{"id":47616377,"url":"https://github.com/omnimind-ai/openomnibot","last_synced_at":"2026-05-27T05:17:04.925Z","repository":{"id":345789264,"uuid":"1185430378","full_name":"omnimind-ai/OpenOmniBot","owner":"omnimind-ai","description":"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 ","archived":false,"fork":false,"pushed_at":"2026-05-18T15:24:32.000Z","size":415096,"stargazers_count":1432,"open_issues_count":14,"forks_count":45,"subscribers_count":3,"default_branch":"main","last_synced_at":"2026-05-18T17:27:26.531Z","etag":null,"topics":["agent","ai","alpine","android","automation","bot","claw","codex","gui","linux","on-device","skills"],"latest_commit_sha":null,"homepage":"https://omnimind-ai.github.io/OmniBot-Docs/","language":"Kotlin","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/omnimind-ai.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-03-18T15:18:51.000Z","updated_at":"2026-05-18T16:02:02.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/omnimind-ai/OpenOmniBot","commit_stats":null,"previous_names":["omnimind-ai/openomnibot"],"tags_count":74,"template":false,"template_full_name":null,"purl":"pkg:github/omnimind-ai/OpenOmniBot","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/omnimind-ai%2FOpenOmniBot","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/omnimind-ai%2FOpenOmniBot/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/omnimind-ai%2FOpenOmniBot/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/omnimind-ai%2FOpenOmniBot/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/omnimind-ai","download_url":"https://codeload.github.com/omnimind-ai/OpenOmniBot/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/omnimind-ai%2FOpenOmniBot/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33426013,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-23T22:14:44.296Z","status":"online","status_checked_at":"2026-05-24T02:00:06.296Z","response_time":57,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent","ai","alpine","android","automation","bot","claw","codex","gui","linux","on-device","skills"],"created_at":"2026-04-01T21:29:33.890Z","updated_at":"2026-05-24T08:02:05.301Z","avatar_url":"https://github.com/omnimind-ai.png","language":"Kotlin","funding_links":[],"categories":["CLIs"],"sub_categories":["Usage"],"readme":"\u003cp align=\"center\"\u003e\n  \u003cpicture\u003e\n    \u003cimg alt=\"OpenOmniBot\" src=\"docs/pic/OmniBot.png\" width=\"50%\"\u003e\n  \u003c/picture\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"README.md\"\u003e\u003cb\u003eEnglish\u003c/b\u003e\u003c/a\u003e |\n  \u003ca href=\"README.zh-CN.md\"\u003e\u003cb\u003e简体中文\u003c/b\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n\u003ch3 align=\"center\"\u003e\nYour On-Device AI Assistant\n\u003c/h3\u003e\n\n\u003cdiv align=\"center\"\u003e\n  \u003cimg alt=\"GitHub Repo stars\" src=\"https://img.shields.io/github/stars/omnimind-ai/OpenOmniBot\"\u003e\n  \u003ca href=\"https://github.com/omnimind-ai/OpenOmniBot/releases/latest\"\u003e\u003cimg alt=\"GitHub Release\" src=\"https://img.shields.io/github/v/release/omnimind-ai/OpenOmniBot\"\u003e\u003c/a\u003e\n  \u003cbr\u003e\n  \u003ca href=\"https://omnimind.com.cn\"\u003e\u003cimg src=\"https://img.shields.io/badge/About_us-万象智维-purple.svg?color=%234b0c77\" alt=\"OmniMind\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://linux.do\"\u003e\u003cimg src=\"https://img.shields.io/badge/Linux_Do-Community-yellow.svg?color=%23ac3712\" alt=\"Linux Do Community\"\u003e\u003c/a\u003e\n  \u003ca href=\"#community\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/WeChat-Group-lightgreen\" alt=\"WeChat Group\"/\u003e\n  \u003c/a\u003e\n\u003c/div\u003e\n\n\u003cp align=\"center\"\u003e\n|\n\u003ca href=\"#use-cases\"\u003e\u003cb\u003eDemo\u003c/b\u003e\u003c/a\u003e\n|\n\u003ca href=\"#quick-start\"\u003e\u003cb\u003eQuick Start\u003c/b\u003e\u003c/a\u003e\n|\n\u003ca href=\"https://github.com/omnimind-ai/OpenOmniBot/releases\"\u003e\u003cb\u003eRelease\u003c/b\u003e\u003c/a\u003e\n|\n\u003ca href=\"https://github.com/omnimind-ai/OpenOmniBot/issues\"\u003e\u003cb\u003eIssues\u003c/b\u003e\u003c/a\u003e\n|\n\u003c/p\u003e\n\n\u003e 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 -\u003e decide -\u003e execute -\u003e reflect**.