bytedance/UI-TARS-desktop

This page introduces an external open-source repository. It is not an HDATF product.

What it does

A multimodal agent stack with two projects. Agent TARS brings GUI agent and vision abilities to the terminal, computer and browser with MCP tools, and UI-TARS Desktop operates local or remote computers and browsers using the UI-TARS model.

How it helps ATF

Could be a reference for AX consulting when a legacy system such as MES or ERP has a screen but no API, since a GUI agent is one possible way in. Also worth comparing as a screen-operating executor for Harness.

License

Apache-2.0 Permissive, with a patent grant. Commercial use is allowed; keep the notices and state your changes.

More in this category

• MiroMindAI/MiroThinker
  MiroThinker is a deep research agent, with released models, built for complex research and prediction tasks. The project includes benchmark evaluation and trace collection, and its online version generates research reports that can be previewed and shared.
• daytonaio/daytona
  Daytona is a runtime that runs AI-generated code and agent workflows in isolated sandboxes, each with its own kernel, filesystem and network stack, managed through SDKs, an API and a CLI. This public repository is no longer maintained.
• virattt/dexter
  Dexter is a financial research agent that breaks a question into research steps, gathers live market data with tools, and checks and refines its own work before answering. It is meant for learning, not real trading or investment.
• code-yeongyu/oh-my-openagent
  A TypeScript orchestration project for AI coding agents that is started by adding a keyword to a prompt. The README excerpt mentions multi-model coding work and a memory system, but gives few other details.
• snarktank/ralph
  Ralph runs Amp or Claude Code in a loop until every item in a PRD (product requirements document) is done. Each run starts with fresh context, and memory persists in git history, progress.txt and prd.json.

Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.