[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-3591":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":25,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":41,"readmeContent":42,"aiSummary":43,"trendingCount":16,"starSnapshotCount":16,"syncStatus":44,"lastSyncTime":45,"discoverSource":46},3591,"UI-TARS-desktop","bytedance\u002FUI-TARS-desktop","bytedance","The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra","https:\u002F\u002Fagent-tars.com",null,"TypeScript",36304,3660,268,320,0,24,261,3230,137,120,"Apache License 2.0",false,"main",true,[27,28,29,30,31,32,33,34,35,36,37,38,39,40],"agent","agent-tars","browser-use","computer-use","cowork","gui-agent","gui-operator","mcp","mcp-server","multimodal","tars","ui-tars","vision","vlm","2026-06-12 04:00:18","\u003Cpicture>\n  \u003Cimg alt=\"Agent TARS Banner\" src=\".\u002Fimages\u002Ftars.png\">\n\u003C\u002Fpicture>\n\n\u003Cbr\u002F>\n\n## Introduction\n\nEnglish | [简体中文](.\u002FREADME.zh-CN.md)\n\n[![](https:\u002F\u002Ftrendshift.io\u002Fapi\u002Fbadge\u002Frepositories\u002F13584)](https:\u002F\u002Ftrendshift.io\u002Frepositories\u002F13584)\n\n\u003Cb>TARS\u003Csup>\\*\u003C\u002Fsup>\u003C\u002Fb> is a Multimodal AI Agent stack, currently shipping two projects: [Agent TARS](#agent-tars) and [UI-TARS-desktop](#ui-tars-desktop):\n\n\u003Ctable>\n  \u003Cthead>\n    \u003Ctr>\n      \u003Cth width=\"50%\" align=\"center\">\u003Ca href=\"#agent-tars\">Agent TARS\u003C\u002Fa>\u003C\u002Fth>\n      \u003Cth width=\"50%\" align=\"center\">\u003Ca href=\"#ui-tars-desktop\">UI-TARS-desktop\u003C\u002Fa>\u003C\u002Fth>\n    \u003C\u002Ftr>\n  \u003C\u002Fthead>\n  \u003Ctbody>\n    \u003Ctr>\n      \u003Ctd align=\"center\">\n        \u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fc9489936-afdc-4d12-adda-d4b90d2a869d\" width=\"50%\">\u003C\u002Fvideo>\n      \u003C\u002Ftd>\n      \u003Ctd align=\"center\">\n        \u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fe0914ce9-ad33-494b-bdec-0c25c1b01a27\" width=\"50%\">\u003C\u002Fvideo>\n      \u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\n      \u003Ctd align=\"left\">\n        \u003Cb>Agent TARS\u003C\u002Fb> is a general multimodal AI Agent stack, it brings the power of GUI Agent and Vision into your terminal, computer, browser and product.\n        \u003Cbr>\n        \u003Cbr>\n        It primarily ships with a \u003Ca href=\"https:\u002F\u002Fagent-tars.com\u002Fguide\u002Fbasic\u002Fcli.html\" target=\"_blank\">CLI\u003C\u002Fa> and \u003Ca href=\"https:\u002F\u002Fagent-tars.com\u002Fguide\u002Fbasic\u002Fweb-ui.html\" target=\"_blank\">Web UI\u003C\u002Fa> for usage.\n        It aims to provide a workflow that is closer to human-like task completion through cutting-edge multimodal LLMs and seamless integration with various real-world \u003Ca href=\"https:\u002F\u002Fagent-tars.com\u002Fguide\u002Fbasic\u002Fmcp.html\" target=\"_blank\">MCP\u003C\u002Fa> tools.\n      \u003C\u002Ftd>\n      \u003Ctd align=\"left\">\n        \u003Cb>UI-TARS Desktop\u003C\u002Fb> is a desktop application that provides a native GUI Agent based on the \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fbytedance\u002FUI-TARS\" target=\"_blank\">UI-TARS\u003C\u002Fa> model.