[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-fiatrete--OpenDAN-Personal-AI-OS":3,"tool-fiatrete--OpenDAN-Personal-AI-OS":64},[4,17,27,35,43,56],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,3,"2026-04-05T11:01:52",[13,14,15],"开发框架","图像","Agent","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":23,"last_commit_at":24,"category_tags":25,"status":16},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",138956,2,"2026-04-05T11:33:21",[13,15,26],"语言模型",{"id":28,"name":29,"github_repo":30,"description_zh":31,"stars":32,"difficulty_score":23,"last_commit_at":33,"category_tags":34,"status":16},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",107662,"2026-04-03T11:11:01",[13,14,15],{"id":36,"name":37,"github_repo":38,"description_zh":39,"stars":40,"difficulty_score":23,"last_commit_at":41,"category_tags":42,"status":16},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[13,26],{"id":44,"name":45,"github_repo":46,"description_zh":47,"stars":48,"difficulty_score":23,"last_commit_at":49,"category_tags":50,"status":16},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[14,51,52,53,15,54,26,13,55],"数据工具","视频","插件","其他","音频",{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":10,"last_commit_at":62,"category_tags":63,"status":16},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,"2026-04-04T04:44:48",[15,14,13,26,54],{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":69,"readme_en":70,"readme_zh":71,"quickstart_zh":72,"use_case_zh":73,"hero_image_url":74,"owner_login":75,"owner_name":75,"owner_avatar_url":76,"owner_bio":77,"owner_company":77,"owner_location":77,"owner_email":77,"owner_twitter":77,"owner_website":77,"owner_url":78,"languages":79,"stars":107,"forks":108,"last_commit_at":109,"license":110,"difficulty_score":10,"env_os":111,"env_gpu":112,"env_ram":112,"env_deps":113,"category_tags":126,"github_topics":127,"view_count":10,"oss_zip_url":77,"oss_zip_packed_at":77,"status":16,"created_at":134,"updated_at":135,"faqs":136,"releases":165},430,"fiatrete\u002FOpenDAN-Personal-AI-OS","OpenDAN-Personal-AI-OS","OpenDAN is an open source Personal AI OS , which consolidates various AI modules in one place for your personal use.","OpenDAN-Personal-AI-OS 是一个开源的个人人工智能操作系统，旨在将多种 AI 功能整合到一个统一平台中，让用户轻松创建和管理个性化的 AI 助手。它解决了当前 AI 工具分散、难以协同的问题，通过模块化设计支持多个 AI 代理（如日程助理、知识管家、英语老师、命令行助手等）协同工作，并能连接 Telegram、邮件等常用服务，甚至控制智能家居设备。\n\nOpenDAN 特别适合对 AI 感兴趣的技术爱好者、开发者以及希望在本地私有环境中使用 AI 的用户。它支持在 PC、Mac、树莓派、NAS 等多种设备上通过 Docker 快速部署，并允许用户切换本地运行的开源大模型（如 LLaMa），保障数据隐私。当前版本已实现基础框架、私有知识库构建、多智能体协作流程（如自动生成有声童话书）等功能，未来还将推出应用商店式的一键安装体验。项目仍处于早期阶段，欢迎社区参与共建。","# **OpenDAN : Your Personal AIOS**\n\n[![Official Website](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FOfficial%20Website-opendan.ai-blue?style=flat&logo=world&logoColor=white)](https:\u002F\u002Fopendan.ai)\n[![GitHub Repo stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ffiatrete\u002FOpenDAN-Personal-AI-OS?style=social)](https:\u002F\u002Fgithub.com\u002Ffiatrete\u002FOpenDAN-Personal-AI-OS\u002Fstargazers)\n[![Twitter Follow](https:\u002F\u002Fimg.shields.io\u002Ftwitter\u002Ffollow\u002FopenDAN_AI?style=social)](https:\u002F\u002Ftwitter.com\u002FopenDAN_AI)\n\nOpenDAN is an open source Personal AI OS , which consolidates various AI modules in one place for your personal use.