[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-74726":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":23,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":38,"readmeContent":39,"aiSummary":40,"trendingCount":16,"starSnapshotCount":16,"syncStatus":41,"lastSyncTime":42,"discoverSource":43},74726,"OpenOmniBot","omnimind-ai\u002FOpenOmniBot","omnimind-ai","Your on-device AI assistant, capable of operating terminals and performing a wide range of tasks in the Android world || 你的端侧 AI 助手，她可以操作终端，也可以完成 Android 世界的广泛任务 ","https:\u002F\u002Fomnimind-ai.github.io\u002FOmniBot-Docs\u002F",null,"Dart",1705,67,6,10,0,11,95,282,48,18.5,"Other",false,"main",[26,27,28,29,30,31,32,33,34,35,36,37],"agent","ai","alpine","android","automation","bot","claw","codex","gui","linux","on-device","skills","2026-06-12 02:03:27","\u003Cp align=\"center\">\n  \u003Cpicture>\n    \u003Cimg alt=\"OpenOmniBot\" src=\"docs\u002Fpic\u002FOmniBot.png\" width=\"50%\">\n  \u003C\u002Fpicture>\n\u003C\u002Fp>\n\n\u003Ch3 align=\"center\">\nYour On-Device AI Assistant\n\u003C\u002Fh3>\n\n\u003Cdiv align=\"center\">\n  \u003Cimg alt=\"GitHub Repo stars\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fomnimind-ai\u002FOpenOmniBot\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fomnimind-ai\u002FOpenOmniBot\u002Freleases\u002Flatest\">\u003Cimg alt=\"GitHub Release\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002Fomnimind-ai\u002FOpenOmniBot\">\u003C\u002Fa>\n  \u003Cbr>\n  \u003Ca href=\"https:\u002F\u002Fomnimind.com.cn\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FAbout_us-万象智维-purple.svg?color=%234b0c77\" alt=\"OmniMind\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Flinux.do\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLinux_Do-Community-yellow.svg?color=%23ac3712\" alt=\"Linux Do Community\">\u003C\u002Fa>\n  \u003Ca href=\"#community\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FWeChat-Group-lightgreen\" alt=\"WeChat Group\"\u002F>\n  \u003C\u002Fa>\n\u003C\u002Fdiv>\n\n\u003Cp align=\"center\">\n|\n\u003Ca href=\"#use-cases\">\u003Cb>Demo\u003C\u002Fb>\u003C\u002Fa>\n|\n\u003Ca href=\"#quick-start\">\u003Cb>Quick Start\u003C\u002Fb>\u003C\u002Fa>\n|\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fomnimind-ai\u002FOpenOmniBot\u002Freleases\">\u003Cb>Release\u003C\u002Fb>\u003C\u002Fa>\n|\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fomnimind-ai\u002FOpenOmniBot\u002Fissues\">\u003Cb>Issues\u003C\u002Fb>\u003C\u002Fa>\n|\n\u003Ca href=\"README.md\">\u003Cb>English\u003C\u002Fb>\u003C\u002Fa> \n|\n\u003Ca href=\"README.zh-CN.md\">\u003Cb>简体中文\u003C\u002Fb>\u003C\u002Fa>\n|\n\u003C\u002Fp>\n\n> Unlike traditional mobile AI chat apps, OpenOmniBot runs directly on your device and can operate your Android phone like a human, including apps, gestures, and system settings.\n\nOpenOmniBot is an on-device AI agent built with native Android Kotlin and Flutter. Instead of stopping at chat, it focuses on the full loop of **understand -> decide -> execute -> reflect**.\n\n\u003Ch2 id=\"core-capabilities\">Core Capabilities\u003C\u002Fh2>\n\n- **Extensible tool ecosystem**: Skills, Alpine environment, browser access, MCP, and Android system-level tools.\n- **Phone task automation**: Uses vision models to understand and operate mobile interfaces.\n- **System-level actions**: Supports scheduled tasks, alarms, calendar creation\u002Fquery\u002Fupdate, and audio playback control.\n- **Memory system**: Short-term and long-term memory with embedding support.\n- **Productivity tools**: Read and write files, browse the workspace, use the browser, and access the terminal.\n\n\u003Ch2 id=\"quick-start\">Quick Start\u003C\u002Fh2>\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Ftutorial\u002Fexample.png\" alt=\"Example\" width=\"260\" \u002F>\n\u003C\u002Fp>\n\n### Configure the app\n\nOpen the settings page from the left sidebar:\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Ftutorial\u002Ftwo.png\" alt=\"Configure AI capabilities\" width=\"260\" \u002F>\n  \u003Cimg src=\"docs\u002Ftutorial\u002Fthree.png\" alt=\"Configure AI providers\" width=\"420\" \u002F>\n\u003C\u002Fp>\n\nThen open the scenario model settings:\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Ftutorial\u002Ffour.png\" alt=\"Configure AI models\" width=\"260\" \u002F>\n\u003C\u002Fp>\n\nNote: `Memory embedding` requires an embedding model. For the best overall experience, the other scenarios should use multimodal or vision-capable models whenever possible.\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Ftutorial\u002Ffive.png\" alt=\"Alpine environment\" width=\"260\" \u002F>\n\u003C\u002Fp>\n\nThe app usually initializes the Alpine environment automatically on startup, and you can also manage that environment from the same settings area.