CUA

pip install tapkit cua

import asyncio
from agent import ComputerAgent
from tapkit import TapKitClient
from tapkit.cua import TapKitComputerHandler
from dotenv import load_dotenv

load_dotenv()

async def main():
    phone = TapKitClient().phone("your-phone-id")
    handler = TapKitComputerHandler(phone)

    agent = ComputerAgent(
        model="openai/computer-use-preview",
        tools=[handler],
        only_n_most_recent_images=3,
        verbosity=2,
    )

    task = "Open Safari and search for the weather"
    async for result in agent.run([{"role": "user", "content": task}]):
        pass

asyncio.run(main())

TapKitComputerHandler(phone: Phone, max_long_edge: int = 1344)