\n\n## **Project Introduction**\n\nOpenDAN (Open and Do Anything Now with AI) is revolutionizing the AI landscape with its Personal AI Operating System. Designed for seamless integration of diverse AI modules, it ensures unmatched interoperability. OpenDAN empowers users to craft powerful AI agents—from butlers and assistants to personal tutors and digital companions—all while retaining control. These agents can team up to tackle complex challenges, integrate with existing services, and command smart(IoT) devices.\n\nWith OpenDAN, we're putting AI in your hands, making life simpler and smarter.\n\nThis project is still in its very early stages, and there may be significant changes in the future.\n\n## **Updates**\n\nAfter over three months of development, the code for the first version of OpenDAN MVP (0.5.1), driven by the new contributor `waterflier`, has been merged into the Master branch. This version has realized many concepts proposed in the PoC version of OpenDAN and completed the basic framework of the OS, especially defining the application form on AIOS. Currently, the 0.5.1 version operates in an \"all-in-one\" mode. For 0.5.2, we will advance the formal implementation of the OpenDAN OS kernel based on the partial framework code of the [CYFS Owner Online Device(OOD) OS](https:\u002F\u002Fgithub.com\u002Fbuckyos\u002FCYFS) that has already been completed.\n\n![MVP](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ffiatrete_OpenDAN-Personal-AI-OS_readme_01dbec1b42b3.png)\n\n**The main new features of OpenDAN 0.5.1 (MVP) :**\n\n- [x] Rapid installation and deployment of OpenDAN based on Docker, making OpenDAN compatible with a wide range of hardware environments (PC\u002FMac\u002FRaspberryPI\u002FNAS) through Docker.\n- [x] AI Agent's large language model can be switched, now supporting locally running the open-source model (LLaMa).\n- [x] Introduction of more built-in AI Agents:\n    - [x] Personal Assistant Jarvis : Consultant.Assistant who anages your schedule and communication records. ChatGPT alternative.\n    - [x] Information Assistant Mia : Manage your personal data and sort it into a knowledge base\n    - [x] Private English Teacher Tracy : Your private English teacher\n    - [x] ai_bash (for developers) :No longer need to memory complicated command line parameters! Bash is used by \"Find FILES in ~\u002FDocuments that Contain OpenDAN\".\n- [x] Connectivity to AI Agent\u002FWorkflow via Telegram\u002FEmail.\n- [x] Building a local private Knowledge Base based on existing file or email spiders, enabling AI Agent access to personal data.\n    - [x] Supports text files and common image formats.\n    - [ ] Supports other common formats.\n- [x] Implemented Workflow: Collaboration of Agents to solve more complex issues.