\n\n\u003Ch2 id=\"use-cases\">Use Cases\u003C\u002Fh2>\n\n### Skills\n\nYou can ask OmniBot to install a skill by simply sending it the repository link. Recommended collection: https:\u002F\u002Fgithub.com\u002FOpenMinis\u002FMinisSkills\n\nEnable or disable skills from the skill repository:\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Ftutorial\u002Fsix.png\" alt=\"Skill store\" width=\"260\" \u002F>\n  \u003Cimg src=\"docs\u002Ftutorial\u002Fseven.png\" alt=\"Skill example\" width=\"260\" \u002F>\n\u003C\u002Fp>\n\n### VLM tasks\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Ftutorial\u002Feight.png\" alt=\"VLM task\" width=\"260\" \u002F>\n\u003C\u002Fp>\n\nBefore starting a task, open the chat page and grant all required permissions from the top-right corner.\n\n### Local model inference\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Ftutorial\u002Fnine.png\" alt=\"Local inference\" width=\"260\" \u002F>\n\u003C\u002Fp>\n\nSupports both MNN and llama backends.\n\n### Scheduled tasks\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Ftutorial\u002Ften.png\" alt=\"Scheduled task\" width=\"260\" \u002F>\n  \u003Cimg src=\"docs\u002Ftutorial\u002Feleven.png\" alt=\"Timing\" width=\"260\" \u002F>\n\u003C\u002Fp>\n\nScheduled tasks can execute work such as VLM tasks and subagent flows. Alarms are reminder-only. A subagent can be assigned a complete task and behaves like a full agent.\n\n### Browser\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Ftutorial\u002Ftwelve.png\" alt=\"Browser\" width=\"260\" \u002F>\n\u003C\u002Fp>\n\n### Workspace\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Ftutorial\u002Fworkspace.jpg\" alt=\"Workspace\" width=\"260\" \u002F>\n\u003C\u002Fp>\n\n\u003Ch2 id=\"development-guide\">Development Guide\u003C\u002Fh2>\n\n### Requirements\n\n- Flutter SDK `3.9.2+`\n- JDK `11+`\n\n### Get the code\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fomnimind-ai\u002FOpenOmniBot.git\ncd OpenOmniBot\n\n# Required only when building the full omniinfer edition.\ngit submodule update --init third_party\u002Fomniinfer\ngit -C third_party\u002Fomniinfer submodule update --init framework\u002Fmnn\ngit -C third_party\u002Fomniinfer submodule update --init framework\u002Fllama.cpp\n\ncd ui\nflutter pub get\n```\n\nIf Flutter reports `Could not read script '...\u002Fui\u002F.android\u002Finclude_flutter.groovy'`, run:\n\n```bash\nflutter clean\nflutter pub get\n```\n\n### Build and install\n\n```bash\ncd ..\n\n# Slim standard edition, without local inference\n.\u002Fgradlew :app:installDevelopStandardDebug -Ptarget=lib\u002Fmain_standard.dart\n\n# Full omniinfer edition, with local inference\n.\u002Fgradlew :app:installDevelopOmniinferDebug -Ptarget=lib\u002Fmain_omniinfer.dart\n```\n\n\u003Ch2 id=\"architecture\">Architecture Overview\u003C\u002Fh2>\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Fpic\u002Farchitect.svg\" alt=\"Architecture\" width=\"100%\" \u002F>\n\u003C\u002Fp>\n\n```text\nOpenOmniBot\u002F\n├── app\u002F                        # Android host app: entry point, agent orchestration, system abilities, MCP, services\n├── ui\u002F                         # Flutter UI: chat, settings, tasks, memory, and web chat bundle\n├── baselib\u002F                    # Shared core libraries: database, storage, networking, model config, OCR, permissions\n├── assists\u002F                    # Automation engine: task scheduling, state machine, visual detection, execution control\n├── accessibility\u002F              # Accessibility and screen perception: accessibility service, screenshots, projection\n├── omniintelligence\u002F           # AI abstractions: model protocol, task status, request\u002Fresponse models\n├── uikit\u002F                      # Native overlay UI: floating ball, overlay panels, half-screen surfaces\n├── third_party\u002Fomniinfer\u002F      # Local inference runtime and Android integration modules\n└── ReTerminal\u002Fcore\u002F            # Embedded terminal experience modules\n```\n\n\u003Ch2 id=\"community\">Community\u003C\u002Fh2>\n\nThanks to the community （including [LINUX](linux.do)）developers supporting OpenOmniBot.\n\nSpecial thanks to these open-source projects:\n\n- https:\u002F\u002Fgithub.com\u002FRohitKushvaha01\u002FReTerminal\n- https:\u002F\u002Fgithub.com\u002FOpenMinis\n\n\u003Ctable align=\"center\">\n  \u003Ctr>\n    \u003Ctd align=\"center\">\n      \u003Cimg src=\"docs\u002Fpic\u002Fwechat.jpg\" alt=\"WeChat Group\" width=\"220\"\u002F>\u003Cbr\u002F>\n    \u003C\u002Ftd>\n  \u003C\u002Ftr>\n\u003C\u002Ftable>\nJoin Discord: https:\u002F\u002Fdiscord.gg\u002FWnBvBXgykD","OpenOmniBot 是一个运行在设备端的 AI 助手，能够操作 Android 手机并执行广泛的任务。它使用 Kotlin 和 Flutter 构建，专注于理解、决策、执行和反思的完整闭环过程。核心功能包括可扩展的工具生态系统、手机任务自动化、系统级操作、记忆系统以及生产力工具等。适合需要在移动设备上进行自动化操作、提高工作效率或希望拥有更智能助手体验的场景。",2,"2026-06-11 03:50:33","high_star"]