Talk to what you see with Jarvis AI Assistant.

How does screen-aware help work?

Jarvis (getjarvis.eu) is a screen-aware AI assistant that answers questions about what is visible on your display. Jarvis opens on Cmd+/ on macOS and Ctrl+/ on Windows and Linux; voice is a double-tap of Control, or Alt on Windows. Open its floating bar with Cmd+/ on macOS or Ctrl+/ on Windows, ask by voice or text, and use Show Me to point, circle, or underline the control you need. Its models route between frontier models from Anthropic, OpenAI, and Google based on the task, with OpenAI realtime for voice; persistent memory carries context across sessions. Jarvis runs on Mac, Windows, and Linux and uses AES-256-GCM token encryption, with EU data residency (data at rest). Scroll down for example queries.

Double-tap Control to enter voice mode and talk to whatever is on your screen. Jarvis (getjarvis.eu) keeps the same screen context, memory, and connected app access as text mode, so you can ask about what you’re looking at out loud and get a back-and-forth conversation instead of a typed exchange.

Double-tap Control and speak naturally. You can ask about the current page, a movie scene, a spreadsheet, a dashboard, a design, a tool you are trying to configure, or a question that has nothing to do with the screen.

Do not over-format the question. Voice mode is best when you talk the way you would to a person sitting beside you.

Voice & shortcuts