OpenAI Testing Agent Demo

This monorepo demonstrates how you can use OpenAI's CUA model and computer use tool to automate frontend testing. It uses Playwright to spin up a browser instance and navigate to the web app to be tested. The CUA model then follows the provided test case and executes actions on the interface until the test case is done.

The repo contains three applications that work together:

• frontend – Next.js web interface used to configure tests and watch them run.
• cua-server – Node service that communicates with the OpenAI CUA model and drives Playwright to interact in a browser with the sample app.
• sample-test-app – Example e‑commerce site used as an example app to test by the agent.

1. Clone the repository

   git clone https://github.com/openai/testing-agent-demo cd testing-agent-demo

2. Prepare environment files

   If you haven't set your OPENAI_API_KEY environment variable on your terminal or globally on your machine (set up instructions here), edit each .env.development file and set OPENAI_API_KEY.

   cp frontend/.env.example frontend/.env.development cp cua-server/.env.example cua-server/.env.development cp sample-test-app/.env.example sample-test-app/.env.development

   The sample app also defines demo login credentials, which by default are:

   ADMIN_USERNAME=test_user_name ADMIN_PASSWORD=test_password

   Make sure you add a sample-test-app/.env.development file with the example credentials to run the demo.

3. Install dependencies

   npm install npx playwright install

4. Run all apps

   This will start all three apps:

   • Frontend UI: http://localhost:3000
   • Sample app: http://localhost:3005
   • CUA server: ws://localhost:8080

   Navigate to localhost:3000 to see the frontend UI and run the demo.

For details on each app see their READMEs:

• frontend/README.md
• cua-server/README.md
• sample-test-app/README.md

You can use this testing agent with any web app you choose, and update the test case and target URL either in the config UI or in the frontend/lib/constants.ts file (default values used in the UI).

sample-test-app is only provided as an example to try the demo, and frontend as a testing interface. The core logic of the testing agent is in cua-server, which is what you might want to bring into your own application.

You are welcome to open issues or submit PRs to improve this app, however, please note that we may not review all suggestions.

• This project is meant to be used on test environments only.
• Do not use real user data in production.

This project is licensed under the MIT License. See the LICENSE file for details.