\n        \u003Cbr>\n        \u003Cbr>\n        It primarily ships a\n        \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fbytedance\u002FUI-TARS-desktop\u002Fblob\u002Fmain\u002Fdocs\u002Fquick-start.md#get-model-and-run-local-operator\" target=\"_blank\">local\u003C\u002Fa> and \n        \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fbytedance\u002FUI-TARS-desktop\u002Fblob\u002Fmain\u002Fdocs\u002Fquick-start.md#run-remote-operator\" target=\"_blank\">remote\u003C\u002Fa> computer as well as browser operators.\n      \u003C\u002Ftd>\n    \u003C\u002Ftr>\n  \u003C\u002Ftbody>\n\u003C\u002Ftable>\n\n## Table of Contents\n\n\u003C!-- START doctoc generated TOC please keep comment here to allow auto update -->\n\u003C!-- DON'T EDIT THIS SECTION, INSTEAD RE-RUN doctoc TO UPDATE -->\n\n- [News](#news)\n- [Agent TARS](#agent-tars)\n  - [Showcase](#showcase)\n  - [Core Features](#core-features)\n  - [Quick Start](#quick-start)\n  - [Documentation](#documentation)\n- [UI-TARS Desktop](#ui-tars-desktop)\n  - [Showcase](#showcase-1)\n  - [Features](#features)\n  - [Quick Start](#quick-start-1)\n- [Contributing](#contributing)\n- [License](#license)\n- [Citation](#citation)\n\n\u003C!-- END doctoc generated TOC please keep comment here to allow auto update -->\n\n## News\n\n- **\\[2025-11-05\\]** 🎉 We're excited to announce the release of [Agent TARS CLI v0.3.0](https:\u002F\u002Fgithub.com\u002Fbytedance\u002FUI-TARS-desktop\u002Freleases\u002Ftag\u002Fv0.3.0)! This version brings streaming support for multiple tools (shell commands, multi-file structured display), runtime settings with timing statistics for tool calls and deep thinking, Event Stream Viewer for data flow tracking and debugging. Additionally, it features exclusive support for [AIO agent Sandbox](https:\u002F\u002Fgithub.com\u002Fagent-infra\u002Fsandbox) as isolated all-in-one tools execution environment.\n- **\\[2025-06-25\\]** We released an Agent TARS Beta and Agent TARS CLI - [Introducing Agent TARS Beta](https:\u002F\u002Fagent-tars.com\u002Fblog\u002F2025-06-25-introducing-agent-tars-beta.html), a multimodal AI agent that aims to explore a work form that is closer to human-like task completion through rich multimodal capabilities (such as GUI Agent, Vision) and seamless integration with various real-world tools.\n- **\\[2025-06-12\\]** - 🎁 We are thrilled to announce the release of UI-TARS Desktop v0.2.0! This update introduces two powerful new features: **Remote Computer Operator** and **Remote Browser Operator**—both completely free. No configuration required: simply click to remotely control any computer or browser, and experience a new level of convenience and intelligence.\n- **\\[2025-04-17\\]** - 🎉 We're thrilled to announce the release of new UI-TARS Desktop application v0.1.0, featuring a redesigned Agent UI. The application enhances the computer using experience, introduces new browser operation features, and supports [the advanced UI-TARS-1.5 model](https:\u002F\u002Fseed-tars.com\u002F1.5) for improved performance and precise control.\n- **\\[2025-02-20\\]** - 📦 Introduced [UI TARS SDK](.\u002Fdocs\u002Fsdk.md), is a powerful cross-platform toolkit for building GUI automation agents.\n- **\\[2025-01-23\\]** - 🚀 We updated the **[Cloud Deployment](.\u002Fdocs\u002Fdeployment.md#cloud-deployment)** section in the 中文版: [GUI模型部署教程](https:\u002F\u002Fbytedance.sg.larkoffice.com\u002Fdocx\u002FTCcudYwyIox5vyxiSDLlgIsTgWf#U94rdCxzBoJMLex38NPlHL21gNb) with new information related to the ModelScope platform. You can now use the ModelScope platform for deployment.