\n    - [x] Built-in Workflow story_maker, integrated the AIGC tool to create audio fairy tale books.\n- [x] Distributed AI computing core available for complex selections.\n- [x] Manual download and installation of new Agent\u002FWorkflow.\n- [ ] OpenDAN Store : Agent\u002FWorkflow\u002FModels One-Stop installation  (Delayed to 0.5.2).\n\n[Try it NOW!](.\u002Fdoc\u002FQuickStart.md)\n\nDevelopers [click here](https:\u002F\u002Fgithub.com\u002Ffiatrete\u002FOpenDAN-Personal-AI-OS\u002Fissues\u002F46) to learn about OpenDan's system development updates.\n\n## **Intro video - What is OpenDAN?**\n\nClick the image below for a demo:\n\n[![Intro Video](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ffiatrete_OpenDAN-Personal-AI-OS_readme_8726670e3d8a.png)](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=l2QmsIOXhdQ \"Intro Video\")\n\n## **Subscribe to updates here**\n\n\u003Chttps:\u002F\u002Ftwitter.com\u002FopenDAN_AI>\n\n## **Installation**\n\nThere are two ways to install the Internal Test Version of OpenDAN:\n\n1. Installation through docker, this is also the installation method we recommend now\n2. Installing through the source code, this method may encounter some traditional Python dependence problems and requires you to have a certain ability to solve.But if you want to do secondary development of OpenDAN, this method is necessary.\n\n### Preparation before installation\n\n1. Docker environment\nThis article does not introduce how to install the docker, execute it under your console\n\n```\ndocker -version\n```\n\nIf you can see the docker version number (> 20.0), it means that you have installed Docker.\nIf you don't know how to install docker, you can refer to [here](https:\u002F\u002Fdocs.docker.com\u002Fengine\u002Finstall\u002F)\n\n2. OpenAI API Token\nIf there is no api token, you can apply for [here](https:\u002F\u002Fbeta.openai.com\u002F)\n\nApplying for the API Token may have some thresholds for new players. You can find friends around you, and he can give you a temporary, or join our internal test experience group. We will also release some free experience API token from time to time.These token is limited to the maximum consumption and effective time\n\n### Install\n\nAfter executing the following command, you can install the Docker Image of OpenDAN\n\n```\ndocker pull paios\u002Faios:latest\n```\n\n## **Run OpenDAN**\n\nThe first Run of OpenDAN needs to be initialized. You need to enter some information in the process of initialization. Therefore, when starting the docker, remember to bring the -it parameter.\n\nOpenDAN is your Personal AIOS, so it will generate some important personal data (such as chat history with agent, schedule data, etc.) during its operation. These data will be stored on your local disk. ThereforeWe recommend that you mount the local disk into the container of Docker so that the data can be guaranteed.\n\n```\ndocker run -v \u002Fyour\u002Flocal\u002Fmyai\u002F:\u002Froot\u002Fmyai --name aios -it paios\u002Faios:latest \n```\n\nIn the above command, we also set up a Docker instance for Docker Run named AIOS, which is convenient for subsequent operations.You can also use your favorite name instead.