Agent Switchboard
A

Agent TARS

by ByteDance

VerifiedOfficial

Official listing: built and published by ByteDance. More from ByteDance

ByteDance's multimodal AI agent for desktop and browser automation — controls GUIs, browsers, and shell via vision and MCP tools. Available as npm CLI and desktop app.

Access
CLI
Auth
None
Skills
4

Skills

  • GUI Control

    Control desktop application interfaces using vision-based element detection, clicking, and keyboard input.

  • Browser Agent

    Navigate websites, fill forms, click elements, and extract data from web pages autonomously via the browser.

  • Shell Execution

    Execute shell commands and scripts as part of multi-step agent workflows with streamed output support.

  • MCP Tool Integration

    Connect to local or remote MCP servers and invoke their tools as steps in multi-tool agent pipelines.

Browser & Computer UseInfrastructure & Opscomputer-usegui-agentmultimodaldesktop-automationmcp-toolsbrowser-controlbytedance
Visit Agent

Related Agents

UI-TARS Desktop

CLI · API

ByteDance's multimodal GUI agent stack that controls desktop and browser interfaces from natural language using…

VerifiedOfficialby ByteDance · Browser & Computer Use · API Key

Microsoft UFO

CLI

Automates Windows desktop apps through natural-language tasks with the UFO2 Desktop AgentOS, and orchestrates agents…

VerifiedOfficialby Microsoft · Browser & Computer Use, Autonomous Agents · 4 skills · No auth

Agent S

API · CLI

Operates desktop graphical interfaces like a person, combining hierarchical planning with visual grounding to click…

Verifiedby Simular AI · Browser & Computer Use, Orchestration · 3 skills · API Key

Ghost OS

MCP · CLI

Lets any MCP-capable agent see and operate every macOS app through the accessibility tree, with vision fallback and…

Verifiedby Ghostwright · Browser & Computer Use · 3 skills · No auth
agent-tars
ByteDance's multimodal AI agent for desktop and browser automation — controls GUIs, browsers, and shell via vision and MCP tools. Available as npm CLI and desktop app.
fields
nameAgent TARS
providerByteDance
urlhttps://github.com/bytedance/UI-TARS-desktop
categoriesbrowser-computer · infrastructure
accesscli
authnone
streamingtrue
pushfalse
verifiedtrue
officialtrue · ByteDance
tagscomputer-use, gui-agent, multimodal, desktop-automation, mcp-tools, browser-control, bytedance
skills
gui-controlGUI ControlControl desktop application interfaces using vision-bas…
browser-agentBrowser AgentNavigate websites, fill forms, click elements, and extr…
shell-executionShell ExecutionExecute shell commands and scripts as part of multi-ste…
mcp-tool-integrationMCP Tool IntegrationConnect to local or remote MCP servers and invoke their…
→ https://github.com/bytedance/UI-TARS-desktop