\n\n\u003ch2 id=\"core-capabilities\"\u003eCore Capabilities\u003c/h2\u003e\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/query/update, 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\"\u003eQuick Start\u003c/h2\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/tutorial/example.jpg\" alt=\"Example\" width=\"260\" /\u003e\n\u003c/p\u003e\n\n### Configure the app\n\nOpen the settings page from the left sidebar:\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/tutorial/1.png\" alt=\"Configure AI capabilities\" width=\"420\" /\u003e\n  \u003cimg src=\"docs/tutorial/2.png\" alt=\"Configure AI providers\" width=\"260\" /\u003e\n\u003c/p\u003e\n\nThen open the scenario model settings:\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/tutorial/3.png\" alt=\"Configure AI models\" width=\"260\" /\u003e\n\u003c/p\u003e\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\"\u003e\n  \u003cimg src=\"docs/tutorial/alpine.jpg\" alt=\"Alpine environment\" width=\"260\" /\u003e\n\u003c/p\u003e\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\"\u003eUse Cases\u003c/h2\u003e\n\n### Skills\n\nYou can ask OmniBot to install a skill by simply sending it the repository link. Recommended collection: https://github.com/OpenMinis/MinisSkills\n\nEnable or disable skills from the skill repository:\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/tutorial/skills_store.jpg\" alt=\"Skill store\" width=\"260\" /\u003e\n  \u003cimg src=\"docs/tutorial/skills_example.jpg\" alt=\"Skill example\" width=\"260\" /\u003e\n\u003c/p\u003e\n\n### VLM tasks\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/tutorial/vlm.jpg\" alt=\"VLM task\" width=\"260\" /\u003e\n\u003c/p\u003e\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\"\u003e\n  \u003cimg src=\"docs/tutorial/local_inference.jpg\" alt=\"Local inference\" width=\"260\" /\u003e\n\u003c/p\u003e\n\nSupports both MNN and llama backends.\n\n### Scheduled tasks\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/tutorial/timed.jpg\" alt=\"Scheduled task\" width=\"260\" /\u003e\n  \u003cimg src=\"docs/tutorial/timing.jpg\" alt=\"Timing\" width=\"260\" /\u003e\n\u003c/p\u003e\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\"\u003e\n  \u003cimg src=\"docs/tutorial/browser.jpg\" alt=\"Browser\" width=\"260\" /\u003e\n\u003c/p\u003e\n\n### Workspace\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"docs/tutorial/workspace.jpg\" alt=\"Workspace\" width=\"260\" /\u003e\n\u003c/p\u003e\n\n\u003ch2 id=\"development-guide\"\u003eDevelopment Guide\u003c/h2\u003e\n\n### Requirements\n\n- Flutter SDK `3.9.2+`\n- JDK `11+`\n\n### Get the code\n\n```bash\ngit clone https://github.com/omnimind-ai/OpenOmniBot.git\ncd OpenOmniBot\n\ngit submodule update --init third_party/omniinfer\ngit -C third_party/omniinfer submodule update --init framework/mnn\ngit -C third_party/omniinfer submodule update --init framework/llama.cpp\n\ncd ui\nflutter pub get\n```\n\nIf Flutter reports `Could not read script '.../ui/.android/include_flutter.groovy'`, run:\n\n```bash\nflutter clean\nflutter pub get\n```\n\n### Build and install\n\n```bash\ncd ..\n./gradlew :app:installDevelopDebug\n```\n\n\u003ch2 id=\"architecture\"\u003eArchitecture Overview\u003c/h2\u003e\n\n```text\nOpenOmniBot/\n├── app/                        # Android host app: entry point, agent orchestration, system abilities, MCP, services\n├── ui/                         # Flutter UI: chat, settings, tasks, memory, and web chat bundle\n├── baselib/                    # Shared core libraries: database, storage, networking, model config, OCR, permissions\n├── assists/                    # Automation engine: task scheduling, state machine, visual detection, execution control\n├── accessibility/              # Accessibility and screen perception: accessibility service, screenshots, projection\n├── omniintelligence/           # AI abstractions: model protocol, task status, request/response models\n├── uikit/                      # Native overlay UI: floating ball, overlay panels, half-screen surfaces\n├── third_party/omniinfer/      # Local inference runtime and Android integration modules\n└── ReTerminal/core/            # Embedded terminal experience modules\n```\n\n\u003ch2 id=\"community\"\u003eCommunity\u003c/h2\u003e\n\nThanks to the community （including [LINUX](linux.do)）developers supporting OpenOmniBot.\n\nSpecial thanks to these open-source projects:\n\n- https://github.com/RohitKushvaha01/ReTerminal\n- https://github.com/OpenMinis\n\n\u003ctable align=\"center\"\u003e\n  \u003ctr\u003e\n    \u003ctd align=\"center\"\u003e\n      \u003cimg src=\"docs/pic/wechat.png\" alt=\"WeChat Group\" width=\"220\"/\u003e\u003cbr/\u003e\n      \u003cb\u003eWeChat Group\u003c/b\u003e\n    \u003c/td\u003e\n  \u003c/tr\u003e\n\u003c/table\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fomnimind-ai%2Fopenomnibot","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fomnimind-ai%2Fopenomnibot","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fomnimind-ai%2Fopenomnibot/lists"}