\n\nAfter the first operation of the docker instance is created, it only needs to be executed again:\n\n```\ndocker start -ai aios\n```\n\nIf you plan to run in a service mode (NO UI), you don't need to bring the -AI parameter:\n\n```\ndocker start aios\n```\n\n### Hello, Jarvis\n\nAfter the configuration is completed, you will enter a AIOS Shell, which is similar to Linux Bash and similar. The meaning of this interface is:\nThe current user \"username\" is communicating with the name \"Agent\u002FWorkflow of Jarvis\". The current topic is default.\n\nSay Hello to your private AI assistant Jarvis !\n\n**If everything is OK, you will get a reply from Jarvis after a moment .At this time, the OpenDAN system is running .**\n![MVP](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ffiatrete_OpenDAN-Personal-AI-OS_readme_d0120f5aa20e.png)\n\n## **Core Concepts and Features of OpenDAN**\n1. **AI Agent**: Driven by a large language model, having own memory.The AI Agent completes tasks through natural language interaction.\n2. **AI Workflow**: Organize different AI Agents into an AI Agent Group to complete complex tasks.\n![workflow](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ffiatrete_OpenDAN-Personal-AI-OS_readme_3531254a400d.png)\n3. **AI Environment**: Supports AI Agents to access file systems, IoT devices, network services, smart contracts, and everything on today's internet once authorized.\n4. **AI Marketplace**: Offer a solution for one-click installation and use of various AI applications, helping users easily access and manage AI apps.\n5. **AI Model Solution**: Provide a unified entry point for model search, download, and access control, making it convenient for users to find and use models suitable for their needs.\n6. **Hardware-specific optimization**: Optimize for specific hardware to enable smooth local running of most open-source AI applications.\n7. **Strict Privacy Protection and Management**: Strictly manage personal data, ranging from family albums to chat records and social media records, and provide a unified access control interface for AI applications.\n8. **Personal knowledge Base**:\n9. **Integrated AIGC Workflow**: Offer AIGC Agent\u002FWorkflow for users to train their own voice models, Lora models, knowledge models, etc., using personal data. Based on these private model data, integrate the most advanced AIGC algorithm to help people release creativity easily and build more COOL and more personalized content.\n10. **Development Framework**: Provide a development framework for customizing AI assistants for specific purposes, making it easy for developers to create unique AI applications \u002F service for their customers.\n\n## **Deeply Understanding OpenDAN**\n\n### Build OpenDAN from source code\n1. Install the latest version of python (>= 3.11) and pip\n1. Clone the source code\n   ```\n   git clone https:\u002F\u002Fgithub.com\u002Ffiatrete\u002FOpenDAN-Personal-AI-OS.git\n   cd OpenDAN-Personal-AI-OS\n   ```\n1. Enable virtual env\n   ```\n   virtualenv venv\n   source .