\n\n\u003Cbr>\n\n## Agent TARS\n\n\u003Cp>\n    \u003Ca href=\"https:\u002F\u002Fnpmjs.com\u002Fpackage\u002F@agent-tars\u002Fcli?activeTab=readme\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fv\u002F@agent-tars\u002Fcli?style=for-the-badge&colorA=1a1a2e&colorB=3B82F6&logo=npm&logoColor=white\" alt=\"npm version\" \u002F>\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fnpmcharts.com\u002Fcompare\u002F@agent-tars\u002Fcli?minimal=true\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fdm\u002F@agent-tars\u002Fcli.svg?style=for-the-badge&colorA=1a1a2e&colorB=0EA5E9&logo=npm&logoColor=white\" alt=\"downloads\" \u002F>\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fnodejs.org\u002Fen\u002Fabout\u002Fprevious-releases\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fnode\u002Fv\u002F@agent-tars\u002Fcli.svg?style=for-the-badge&colorA=1a1a2e&colorB=06B6D4&logo=node.js&logoColor=white\" alt=\"node version\">\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FHnKcSBgTVx\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-Join%20Community-5865F2?style=for-the-badge&logo=discord&logoColor=white\" alt=\"Discord Community\" \u002F>\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Ftwitter.com\u002Fagent_tars\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FTwitter-Follow%20%40agent__tars-1DA1F2?style=for-the-badge&logo=twitter&logoColor=white\" alt=\"Official Twitter\" \u002F>\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fapplink.larkoffice.com\u002Fclient\u002Fchat\u002Fchatter\u002Fadd_by_link?link_token=deen76f4-ea3c-4964-93a3-78f126f39651\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F飞书群-加入交流群-00D4AA?style=for-the-badge&logo=lark&logoColor=white\" alt=\"飞书交流群\" \u002F>\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fdeepwiki.com\u002Fbytedance\u002FUI-TARS-desktop\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDeepWiki-Ask%20AI-8B5CF6?style=for-the-badge&logo=gitbook&logoColor=white\" alt=\"Ask DeepWiki\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cb>Agent TARS\u003C\u002Fb> is a general multimodal AI Agent stack, it brings the power of GUI Agent and Vision into your terminal, computer, browser and product. \u003Cbr> \u003Cbr>\nIt primarily ships with a \u003Ca href=\"https:\u002F\u002Fagent-tars.com\u002Fguide\u002Fbasic\u002Fcli.html\" target=\"_blank\">CLI\u003C\u002Fa> and \u003Ca href=\"https:\u002F\u002Fagent-tars.com\u002Fguide\u002Fbasic\u002Fweb-ui.html\" target=\"_blank\">Web UI\u003C\u002Fa> for usage.\nIt aims to provide a workflow that is closer to human-like task completion through cutting-edge multimodal LLMs and seamless integration with various real-world \u003Ca href=\"https:\u002F\u002Fagent-tars.com\u002Fguide\u002Fbasic\u002Fmcp.html\" target=\"_blank\">MCP\u003C\u002Fa> tools.\n\n### Showcase\n\n```\nPlease help me book the earliest flight from San Jose to New York on September 1st and the last return flight on September 6th on Priceline\n```\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F772b0eef-aef7-4ab9-8cb0-9611820539d8\n\n\u003Cbr>\n\n\u003Ctable>\n  \u003Cthead>\n    \u003Ctr>\n      \u003Cth width=\"50%\" align=\"center\">Booking Hotel\u003C\u002Fth>\n      \u003Cth width=\"50%\" align=\"center\">Generate Chart with extra MCP Servers\u003C\u002Fth>\n    \u003C\u002Ftr>\n  \u003C\u002Fthead>\n  \u003Ctbody>\n    \u003Ctr>\n      \u003Ctd align=\"center\">\n        \u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fc9489936-afdc-4d12-adda-d4b90d2a869d\" width=\"50%\">\u003C\u002Fvideo>\n      \u003C\u002Ftd>\n      \u003Ctd align=\"center\">\n        \u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fa9fd72d0-01bb-4233-aa27-ca95194bbce9\" width=\"50%\">\u003C\u002Fvideo>\n      \u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\n      \u003Ctd align=\"left\">\n        \u003Cb>Instruction:\u003C\u002Fb> \u003Ci>I am in Los Angeles from September 1st to September 6th, with a budget of $5,000. Please help me book a Ritz-Carlton hotel closest to the airport on booking.com and compile a transportation guide for me\u003C\u002Fi>\n      \u003C\u002Ftd>\n      \u003Ctd align=\"left\">\n        \u003Cb>Instruction:\u003C\u002Fb> \u003Ci>Draw me a chart of Hangzhou's weather for one month\u003C\u002Fi>\n      \u003C\u002Ftd>\n    \u003C\u002Ftr>\n  \u003C\u002Ftbody>\n\u003C\u002Ftable>\n\nFor more use cases, please check out [#842](https:\u002F\u002Fgithub.com\u002Fbytedance\u002FUI-TARS-desktop\u002Fissues\u002F842).\n\n### Core Features\n\n- 🖱️ **One-Click Out-of-the-box CLI** - Supports both **headful** [Web UI](https:\u002F\u002Fagent-tars.com\u002Fguide\u002Fbasic\u002Fweb-ui.html) and **headless** [server](https:\u002F\u002Fagent-tars.com\u002Fguide\u002Fadvanced\u002Fserver.html) [execution](https:\u002F\u002Fagent-tars.com\u002Fguide\u002Fbasic\u002Fcli.html).\n- 🌐 **Hybrid Browser Agent** - Control browsers using [GUI Agent](https:\u002F\u002Fagent-tars.com\u002Fguide\u002Fbasic\u002Fbrowser.html#visual-grounding), [DOM](https:\u002F\u002Fagent-tars.com\u002Fguide\u002Fbasic\u002Fbrowser.html#dom), or a hybrid strategy.\n- 🔄 **Event Stream** - Protocol-driven Event Stream drives [Context Engineering](https:\u002F\u002Fagent-tars.com\u002Fbeta#context-engineering) and [Agent UI](https:\u002F\u002Fagent-tars.com\u002Fblog\u002F2025-06-25-introducing-agent-tars-beta.html#easy-to-build-applications).\n- 🧰 **MCP Integration** - The kernel is built on MCP and also supports mounting [MCP Servers](https:\u002F\u002Fagent-tars.com\u002Fguide\u002Fbasic\u002Fmcp.html) to connect to real-world tools.\n\n### Quick Start\n\n\u003Cimg alt=\"Agent TARS CLI\" src=\"https:\u002F\u002Fagent-tars.com\u002Fagent-tars-cli.png\">\n\n```bash\n# Launch with `npx`.\nnpx @agent-tars\u002Fcli@latest\n\n# Install globally, required Node.js >= 22\nnpm install @agent-tars\u002Fcli@latest -g\n\n# Run with your preferred model provider\nagent-tars --provider volcengine --model doubao-1-5-thinking-vision-pro-250428 --apiKey your-api-key\nagent-tars --provider anthropic --model claude-3-7-sonnet-latest --apiKey your-api-key\n```\n\nVisit the comprehensive [Quick Start](https:\u002F\u002Fagent-tars.com\u002Fguide\u002Fget-started\u002Fquick-start.html) guide for detailed setup instructions.\n\n### Documentation\n\n> 🌟 **Explore Agent TARS Universe** 🌟\n\n\u003Ctable>\n  \u003Cthead>\n    \u003Ctr>\n      \u003Cth width=\"20%\" align=\"center\">Category\u003C\u002Fth>\n      \u003Cth width=\"30%\" align=\"center\">Resource Link\u003C\u002Fth>\n      \u003Cth width=\"50%\" align=\"left\">Description\u003C\u002Fth>\n    \u003C\u002Ftr>\n  \u003C\u002Fthead>\n  \u003Ctbody>\n    \u003Ctr>\n      \u003Ctd align=\"center\">🏠 \u003Cstrong>Central Hub\u003C\u002Fstrong>\u003C\u002Ftd>\n      \u003Ctd align=\"center\">\n        \u003Ca href=\"https:\u002F\u002Fagent-tars.com\">\n          \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FVisit-Website-4F46E5?style=for-the-badge&logo=globe&logoColor=white\" alt=\"Website\" \u002F>\n        \u003C\u002Fa>\n      \u003C\u002Ftd>\n      \u003Ctd align=\"left\">Your gateway to Agent TARS ecosystem\u003C\u002Ftd>\n    \u003C\u002Ftr>\n      \u003Ctr>\n      \u003Ctd align=\"center\">📚 \u003Cstrong>Quick Start\u003C\u002Fstrong>\u003C\u002Ftd>\n      \u003Ctd align=\"center\">\n        \u003Ca href=\"https:\u002F\u002Fagent-tars.com\u002Fguide\u002Fget-started\u002Fquick-start.html\">\n          \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FGet-Started-06B6D4?style=for-the-badge&logo=rocket&logoColor=white\" alt=\"Quick Start\" \u002F>\n        \u003C\u002Fa>\n      \u003C\u002Ftd>\n      \u003Ctd align=\"left\">Zero to hero in 5 minutes\u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\n      \u003Ctd align=\"center\">🚀 \u003Cstrong>What's New\u003C\u002Fstrong>\u003C\u002Ftd>\n      \u003Ctd align=\"center\">\n        \u003Ca href=\"https:\u002F\u002Fagent-tars.com\u002Fbeta\">\n          \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FRead-Blog-F59E0B?style=for-the-badge&logo=rss&logoColor=white\" alt=\"Blog\" \u002F>\n        \u003C\u002Fa>\n      \u003C\u002Ftd>\n      \u003Ctd align=\"left\">Discover cutting-edge features & vision\u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\n      \u003Ctd align=\"center\">🛠️ \u003Cstrong>Developer Zone\u003C\u002Fstrong>\u003C\u002Ftd>\n      \u003Ctd align=\"center\">\n        \u003Ca href=\"https:\u002F\u002Fagent-tars.com\u002Fguide\u002Fget-started\u002Fintroduction.html\">\n          \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FView-Docs-10B981?style=for-the-badge&logo=gitbook&logoColor=white\" alt=\"Docs\" \u002F>\n        \u003C\u002Fa>\n      \u003C\u002Ftd>\n      \u003Ctd align=\"left\">Master every command & features\u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\n      \u003Ctd align=\"center\">🎯 \u003Cstrong>Showcase\u003C\u002Fstrong>\u003C\u002Ftd>\n      \u003Ctd align=\"center\">\n        \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fbytedance\u002FUI-TARS-desktop\u002Fissues\u002F842\">\n          \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FView-Examples-8B5CF6?style=for-the-badge&logo=github&logoColor=white\" alt=\"Examples\" \u002F>\n        \u003C\u002Fa>\n      \u003C\u002Ftd>\n      \u003Ctd align=\"left\">View use cases built by the official and community\u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\n      \u003Ctd align=\"center\">🔧 \u003Cstrong>Reference\u003C\u002Fstrong>\u003C\u002Ftd>\n      \u003Ctd align=\"center\">\n        \u003Ca href=\"https:\u002F\u002Fagent-tars.com\u002Fapi\u002F\">\n          \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FAPI-Reference-EF4444?style=for-the-badge&logo=book&logoColor=white\" alt=\"API\" \u002F>\n        \u003C\u002Fa>\n      \u003C\u002Ftd>\n      \u003Ctd align=\"left\">Complete technical reference\u003C\u002Ftd>\n    \u003C\u002Ftr>\n  \u003C\u002Ftbody>\n\u003C\u002Ftable>\n\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\u003Cbr\u002F>\n\n## UI-TARS Desktop\n\n\u003Cp align=\"center\">\n  \u003Cimg alt=\"UI-TARS\" width=\"260\" src=\".\u002Fapps\u002Fui-tars\u002Fresources\u002Ficon.png\">\n\u003C\u002Fp>\n\nUI-TARS Desktop is a native GUI agent for your local computer, driven by [UI-TARS](https:\u002F\u002Fgithub.com\u002Fbytedance\u002FUI-TARS) and Seed-1.5-VL\u002F1.6 series models.