Skip to main content

Computer Use Automation (CUA) client for remote function execution

Project description

CUA Client

Computer Use Automation (CUA) Client - A Python package for remote function execution and computer automation tasks via WebSocket connections.

Features

  • Remote Function Execution: Connect to remote servers and execute functions over WebSocket
  • Computer Use Automation: Automate mouse, keyboard, and screen interactions
  • Flexible Configuration: Environment-based configuration with validation
  • Async Support: Built with asyncio for high-performance concurrent operations
  • Extensible: Easy to add custom functions and routers

Installation

pip install cua-client

Quick Start

1. Set Environment Variables

export REMOTE_FUNCTION_URL="ws://your-server.com/ws"
export AGENT_ID="123"
export SECRET_KEY="your-secret-key"

2. Run the Client

# As a command-line tool
cua-client

# Or programmatically
python -m cua_client.main

3. Programmatic Usage

import asyncio
from cua_client import RemoteFunctionClient, RemoteFunctionRouter

# Create a custom router
my_router = RemoteFunctionRouter(tags=["custom"])

@my_router.function("greet")
def greet(name: str) -> str:
    return f"Hello, {name}!"

# Set up the client
async def main():
    client = RemoteFunctionClient(
        remote_function_url="ws://your-server.com/ws",
        agent_id=123,
        secret_key="your-secret-key"
    )
    
    # Add your custom router
    client.include_router(my_router)
    
    # Run the client
    await client.run()

if __name__ == "__main__":
    asyncio.run(main())

Configuration

The client requires three environment variables:

  • REMOTE_FUNCTION_URL: WebSocket server URL (e.g., ws://localhost:8000/ws)
  • AGENT_ID: Unique identifier for the client agent (integer)
  • SECRET_KEY: Authentication secret key

Built-in Functions

Computer Use Functions

The client comes with built-in computer automation capabilities:

  • Screen capture: Take screenshots and analyze screen content
  • Mouse control: Click, drag, and move mouse cursor
  • Keyboard input: Type text and send key combinations
  • Window management: Focus windows and manage applications

Basic Functions

  • print: Simple message printing function for testing

Advanced Usage

Custom Function Registration

from cua_client import RemoteFunctionClient

client = RemoteFunctionClient(url, agent_id, secret_key)

# Register a single function
def my_function(param: str) -> str:
    return f"Processed: {param}"

client.register_function("my_func", my_function)

# Or use a router for organized function groups
router = RemoteFunctionRouter(tags=["data"])

@router.function("process_data")
def process_data(data: dict) -> dict:
    # Your processing logic here
    return {"result": "processed", "original": data}

client.include_router(router)

Error Handling

try:
    await client.run()
except ConnectionError:
    print("Failed to connect to server")
except KeyboardInterrupt:
    print("Client stopped by user")
except Exception as e:
    print(f"Unexpected error: {e}")

Security Considerations

  • Always use secure WebSocket connections (wss://) in production
  • Keep your SECRET_KEY confidential and rotate it regularly
  • Validate all inputs in your custom functions
  • Run the client with minimal required permissions

Dependencies

  • pydantic>=1.8.0: Data validation and configuration
  • websockets>=10.0: WebSocket client implementation
  • pynput>=1.7.0: Mouse and keyboard control
  • Pillow>=8.0.0: Image processing for screenshots
  • pyautogui>=0.9.50: GUI automation utilities

Development

Installation for Development

# Clone the repository
git clone https://github.com/168x/cua-client.git
cd cua-client

# Install in development mode
pip install -e .[dev]

Building and Publishing

Use the provided script to build and publish the package:

# Make the script executable
chmod +x publish.sh

# Run the interactive publish script
./publish.sh

The script will:

  • Show current version and suggest increments
  • Update version in all necessary files
  • Build the package
  • Validate the build
  • Optionally publish to PyPI or Test PyPI

See PUBLISH_USAGE.md for detailed usage instructions.

Running Tests

pytest

Code Formatting

black src/
flake8 src/
mypy src/

Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Add tests for new functionality
  5. Ensure all tests pass
  6. Submit a pull request

License

MIT License - see LICENSE file for details.

Support

Changelog

v0.1.0

  • Initial release
  • Basic remote function execution
  • Computer use automation features
  • WebSocket-based communication
  • Environment-based configuration

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

cua_client-0.3.1.tar.gz (29.6 kB view details)

Uploaded Source

Built Distribution

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

cua_client-0.3.1-py3-none-any.whl (35.1 kB view details)

Uploaded Python 3

File details

Details for the file cua_client-0.3.1.tar.gz.

File metadata

  • Download URL: cua_client-0.3.1.tar.gz
  • Upload date:
  • Size: 29.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.3

File hashes

Hashes for cua_client-0.3.1.tar.gz
Algorithm Hash digest
SHA256 3654e3ccc69abc92cca362ef3ffb6c19928e83676671a2e861503b5ec8ef5ced
MD5 b4ec74818518013dc3c7312aa8e46f60
BLAKE2b-256 a35f88aea91ef1966346d8e27eabb49ed6d4e6d53924047398b10475055268d6

See more details on using hashes here.

File details

Details for the file cua_client-0.3.1-py3-none-any.whl.

File metadata

  • Download URL: cua_client-0.3.1-py3-none-any.whl
  • Upload date:
  • Size: 35.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.3

File hashes

Hashes for cua_client-0.3.1-py3-none-any.whl
Algorithm Hash digest
SHA256 3a82d7caa2d2c4bbc8f016c687cba06c11464087775c0072c794c8414a0501bc
MD5 60f93775f73b2a5f2a31f1dee5215fab
BLAKE2b-256 5d4d138b4fc01484b50d1c56aa214a963a0ed3edc0b26a4e13534916d85b1b0c

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