\u002Fvenv\u002Fbin\u002Factivate\n   ```\n1. Install the dependent python library\n   ```\n   pip install -r .\u002Fsrc\u002Frequirements.txt\n   ```\n   Waiting for installation.\n1. Start OpenDAN through aios_shell\n   ```\n   python .\u002Fsrc\u002Fsrvice\u002Faios_shell\u002Faios_shell.py\n   ```\n   1. If seeing error saying `No ffmpeg exe could be found`, you need to install it manually from https:\u002F\u002Fwww.ffmpeg.org\u002F\n      \nNow OpenDAN runs in the development mode, and the directory is:\n- AIOS_ROOT: .\u002Frootfs (\u002Fopt\u002Faios in docker)\n- AIOS_MYAI: ~\u002Fmyai (\u002Froot\u002Fmyai in docer)\n\n### OpenDAN Cookbook\n\n#### Chapter 1: Hello, Jarvis! \n- 1.1 Installation of OpenDAN\n- 1.2 Initial Configuration of OpenDAN\n- 1.3 Introduction to Agent and Using Jarvis\n- 1.4 Communicating with Jarvis Anytime and Anywhere via Telegram and Email\n- 1.5 Using Jarvis in Daily Life\n- 1.6 Mia and the Knowledge Base\n- 1.7 Introduction to Other Built-in Agents\n\n[Click to Read](.\u002Fdoc\u002FQuickStart.md)\n\n#### Chapter 2: AIGC Workflow （Coming Soon）\nUsing Workflow to activate the AIGC feature and let the Agent team (director, artist, and narrator) collaborate to create a unique bedtime story for your child based on your instructions!\n\n- 2.1 Using Workflow `story_maker`\n- 2.2 Enabling Your Own AIGC Computation Node\n- 2.3 Training and Using Your Own AIGC LoRA Model.\n\n#### Chapter 3: Develop Agent\u002FWorkflow on OpenDAN (Writing)\n\nWhat's the most crucial design aspect of an operating system? Defining new forms of applications!\n\nThis article will systematically introduce what future Intelligence Applications look like, how to develop and release Intelligence Applications, and how to connect new-age Intelligence Applications with traditional computing.\n\n- 3.1 Developing Agents that Run on OpenDAN\n- 3.2 Developing Workflows that Run on OpenDAN\n- 3.3 Extending the Environments Accessible by Agents\n- 3.4 Releasing Various Models Trained by Yourself\n- 3.5 Expanding More Tunnels to Enhance the Accessibility of Agents\u002FWorkflow\n- 3.6 Developing Traditional dApps on the Personal Server.\n\n#### Chapter 4: OpenDAN Kernel Development (Writing)\nThis article will introduce the design and implementation of OpenDAN's architecture\n\n![architecture](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ffiatrete_OpenDAN-Personal-AI-OS_readme_cca974aba1d1.png)\n\n\n- 4.1 Integrate your own LLM core into OpenDAN.\n- 4.2 Knowledge Base: Expand more file types, allowing Agents to better understand your knowledge graph.\n- 4.3 AI computation engine, integrating more AIGC capabilities, and accessing more computational power.\n- 4.4 OpenDAN's state management: File system and vector database.\n- 4.5 Kernel services and permission isolation.\n- 4.6 Smart gateway.