GuideIntegrations
Yutori
Use Yutori's n1 model with Cua cloud sandboxes
Cua supports Yutori's n1 model as a computer-use agent. This guide shows how to connect Yutori n1 to a Cua cloud sandbox for an interactive agent loop.
Setup
Install the Cua SDK and python-dotenv:
pip install cua-computer cua-agent python-dotenvSet the following environment variables (or add them to a .env file):
export CUA_API_KEY=your-cua-api-key
export YUTORI_API_KEY=your-yutori-api-keyCUA_API_KEY— your Cua cloud API key. Get one from the Cua dashboard.YUTORI_API_KEY— your Yutori API key. Get one from Yutori.
Usage
Create a file called yutori_cua_script.py with the following contents:
import asyncio
import os
import dotenv
dotenv.load_dotenv()
from cua import ComputerAgent, Computer
CUA_API_KEY = os.environ["CUA_API_KEY"]
YUTORI_API_KEY = os.environ["YUTORI_API_KEY"]
async def main():
async with Computer(
os_type="linux",
provider_type="cloudv2",
name="my-sandbox",
api_key=CUA_API_KEY,
) as computer:
agent = ComputerAgent(
model="yutori/n1",
tools=[computer],
api_key=YUTORI_API_KEY,
)
history = []
while True:
user_input = input("> ")
history.append({"role": "user", "content": user_input})
async for result in agent.run(history, stream=False):
history += result["output"]
asyncio.run(main())Running the script
python yutori_cua_script.pyOnce running, you'll see a > prompt. Type a natural-language instruction and the Yutori n1 agent will execute it inside the Cua cloud sandbox. For example:
> Open Firefox and search for "Cua computer use agent"The agent maintains conversation history, so you can issue follow-up instructions that build on previous actions.
Was this page helpful?