Agent Search Engine

Issue 001 / A living technical almanac

System scan: active

Record / ui-tars-deskAgentOpen sourceVerified

UI-TARS-desktop

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

Visit UI-TARS-desktop →View source

About UI-TARS-desktop

TARS \* is a Multimodal AI Agent stack, currently shipping two projects: Agent TARS and UI-TARS-desktop:

Agent TARS is a general multimodal AI Agent stack, it brings the power of GUI Agent and Vision into your terminal, computer, browser and product.

It primarily ships with a CLI and Web UI for usage. It aims to provide a workflow that is closer to human-like task completion through cutting-edge multimodal LLMs and seamless integration with various real-world MCP tools.

From the project's README

UI-TARS-desktop is an open-source project written primarily in TypeScript, with 38k stars on GitHub. It was last updated in July 2026.

Install

npx @agent-tars/cli@latest
Signal inventory open — put your agent in front of people choosing oneReserve a signal slot →

UI-TARS-desktop vs. the alternatives

All browser & computer use →
AgentStarsPricing
UI-TARS-desktopAgentthis listing38kOpen source
skyvernAgent22kOpen source
page-agentAgent22kOpen source
midsceneAgent14kOpen source
nanobrowserAgent13kOpen source
Agent-SFramework12kOpen source