\n\n\n## **Upcoming Roadmap**\n\n- [x] Release PoC of OpenDAN\n- [x] **0.5.1** Implement personal data embeding to Knownlege-Base(KB) via Spider, followed by access by AI Agent\n- [ ] 0.5.2 Separate user mode and kernel mode, Knowledge Base supports scene format and more Spiders, supports personal AIGC model training\n- [ ] 0.5.3 Release Home Environment, allowing Agents to access and control your home's IoT devices\n- [ ] 0.5.x Official version of OpenDAN Alpha. Release OpenDAN SDK 1.0.\n\n## **Contributing**\n\nWe welcome community members to contribute to the project, including but not limited to submitting issues, improving documentation, fixing bugs, or providing new features. You can participate in the contribution through the following ways:\n\n- Submit an Issue in the GitHub repository\n- Submit a Pull Request to the repository\n- Participate in discussions and development\n\nOpenDAN utilizes the SourceDAO smart contract to incentivize the community. Developers who contribute can receive rewards in the form of OpenDAN DAO Tokens. DAO Token holders can collaboratively determine the development direction of OpenDAN. You can learn more about the rules of SourceDAO by reading this article（ https:\u002F\u002Fgithub.com\u002Ffiatrete\u002FOpenDAN-Personal-AI-OS\u002Fissues\u002F25 ）\n\nThe DAO governance page for OpenDAN is under development. Once officially launched, all contributors will receive DAO Tokens according to the rules.\n\n## **⭐Star History**\n\n[![Star History Chart](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ffiatrete_OpenDAN-Personal-AI-OS_readme_f0beef7449f3.png)](https:\u002F\u002Fstar-history.com\u002F#fiatrete\u002FOpenDAN-Personal-AI-Server-OS&Date)\n\n## **License**\n\nThe current license is MIT, but it will transition to SourceDAO in the future.\n","# **OpenDAN：你的个人 AI 操作系统（AIOS）**\n\n[![Official Website](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FOfficial%20Website-opendan.ai-blue?style=flat&logo=world&logoColor=white)](https:\u002F\u002Fopendan.ai)\n[![GitHub Repo stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ffiatrete\u002FOpenDAN-Personal-AI-OS?style=social)](https:\u002F\u002Fgithub.com\u002Ffiatrete\u002FOpenDAN-Personal-AI-OS\u002Fstargazers)\n[![Twitter Follow](https:\u002F\u002Fimg.shields.io\u002Ftwitter\u002Ffollow\u002FopenDAN_AI?style=social)](https:\u002F\u002Ftwitter.com\u002FopenDAN_AI)\n\nOpenDAN 是一个开源的个人 AI 操作系统（Personal AI OS），将各种 AI 模块整合到一个统一平台，供你个人使用。\n\n## **项目介绍**\n\nOpenDAN（Open and Do Anything Now with AI）正在通过其个人 AI 操作系统（AIOS）重塑 AI 领域。该系统专为无缝集成多样化的 AI 模块而设计，确保卓越的互操作性（interoperability）。OpenDAN 赋予用户构建强大的 AI 智能体（Agent）的能力——无论是管家、助手、私人导师还是数字伴侣——同时始终保持对系统的掌控权。这些智能体可以协同工作以应对复杂挑战，与现有服务集成，并控制智能（IoT）设备。\n\n通过 OpenDAN，我们将 AI 交到你手中，让生活更简单、更智能。\n\n本项目仍处于非常早期的阶段，未来可能会有重大变更。\n\n## **更新日志**\n\n经过三个多月的开发，由新贡献者 `waterflier` 主导开发的 OpenDAN MVP（最小可行产品）首个版本（0.5.1）的代码已合并至 Master 分支。该版本实现了 OpenDAN PoC（概念验证）版本中提出的许多构想，并完成了操作系统的基本框架，特别是定义了在 AIOS 上的应用形态。目前，0.5.1 版本以“一体化”（all-in-one）模式运行。对于 0.5.2 版本，我们将基于已部分完成的 [CYFS Owner Online Device (OOD) OS](https:\u002F\u002Fgithub.com\u002Fbuckyos\u002FCYFS) 框架代码，推进 OpenDAN OS 内核的正式实现。