f77b650c

See more details on using hashes here.

File details

Details for the file haconiwa-0.2.0-py3-none-any.whl.

File metadata

  • Download URL: haconiwa-0.2.0-py3-none-any.whl
  • Upload date:
  • Size: 40.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.11.5

File hashes

Hashes for haconiwa-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 fc8dd1bdd640767d955d0ca8a1a5bdf0e460e37c8834d9639c57e8c70e1dfaee
MD5 7795e026178180532d259adc4198c057
BLAKE2b-256 bcceedb6895d3569ae0d59b0b4eb7d01dca766c057018b523372c5c608aed837

See more details on using hashes here.

Supported by

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