trycua/cua agent-v0.4.53

cua-agent v0.4.53

on GitHub

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.

Installation

pip install cua-agent==0.4.53

Usage

import asyncio
from agent import ComputerAgent
from computer import Computer

async def main():
  # Initialize cloud computer
  computer = Computer(
    os_type="linux",
    provider_type="cloud",
    name="your-container-name",
    api_key="your-cua-api-key"
  )

  # Initialize agent with ByteDance UI-TARS-2
  agent = ComputerAgent(
    tools=[computer],
    model="cua/bytedance/ui-tars-2",
    api_key="your-cua-api-key",
    instructions="You are a helpful assistant that can control computers",
    only_n_most_recent_images=3
  )

  # Run a task
  async for result in agent.run("Open a browser and search for Python tutorials"):
    print(result)

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

What's Changed

• Jagjeevan's Fix + Merged Main for 4o Model Fix by @sarinali in #522
• fix: Added GPT-4o compatibility for screenshot actions with text parameter by @JagjeevanAK in #422
• Add test infrastructure with CI/CD #478 by @AceAtDev in #491
• Fix/omniparser predict refactor by @sarinali in #529
• Make VS Code Python interpreter path cross-platform by @skools-here in #520
• Fix: sanitize shell in subprocess calls by @AdityaBavadekar in #519
• [Agent] Add support for overriding api_base and api_url kwargs by @ddupont808 in #504
• Update model list and schedule daily test for agent testing by @YeIIcw in #540
• Add Claude Desktop Extension by @YeIIcw in #521
• [AGENT] - New Model Gelato-30B-A3B added by @tamoghnokandar in #558
• [AGENT] - New model UI-Ins added by @tamoghnokandar in #549
• Add "cua/" LLM provider by @ddupont808 in #506
• Add Local Desktop Mode for MCP Server with updated docs by @YeIIcw in #493
• Fix: Enable custom function tools with Anthropic models by @LucaStngn in #548
• Fix cua adapter, add UI-TARS-2 model by @ddupont808 in #592
• Fix cua adapter for anthropic models by @ddupont808 in #601
• Remove hud-python from cua-agent[all] extra by @f-trycua in #603
• Add automatic CUA_API_KEY environment variable support by @f-trycua in #604

New Contributors

• @AceAtDev made their first contribution in #491
• @skools-here made their first contribution in #520
• @tamoghnokandar made their first contribution in #545
• @dinmukhamedm made their first contribution in #404
• @LucaStngn made their first contribution in #548

Full Changelog: agent-v0.4.35...agent-v0.4.53