\n\n![MVP](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ffiatrete_OpenDAN-Personal-AI-OS_readme_01dbec1b42b3.png)\n\n**OpenDAN 0.5.1（MVP）主要新特性：**\n\n- [x] 基于 Docker 的快速安装与部署，使 OpenDAN 通过 Docker 兼容广泛的硬件环境（PC\u002FMac\u002F树莓派\u002FNAS）。\n- [x] AI 智能体的大语言模型（LLM）可切换，现已支持本地运行开源模型（如 LLaMa）。\n- [x] 引入更多内置 AI 智能体：\n    - [x] 个人助理 Jarvis：管理你的日程和通讯记录的顾问型助手，ChatGPT 的替代方案。\n    - [x] 信息助理 Mia：管理你的个人数据并将其整理成知识库。\n    - [x] 私人英语教师 Tracy：你的专属英语老师。\n    - [x] ai_bash（面向开发者）：无需再记忆复杂的命令行参数！例如直接输入“在 ~\u002FDocuments 中查找包含 OpenDAN 的文件”即可使用 Bash。\n- [x] 通过 Telegram \u002F 邮件连接 AI 智能体或工作流（Workflow）。\n- [x] 基于现有文件或邮件爬虫构建本地私有知识库，使 AI 智能体可访问个人数据。\n    - [x] 支持文本文件和常见图像格式。\n    - [ ] 支持其他常见格式。\n- [x] 实现工作流（Workflow）：多个智能体协作解决更复杂的问题。\n    - [x] 内置工作流 story_maker，集成 AIGC 工具生成音频童话书。\n- [x] 提供分布式 AI 计算核心，用于复杂任务调度。\n- [x] 支持手动下载并安装新的智能体\u002F工作流。\n- [ ] OpenDAN 商店（Store）：智能体\u002F工作流\u002F模型一站式安装（推迟至 0.5.2 版本）。\n\n[立即体验！](.\u002Fdoc\u002FQuickStart.md)\n\n开发者请[点击此处](https:\u002F\u002Fgithub.com\u002Ffiatrete\u002FOpenDAN-Personal-AI-OS\u002Fissues\u002F46)了解 OpenDAN 系统开发的最新进展。\n\n## **介绍视频 —— 什么是 OpenDAN？**\n\n点击下方图片观看演示：\n\n[![Intro Video](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ffiatrete_OpenDAN-Personal-AI-OS_readme_8726670e3d8a.png)](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=l2QmsIOXhdQ \"Intro Video\")\n\n## **订阅更新**\n\n\u003Chttps:\u002F\u002Ftwitter.com\u002FopenDAN_AI>\n\n## **安装**\n\n目前有两种方式安装 OpenDAN 内测版：\n\n1. 通过 Docker 安装 —— 这也是我们当前推荐的方式。\n2. 通过源码安装 —— 此方法可能遇到传统的 Python 依赖问题，需要你具备一定的排错能力。但如果你想对 OpenDAN 进行二次开发，则必须使用此方法。\n\n### 安装前准备\n\n1. **Docker 环境**  \n本文不介绍如何安装 Docker，请在你的终端执行以下命令：\n\n```\ndocker -version\n```\n\n若能看到 Docker 版本号（> 20.0），说明你已成功安装 Docker。  \n如不清楚如何安装 Docker，可参考[此处](https:\u002F\u002Fdocs.docker.com\u002Fengine\u002Finstall\u002F)。\n\n2. **OpenAI API Token**  \n如果没有 API Token，可在此[申请](https:\u002F\u002Fbeta.openai.com\u002F)。\n\n新用户申请 API Token 可能存在一定门槛。你可以向身边的朋友借用临时 Token，或加入我们的内测体验群。我们也会不定期发放一些免费体验用的 API Token（这些 Token 有最大消费额度和有效期限制）。\n\n### 安装\n\n执行以下命令即可拉取 OpenDAN 的 Docker 镜像：\n\n```\ndocker pull paios\u002Faios:latest\n```\n\n## **运行 OpenDAN**\n\n首次运行 OpenDAN 需要初始化。初始化过程中你需要输入一些信息，因此启动 Docker 时请务必带上 `-it` 参数。\n\nOpenDAN 是你的个人 AIOS，运行过程中会生成一些重要的个人数据（如与智能体的聊天记录、日程数据等）。这些数据将存储在你的本地磁盘上。因此，**我们建议将本地目录挂载到 Docker 容器中，以确保数据持久化**。\n\n```\ndocker run -v \u002Fyour\u002Flocal\u002Fmyai\u002F:\u002Froot\u002Fmyai --name aios -it paios\u002Faios:latest \n```\n\n上述命令中，我们还为 Docker 实例指定了名称 `aios`，便于后续操作。你也可以使用自己喜欢的名称。\n\n首次创建 Docker 实例后，后续只需执行：\n\n```\ndocker start -ai aios\n```\n\n如果你计划以后台服务模式运行（无交互界面），则无需 `-ai` 参数：\n\n```\ndocker start aios\n```\n\n### 你好，Jarvis！\n\n配置完成后，你将进入一个 AIOS Shell，其界面类似于 Linux Bash。该界面的含义是：  \n当前用户 “username” 正在与名为 “Jarvis” 的智能体\u002F工作流进行通信，当前话题为默认状态。\n\n向你的私人 AI 助手 Jarvis 打个招呼吧！\n\n**如果一切正常，稍等片刻你就会收到 Jarvis 的回复。此时，OpenDAN 系统已成功运行。**\n![MVP](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ffiatrete_OpenDAN-Personal-AI-OS_readme_d0120f5aa20e.png)\n\n## **OpenDAN 的核心概念与特性**\n1. **AI Agent（AI 智能体）**：由大语言模型驱动，拥有自身的记忆。AI 智能体通过自然语言交互完成任务。\n2. **AI Workflow（AI 工作流）**：将不同的 AI 智能体组织成一个 AI 智能体群组，以完成复杂任务。