OpenAI CUA

Execute tasks with OpenAI CUA.

1

Install Hyperbrowser

Node

npm install @hyperbrowser/sdk dotenv

or

yarn add @hyperbrowser/sdk dotenv

Python

pip install hyperbrowser python-dotenv

or

uv add hyperbrowser python-dotenv

2

Setup your Environment

To use Hyperbrowser with your code, you will need an API Key. You can get one easily from the dashboard. Once you have your API Key, add it to your .env file as HYPERBROWSER_API_KEY .

3

Execute a Task

Next, you can have Hyperbrowser execute a task using OpenAI's Computer-Using Agent by simply providing a task.

Node

import { Hyperbrowser } from "@hyperbrowser/sdk";
import { config } from "dotenv";

config();

const hbClient = new Hyperbrowser({
  apiKey: process.env.HYPERBROWSER_API_KEY,
});

const main = async () => {
  const result = await hbClient.agents.cua.startAndWait({
    task: "What is the top post on Hacker News?",
  });

  console.log(`Output:\n\n${result.data?.finalResult}`);
};

main().catch((err) => {
  console.error(`Error: ${err.message}`);
});

Python

import os
from hyperbrowser import Hyperbrowser
from hyperbrowser.models import StartCuaTaskParams
from dotenv import load_dotenv

load_dotenv()

hb_client = Hyperbrowser(api_key=os.getenv("HYPERBROWSER_API_KEY"))


def main():
    resp = hb_client.agents.cua.start_and_wait(
        StartCuaTaskParams(
            task="What is the top post on Hacker News?"
        )
    )

    print(f"Output:\n\n{resp.data.final_result}")


if __name__ == "__main__":
    try:
        main()
    except Exception as e:
        print(f"Error: {e}")

4

View Agent in Dashboard

You can view all of your OpenAI CUA tasks in the dashboard. You can see what currently running ones are doing live or view information about completed ones.

More information about sessions, including user profiles, web recordings, live view, and more can be found in the Sessions Overview

To view more details check out the Agents OpenAI CUA page.