1.bytedance / UI-TARS-desktopThe Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infraagentvlmvisioncomputer-usemcpmcp-server+8 moreTypeScriptAPACHE-2.040K total4K forks+10,319 starsfrom 29,191 · score 9.24
2.web-infra-dev / midsceneSee interfaces like a human. E2E testing in natural language.testingbrowser-usecomputer-usegpt-operatorjavascriptphone-use+2 moreTypeScriptMIT15K total1.2K forks+2,656 starsfrom 12,803 · score 7.88
3.nanobrowser / nanobrowserOpen-source AI agent for web automation. Use your real, logged-in browser to automate daily tasks.chrome-extensionagentai-agentsai-toolsautomationbrowser-use+14 moreTypeScriptAPACHE-2.014K total1.5K forks+1,500 starsfrom 12,713 · score 7.31