Vibe Coding DiscoverUI-TARS-desktop
View on GitHubThe Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
ByteDance's TARS stack ships Agent TARS (multimodal agent CLI/Web UI with GUI, vision and MCP tool use) plus UI-TARS Desktop, a native desktop app driving computer and browser operators from the UI-TARS vision-language model.
Use Cases
Control desktop computer with natural languageAutomate browser tasks via GUI or DOMBook flights/hotels autonomouslyBuild custom GUI automation agents with SDKRun headless agent serverConnect real-world tools via MCP serversGenerate charts from web dataRemote computer operatorRemote browser operatorDebug agent data flow with Event Stream ViewerMultimodal task completion in terminalExtract structured data from webpages
Built With
- Language
- TypeScript
- Frameworks
- Electron · Node.js · TypeScript · pnpm · Turborepo · Vitest · Playwright · MCP · Vite
Tags
multimodal-agent · gui-agent · computer-use · browser-automation · vision-language-model · mcp · agent-stack · electron · cli · web-ui · desktop-automation · gui-operator · agent-tars · ui-tars · event-stream · sdk