Skip to main content

CUA (Computer Use) Agent for AI-driven computer interaction

Project description

Shows my svg

Python macOS Discord PyPI

cua-agent is a general Computer-Use framework with liteLLM integration for running agentic workflows on macOS, Windows, and Linux sandboxes. It provides a unified interface for computer-use agents across multiple LLM providers with advanced callback system for extensibility.

Features

  • Safe Computer-Use/Tool-Use: Using Computer SDK for sandboxed desktops
  • Multi-Agent Support: Anthropic Claude, OpenAI computer-use-preview, UI-TARS, Omniparser + any LLM
  • Multi-API Support: Take advantage of liteLLM supporting 100+ LLMs / model APIs, including local models (huggingface-local/, ollama_chat/, mlx/)
  • Cross-Platform: Works on Windows, macOS, and Linux with cloud and local computer instances
  • Extensible Callbacks: Built-in support for image retention, cache control, PII anonymization, budget limits, and trajectory tracking

Install

pip install "cua-agent[all]"

Quick Start

import asyncio
import os
from agent import ComputerAgent
from computer import Computer

async def main():
    # Set up computer instance
    async with Computer(
        os_type="linux",
        provider_type="cloud",
        name=os.getenv("CUA_CONTAINER_NAME"),
        api_key=os.getenv("CUA_API_KEY")
    ) as computer:

        # Create agent
        agent = ComputerAgent(
            model="anthropic/claude-3-5-sonnet-20241022",
            tools=[computer],
            only_n_most_recent_images=3,
            trajectory_dir="trajectories",
            max_trajectory_budget=5.0  # $5 budget limit
        )

        # Run agent
        messages = [{"role": "user", "content": "Take a screenshot and tell me what you see"}]

        async for result in agent.run(messages):
            for item in result["output"]:
                if item["type"] == "message":
                    print(item["content"][0]["text"])

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

Docs

License

MIT License - see LICENSE file for details.

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

cua_agent-0.4.50.tar.gz (139.3 kB view details)

Uploaded Source

Built Distribution

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

cua_agent-0.4.50-py3-none-any.whl (174.8 kB view details)

Uploaded Python 3

File details

Details for the file cua_agent-0.4.50.tar.gz.

File metadata

  • Download URL: cua_agent-0.4.50.tar.gz
  • Upload date:
  • Size: 139.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.9

File hashes

Hashes for cua_agent-0.4.50.tar.gz
Algorithm Hash digest
SHA256 f5c8c0f358ae5641a3054f789db0ecc8bc5b555fa238232f15161895441b3dfb
MD5 0cda0e971fd24b0164301fd6ea563ef1
BLAKE2b-256 3cac65de45e17dbfe21da68d99cdf9fbcbb9d77d8ef3b0d78749fc2df90ed6e4

See more details on using hashes here.

File details

Details for the file cua_agent-0.4.50-py3-none-any.whl.

File metadata

  • Download URL: cua_agent-0.4.50-py3-none-any.whl
  • Upload date:
  • Size: 174.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.9

File hashes

Hashes for cua_agent-0.4.50-py3-none-any.whl
Algorithm Hash digest
SHA256 20eebb512fd58f92386d07951217361e054c903c4c76ecd2e8e099f3542d478a
MD5 1c02c7d003e9cc384d62419dac3bdcc2
BLAKE2b-256 bbe00f161f56c59d43522b2ca9dd3c0fea279d886876f93fd16ce8b3652c90fd

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