π€ MacPilot - Advanced macOS UI Automation Framework
Native macOS UI Automation with GPT-Powered Intelligence
Key Features β’ Architecture β’ Installation β’ Usage β’ Roadmap β’ Contributing
π What is MacPilot?
MacPilot is a state-of-the-art macOS UI automation framework that combines native Apple technologies with GPT intelligence to enable human-like interaction with your Mac. Write instructions in plain English, and let MacPilot handle the automation.
Perfect For:
- π Process Automation - Automate repetitive UI tasks
- π§ͺ UI Testing - Test macOS applications
- π€ Desktop RPA - Build robotic process automation
- π Screen Analysis - Extract data from UI elements
- π§ Workflow Automation - Create complex UI workflows
β¨ Key Features
π§ Core Intelligence
- GPT Integration - Natural language instruction processing
- Vision Framework - Advanced UI element detection
- State Awareness - Real-time system state tracking
- Pattern Recognition - Learned UI interaction patterns
- Self-healing - Automated error recovery
π― Native Integration
- Apple Vision - Native OCR and element detection
- AppleScript - Deep OS integration
- Accessibility APIs - Comprehensive UI control
- Cocoa/AppKit - Native macOS frameworks
- Core Graphics - Low-level screen capture
π Developer Experience
- Async Architecture - Built on modern async Python
- Type Safety - Full Pydantic validation
- Actor System - Modular action execution
- State Management - Comprehensive UI state tracking
- Pattern System - Reusable interaction patterns
π Application Control
- Chrome Control - Deep browser automation
- Finder Operations - File system automation
- System Control - OS-level operations
- Menu Navigation - Application menu control
- Window Management - Window state control
ποΈ Architecture
graph TD
A[Natural Language Instructions] --> B[GPT Analysis Layer]
B --> C[Action Planning]
C --> D[Actor System]
D --> E[UI Interaction Layer]
E --> F[State Management]
F --> B
Core Components:
- Instruction Processing - GPT-powered instruction analysis
- State Management - UI state tracking and validation
- Actor System - Modular action execution
- Pattern System - Reusable interaction patterns
- Vision System - UI element detection and OCR
- Recovery System - Automated error handling
π Installation
# Install from PyPI
pip install macpilot
# Or install from source
git clone https://github.com/adeelahmad/macpilot.git
cd macpilot
pip install -e .
π Usage
Basic Example
from macpilot import MacPilot
async def main():
pilot = MacPilot()
# Simple automation
await pilot.execute("Open Chrome and search for 'Python tutorials'")
# Complex workflows
await pilot.execute("""
1. Find all PDFs in Downloads
2. Create a folder named 'Documents'
3. Move PDFs older than 30 days
4. Create a summary spreadsheet
""")
if __name__ == "__main__":
asyncio.run(main())
Pattern Example
from macpilot.patterns import register_pattern
@register_pattern("login_flow")
async def handle_login(username: str, password: str):
return [
{"action": "click", "target": "username_field"},
{"action": "type", "text": username},
{"action": "click", "target": "password_field"},
{"action": "type", "text": password},
{"action": "click", "target": "login_button"}
]
π Todo & Roadmap
High Priority
-
[ ] User Interface
- [ ] CLI tool for automation scripts
- [ ] Web dashboard for monitoring
- [ ] Visual workflow builder
-
[ ] Core Features
- [ ] Local LLM support
- [ ] Improved error recovery
- [ ] Performance optimizations
Medium Priority
-
[ ] Documentation
- [ ] API reference
- [ ] Pattern library
- [ ] Example gallery
-
[ ] Testing
- [ ] Increase test coverage
- [ ] Integration tests
- [ ] Performance benchmarks
Low Priority
- [ ] Additional Features
- [ ] Safari automation support
- [ ] Network request monitoring
- [ ] Advanced screen recording
- [ ] Workflow marketplace
π€ Contributing
Contributions are welcome! Areas we're focusing on:
- π Documentation improvements
- π§ͺ Testing and bug fixes
- π― New application actors
- π Pattern implementations
- π Performance optimizations
Check our Contributing Guide for details.
π License
MacPilot is MIT licensed. See LICENSE for details.
π Acknowledgments
- Apple for macOS APIs
- OpenAI for GPT models
- Python community
Made with β€οΈ by the MacPilot Team