Open source
UI TARS Desktop: Open Source GUI Agent
UI TARS Desktop is an open source app that controls your computer with plain language. It takes screenshots, sends them to a vision model, and moves the mouse and types.
Watch on YouTube · Watch on TikTok
The story
What the video said
UI TARS desktop is an open source app that turns plain words into real clicks and typing on your own computer screen.
You already use an AI coding tool to write scripts. Now you want it to fill a form in an app that has no API.
UI TARS desktop is an open source project from ByteDance. It runs a loop that takes a screenshot, asks a vision model what to do, then moves the mouse or types.
The browser operator highlights clickable elements before each screenshot. The app marks predicted click spots on screen, so you can watch the agent work.
It is Apache licensed and has about thirty nine thousand stars. You can install it with Homebrew or download a release from GitHub.
This page was generated from the Ming Dao AI publication record.
Ming Dao AI is independent and unaffiliated with GitHub or the featured project. Read our editorial policy.