For AI agents: the complete documentation index is available at /llms.txt, the full documentation bundle is available at /llms-full.txt, and this page is available as Markdown at /get-started/desktop-playground-chatgpt.md.
  • English

      • Get started: Desktop · Playground · ChatGPT subscription

      These are the setup steps for Midscene on Desktop with Playground and a ChatGPT subscription. To choose another combination, change the answers below or see all setup paths.

      Which platform do you want to automate?
      What do you want to do first?
      How will you connect a model?

      Step 1

      Grant desktop permissions

      • macOS: Grant two separate system permissions to the terminal or IDE that launches Playground or runs your scripts (such as Terminal, iTerm2, VS Code, Cursor, or WebStorm):
        1. Accessibility (for mouse and keyboard control): Enable your terminal or IDE in System Settings > Privacy & Security > Accessibility (see nut.js macOS setup).
        2. Screen Recording (for desktop screenshots): Enable your terminal or IDE in System Settings > Privacy & Security > Screen Recording. After granting access, completely quit and relaunch the terminal or IDE before starting Playground.
      • Windows: No extra setup is required for standard applications. However, Windows User Interface Privilege Isolation (UIPI) blocks non-elevated processes from injecting mouse clicks or keystrokes into windows running as Administrator (the cursor still moves to the target coordinates, but clicks and key presses are silently dropped). Prefer running the target app without Administrator privileges; if it must run elevated, launch the terminal or Node.js process running Midscene as Administrator as well (see Windows: clicks have no effect on some apps).
      • Linux (desktop GUI): Install ImageMagick for screen capture support.
      • Linux (headless server / CI): To run desktop automation on a headless Linux host (such as GitHub Actions), install Xvfb and ImageMagick, then enable headless mode to start a virtual display automatically:
      # Install dependencies
sudo apt-get install -y xvfb x11-xserver-utils imagemagick

      When using Xvfb, make sure the target application is started inside the same virtual display environment (not needed on machines with a physical display).

      To control a remote Windows desktop over RDP, see Desktop environment setup.

      Step 2

      Sign in with your ChatGPT subscription

      The login command needs Node.js ^20.19.0 || ^22.12.0 || >=24.0.0 and pnpm. Check that node -v works in your terminal. If pnpm is not installed yet, run npm install -g pnpm.

      First, run the following command in your terminal:

      pnpm dlx @midscene/cli model siwc login

      Follow the terminal instructions to sign in to ChatGPT in your browser and authorize plan usage. You can choose a name for your Agent during authorization. Once authorized, the Agent appears on your ChatGPT usage page.

      The command saves credentials to ~/.midscene/siwc.json. Complete this sign-in manually before first use.

      Playground reads the credentials saved by this command. Keep the following lines at hand. You will paste them into Playground settings in a later step:

      MIDSCENE_MODEL_AUTH_MODE="siwc"
MIDSCENE_MODEL_NAME="gpt-6-sol"
MIDSCENE_MODEL_FAMILY="gpt-6"

      Available models depend on your ChatGPT account. For credentials and usage, see Use a ChatGPT subscription.

      Step 3

      Launch Playground

      Make sure Node.js (^20.19.0 || ^22.12.0 || >=24.0.0) is installed and node -v works in your terminal. The command below uses pnpm. If it is not installed yet, run npm install -g pnpm.

      1. Start the Desktop Playground CLI:
      pnpm dlx @midscene/computer-playground

      On headless Linux, enable a virtual display with the following command and run the target application in that same display:

      MIDSCENE_COMPUTER_HEADLESS_LINUX=true pnpm dlx @midscene/computer-playground
      1. In the Playground window that opens, click the gear icon in the top-right corner, paste your model configuration, and save.
      2. If your browser does not open automatically, visit the local Playground URL printed in the terminal, and keep the terminal process running.
      3. In the connection panel on the left, select the target Display to control, create the Agent, and place the target application window on that display.
      4. Confirm that the preview area shows the live screen of the selected display. If the preview is blank or fails to load, check the Screen Recording permission or Linux dependencies above.

      Step 4

      Run an action and verify the result

      Open a browser window on the target display and enter the following TodoMVC URL in the address bar:

      https://todomvc.com/examples/react/dist/#/

      Position the windows so that the Playground tab does not cover the TodoMVC page.

      1. In Playground, select aiAct, enter the following instruction, and run it (avoid moving the mouse or typing while the action is running):
      Add a todo named "Try Midscene", then mark it as completed.
      1. Once the completed todo item appears on the page, switch to aiAssert, enter the following assertion, and run it:
      The list contains a todo named "Try Midscene", and it is marked as completed.

      1. Confirm that the assertion passes and inspect the step-by-step screenshots in the results panel. At this point, desktop screen capture, mouse/keyboard input, and model calls have all been verified together.

      2. (Optional) Switch to aiQuery, enter the following query, and run it:

      Return the visible todo items as {name: string, completed: boolean}[].

      The result contains each todo item's name and completion status. aiQuery extracts data from the current UI without changing the page.

      If execution fails, check the failed step and error message: for missing screenshots or unresponsive mouse/keyboard input, see the FAQ; for model request errors, see Verify model connectivity.

      After verification, delete the "Try Midscene" item in TodoMVC. If you plan to run the Midscene Test Desktop example next, switch to the All filter and make sure the list is completely empty (including completed items), as the example template checks for an empty list before running and does not overwrite existing items.

      Step 5

      Next steps

      • Explore more examples: Showcases includes demo videos and full execution reports across platforms.
      • Learn how Midscene works: The Basics explains the vision-based approach and when to use aiAct, instant actions, and insight APIs.

      Want to try another platform or way to use Midscene? Back to top to change your selections.