Launch, observe, and automate X11 apps through accessibility and input control.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "gui-user" yet — see the docs or source repo.
Use gui-user to open an X11 application, inspect its AT-SPI2 accessibility tree, locate the "Login" button, click it, and capture a screenshot of the result.
Returns the launch and interaction results, including detected UI elements, performed clicks, and a screenshot or state log.
Use gui-user to launch the target X11 program, open Settings, enable the specified option, save the configuration, and report the status of each step.
Produces a GUI automation execution log showing whether each step succeeded and the final configuration state.
Use gui-user to read the current window's AT-SPI2 tree for this X11 application, list buttons, text fields, and menu items, and identify controls that may be missing labels.
Returns a structured inventory of UI elements and flags controls with accessibility or discoverability issues.
Enable AI agents to control macOS GUI for end-to-end task automation.
Enable AI to control Windows apps through vision and simulated input.
Generate and serve ephemeral interactive UIs from natural language.
Automate Windows desktop apps with reliable UI control discovery and action verification.
Let AI see and control a Linux desktop for visual task automation.
Provide AI coding tools with live UI annotations, screenshots, and structured context.