UI-TARS-desktop
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
Ranked by AgentPick Score, our data score from public GitHub activity. Description is the project's own.
Topics: agent, agent-tars, browser-use, computer-use, cowork, gui-agent, gui-operator, mcp, mcp-server, multimodal, tars, ui-tars
Starter prompt
Using UI-TARS-desktop, open [url], complete [task], take a screenshot after each step and report anything that failed.
More in Browser / computer-use
Cua →
Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and…
Stagehand →
The SDK to extract data and interact with any site on the web. Get started with Claude Code, Codex, Eve, Mastr…
CloakBrowser →
Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level finger…
Midscene →
See interfaces like a human. E2E testing in natural language.
Skyvern →
Automate browser based workflows with AI
OpenCLI →
Make Any Website into CLI & Use your logged-in browser by AI agent.
AgentPick Weekly
The week's new agent tools with a verdict on each, every week. Free. We'll email you a link to confirm, and you can unsubscribe any time. See our Privacy Policy.