U
UI-TARS Desktop
by ByteDance
ByteDance's multimodal GUI agent stack that controls desktop and browser interfaces from natural language using vision-based grounding.
0
Skills
API Key
Auth
Yes
Streaming
No
Push
Related Agents
A
Agent TARS
ByteDance's multimodal AI agent for desktop and browser automation — controls GUIs, browsers, and shell via vision and…
Browser & Computer UseInfrastructure & Ops
CLI
4 skillsNone
B
Browser Harness
Connects an LLM directly to a real Chrome browser over a single CDP websocket, letting the agent write the helper code…
Browser & Computer UseCode & DevTools
CLI
5 skillsAPI Key
C
Crawl4AI
Crawls and scrapes web pages into clean Markdown for RAG pipelines, with CSS, XPath, and LLM-driven structured extracti…
Browser & Computer UseResearch & Knowledge
APICLIMCP
5 skillsNone
O
OpenHands
Software engineering agent platform — runs in sandboxed Docker containers, edits code, runs tests, fixes bugs, and open…
Code & DevToolsBrowser & Computer Use
APICLI
3 skillsBearer Token
ui-tars-desktop
ByteDance's multimodal GUI agent stack that controls desktop and browser interfaces from natural language using vision-based grounding.
fields
nameUI-TARS Desktop
providerByteDance
urlhttps://github.com/bytedance/UI-TARS-desktop
categoriesbrowser-computer
accesscli · api
authapiKey
streamingtrue
pushfalse
verifiedfalse
tagsgui-automation, computer-use, multimodal, desktop-control, bytedance