\n\n\u003Cdiv align=\"center\">\n\u003Cp>\n        &nbsp&nbsp 📑 \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2501.12326\">Paper\u003C\u002Fa> &nbsp&nbsp\n        | 🤗 \u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002FByteDance-Seed\u002FUI-TARS-1.5-7B\">Hugging Face Models\u003C\u002Fa>&nbsp&nbsp\n        | &nbsp&nbsp🫨 \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FpTXwYVjfcs\">Discord\u003C\u002Fa>&nbsp&nbsp\n        | &nbsp&nbsp🤖 \u003Ca href=\"https:\u002F\u002Fwww.modelscope.cn\u002Fcollections\u002FUI-TARS-bccb56fa1ef640\">ModelScope\u003C\u002Fa>&nbsp&nbsp\n\u003Cbr>\n🖥️ Desktop Application &nbsp&nbsp\n| &nbsp&nbsp 👓 \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fweb-infra-dev\u002Fmidscene\">Midscene (use in browser)\u003C\u002Fa> &nbsp&nbsp\n\u003C\u002Fp>\n\n\u003C\u002Fdiv>\n\n### Showcase\n\n\u003C!-- \u002F\u002F FIXME: Choose only two demo, one local computer and one remote computer showcase. -->\n\n|                                                          Instruction                                                           |                                                Local Operator                                                |                                               Remote Operator                                                |\n| :----------------------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------: |\n| Please help me open the autosave feature of VS Code and delay AutoSave operations for 500 milliseconds in the VS Code setting. | \u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fe0914ce9-ad33-494b-bdec-0c25c1b01a27\" height=\"300\" \u002F> | \u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F01e49b69-7070-46c8-b3e3-2aaaaec71800\" height=\"300\" \u002F> |\n|                    Could you help me check the latest open issue of the UI-TARS-Desktop project on GitHub?                     | \u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F3d159f54-d24a-4268-96c0-e149607e9199\" height=\"300\" \u002F> | \u003Cvideo src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F072fb72d-7394-4bfa-95f5-4736e29f7e58\" height=\"300\" \u002F> |\n\n### Features\n\n- 🤖 Natural language control powered by Vision-Language Model\n- 🖥️ Screenshot and visual recognition support\n- 🎯 Precise mouse and keyboard control\n- 💻 Cross-platform support (Windows\u002FMacOS\u002FBrowser)\n- 🔄 Real-time feedback and status display\n- 🔐 Private and secure - fully local processing\n\n### Quick Start\n\nSee [Quick Start](.\u002Fdocs\u002Fquick-start.md)\n\n## Contributing\n\nSee [CONTRIBUTING.md](.\u002FCONTRIBUTING.md).\n\n## License\n\nThis project is licensed under the Apache License 2.0.\n\n## Citation\n\nIf you find our paper and code useful in your research, please consider giving a star :star: and citation :pencil:\n\n```BibTeX\n@article{qin2025ui,\n  title={UI-TARS: Pioneering Automated GUI Interaction with Native Agents},\n  author={Qin, Yujia and Ye, Yining and Fang, Junjie and Wang, Haoming and Liang, Shihao and Tian, Shizuo and Zhang, Junda and Li, Jiahao and Li, Yunxin and Huang, Shijue and others},\n  journal={arXiv preprint arXiv:2501.12326},\n  year={2025}\n}\n```\n","UI-TARS-desktop 是一个基于多模态AI代理的桌面应用程序，它提供了基于UI-TARS模型的原生GUI代理。该项目的核心功能包括本地和远程计算机以及浏览器操作员的支持，旨在通过先进的多模态大语言模型实现类似人类的任务完成流程，并无缝集成多种现实世界的MCP工具。该应用特别适合需要在终端、计算机或浏览器上利用图形界面和视觉能力来增强工作流程的场景，如协作办公、自动化任务处理等。项目采用TypeScript编写，遵循Apache License 2.0开源许可协议。",2,"2026-06-11 02:54:47","top_language"]