craftxpy 0.1.2

Python-native intelligence, modular by design

CraftX.py

Python-native intelligence, modular by design.

CraftX.py is a modular AI scripting framework designed specifically for Python developers. It provides seamless integration with multiple AI models, secure automation tools, and an extensible plugin architecture.

🚀 Features

• 🤖 Multi-Model Support: Integrate WizardCoder, CommandR7B, CodeGeeX4, and Qwen2.5-Coder
• 🔧 Modular Tools: Extensible plugin system with built-in utilities
• 🛡️ Secure Execution: Safe shell commands with whitelist protection
• 💾 Memory System: Persistent conversation history and session management
• 🎨 Beautiful UI: Modern Streamlit-based interface
• 🐍 Python-Native: Clean APIs with type hints and pythonic design

📦 Installation

Quick Start

git clone https://github.com/davidanderson01/CraftX.py.git
cd CraftX.py
pip install -r requirements.txt

Development Installation

pip install -e .[dev]

🎯 Quick Start

1. Basic Usage

from craftxpy.agents.router import AgentRouter
from craftxpy.plugins.wizardcoder import WizardCoder

# Initialize AI model router
router = AgentRouter({"codegen": WizardCoder()})

# Generate code
response = router.route("codegen", "Create a FastAPI endpoint for user auth")
print(response)

2. Web Interface

streamlit run assistant_ui/app.py

3. Run Demo

python examples/demo.py

🏗️ Architecture

craftxpy/
├── agents/          # AI model routing and management
├── plugins/         # Model integrations and tools
│   ├── wizardcoder.py
│   ├── commandr7b.py
│   ├── codegeex4.py
│   ├── qwen25coder.py
│   └── tools/       # Extensible tool plugins
├── memory/          # Conversation logging and history
├── utils/           # Utilities (shell, page builder)
└── assistant_ui/    # Streamlit web interface

🔧 Built-in Tools

• 🌐 DNS Validator: Validate domain resolution
• 🔒 SSL Checker: Check certificate status and expiration
• 📁 File Monitor: Monitor OneDrive file hydration (Windows)
• 🛠️ Custom Tools: Easy plugin creation system

💡 Creating Custom Tools

python scripts/new_tool.py "My Custom Tool"

Or programmatically:

from craftxpy.plugins.tools.base_tool import BaseTool

class MyTool(BaseTool):
    def run(self, **kwargs) -> str:
        return "✅ Tool executed successfully!"

🎨 Web Interface

The Streamlit-based interface provides:

• Real-time Chat: Interactive AI conversations
• Model Switching: Choose between different AI models
• Tool Integration: Access all tools through the UI
• Session Management: Persistent conversation history
• Developer Mode: Safe shell execution and debugging

🛡️ Security Features

• Command Whitelisting: Only approved shell commands can execute
• Input Validation: All inputs are validated and sanitized
• Error Handling: Comprehensive error handling and logging
• Session Isolation: Each session is isolated and secure

📚 Documentation

• Website: https://craftx.py
• Documentation: https://docs.craftx.py

🧪 Testing

# Run all tests with beautiful output
python run_tests.py

# Run with pytest
python -m pytest tests/ -v

# Run specific test
python -m pytest tests/test_ui.py::test_logo_files -v

🌐 Static Website

CraftX.py includes a complete static website with:

• Landing Page (index.html) - Professional project showcase
• Documentation (docs.html) - Complete API and usage docs
• Examples (examples.html) - Code samples and tutorials
• About Page (about.html) - Project information and stats

To view locally:

# Simple HTTP server
python -m http.server 8000
# Then visit: http://localhost:8000

The website is also GitHub Pages ready with automatic deployment.

🤝 Contributing

We welcome contributions! Please see our Contributing Guide for details.

Development Setup

git clone https://github.com/davidanderson01/CraftX.py.git
cd CraftX.py
pip install -e .[dev]
pre-commit install

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

• AI Models: Thanks to the teams behind WizardCoder, CommandR7B, CodeGeeX4, and Qwen2.5-Coder
• Framework: Built with Streamlit, Python, and modern web technologies
• Community: Special thanks to all contributors and early adopters

🔗 Links

• GitHub: github.com/davidanderson01/CraftX.py
• PyPI: pypi.org/project/craftxpy
• Docker: hub.docker.com/r/craftx/craftxpy

---

CraftX.py - Python-native intelligence, modular by design.

Get Started • Documentation • Examples • Community