\n![workflow](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ffiatrete_OpenDAN-Personal-AI-OS_readme_3531254a400d.png)\n3. **AI Environment（AI 环境）**：在获得授权后，支持 AI 智能体访问文件系统、物联网（IoT）设备、网络服务、智能合约以及当今互联网上的所有资源。\n4. **AI Marketplace（AI 应用市场）**：提供一键安装和使用各类 AI 应用的解决方案，帮助用户轻松获取和管理 AI 应用。\n5. **AI Model Solution（AI 模型解决方案）**：为模型搜索、下载和访问控制提供统一入口，方便用户查找并使用符合自身需求的模型。\n6. **硬件专属优化**：针对特定硬件进行优化，使大多数开源 AI 应用能够流畅地在本地运行。\n7. **严格的隐私保护与管理**：严格管理个人数据，涵盖家庭相册、聊天记录、社交媒体记录等，并为 AI 应用提供统一的访问控制接口。\n8. **个人知识库**：\n9. **集成式 AIGC（生成式人工智能）工作流**：提供 AIGC 智能体\u002F工作流，允许用户利用个人数据训练自己的语音模型、LoRA 模型、知识模型等。基于这些私有模型数据，整合最先进的 AIGC 算法，帮助用户轻松释放创造力，打造更酷、更具个性化的数字内容。\n10. **开发框架**：提供用于定制特定用途 AI 助手的开发框架，使开发者能够轻松为客户创建独特的 AI 应用\u002F服务。\n\n## **深入理解 OpenDAN**\n\n### 从源代码构建 OpenDAN\n1. 安装最新版本的 Python（>= 3.11）和 pip\n1. 克隆源代码\n   ```\n   git clone https:\u002F\u002Fgithub.com\u002Ffiatrete\u002FOpenDAN-Personal-AI-OS.git\n   cd OpenDAN-Personal-AI-OS\n   ```\n1. 启用虚拟环境\n   ```\n   virtualenv venv\n   source .\u002Fvenv\u002Fbin\u002Factivate\n   ```\n1. 安装依赖的 Python 库\n   ```\n   pip install -r .\u002Fsrc\u002Frequirements.txt\n   ```\n   等待安装完成。\n1. 通过 aios_shell 启动 OpenDAN\n   ```\n   python .\u002Fsrc\u002Fsrvice\u002Faios_shell\u002Faios_shell.py\n   ```\n   1. 如果出现错误提示 `No ffmpeg exe could be found`，你需要从 https:\u002F\u002Fwww.ffmpeg.org\u002F 手动安装它。\n\n现在 OpenDAN 以开发模式运行，相关目录如下：\n- AIOS_ROOT: .\u002Frootfs （在 Docker 中为 \u002Fopt\u002Faios）\n- AIOS_MYAI: ~\u002Fmyai （在 Docker 中为 \u002Froot\u002Fmyai）\n\n### OpenDAN 使用指南\n\n#### 第一章：你好，Jarvis！\n- 1.1 OpenDAN 的安装\n- 1.2 OpenDAN 的初始配置\n- 1.3 智能体介绍与 Jarvis 的使用\n- 1.4 通过 Telegram 和电子邮件随时随地与 Jarvis 通信\n- 1.5 在日常生活中使用 Jarvis\n- 1.6 Mia 与知识库\n- 1.7 其他内置智能体介绍\n\n[点击阅读](.\u002Fdoc\u002FQuickStart.md)\n\n#### 第二章：AIGC 工作流（即将推出）\n使用工作流激活 AIGC 功能，让智能体团队（导演、艺术家、旁白）协作，根据你的指令为孩子创作独一无二的睡前故事！\n\n- 2.1 使用工作流 `story_maker`\n- 2.2 启用你自己的 AIGC 计算节点\n- 2.3 训练并使用你自己的 AIGC LoRA 模型\n\n#### 第三章：在 OpenDAN 上开发智能体\u002F工作流（撰写中）\n操作系统最关键的设计是什么？定义新型应用形态！\n\n本文将系统性地介绍未来智能应用（Intelligence Applications）的样貌、如何开发与发布智能应用，以及如何将新一代智能应用与传统计算连接起来。\n\n- 3.1 开发可在 OpenDAN 上运行的智能体\n- 3.2 开发可在 OpenDAN 上运行的工作流\n- 3.3 扩展智能体可访问的环境\n- 3.4 发布你自己训练的各种模型\n- 3.5 扩展更多通道以增强智能体\u002F工作流的可访问性\n- 3.6 在个人服务器上开发传统 dApp（去中心化应用）\n\n#### 第四章：OpenDAN 内核开发（撰写中）\n本文将介绍 OpenDAN 架构的设计与实现\n\n![architecture](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ffiatrete_OpenDAN-Personal-AI-OS_readme_cca974aba1d1.png)\n\n- 4.1 将你自己的 LLM（大语言模型）核心集成到 OpenDAN\n- 4.2 知识库：支持更多文件类型，使智能体更好地理解你的知识图谱\n- 4.3 AI 计算引擎：集成更多 AIGC 能力，并接入更强的算力\n- 4.4 OpenDAN 的状态管理：文件系统与向量数据库\n- 4.5 内核服务与权限隔离\n- 4.6 智能网关\n\n## **即将推出的路线图**\n\n- [x] 发布 OpenDAN 的概念验证（PoC）\n- [x] **0.5.1** 通过 Spider 实现个人数据嵌入知识库（KB），并供 AI 智能体访问\n- [ ] 0.5.2 分离用户态与内核态，知识库支持场景格式和更多 Spider，支持个人 AIGC 模型训练\n- [ ] 0.5.3 发布家庭环境，允许智能体访问并控制家中的 IoT 设备\n- [ ] 0.5.x OpenDAN Alpha 正式版发布，同时推出 OpenDAN SDK 1.0\n\n## **贡献指南**\n\n我们欢迎社区成员参与项目贡献，包括但不限于提交 Issue、改进文档、修复 Bug 或提供新功能。你可以通过以下方式参与贡献：\n\n- 在 GitHub 仓库中提交 Issue\n- 向仓库提交 Pull Request\n- 参与讨论与开发\n\nOpenDAN 利用 SourceDAO 智能合约激励社区。做出贡献的开发者将获得 OpenDAN DAO 代币形式的奖励。DAO 代币持有者可共同决定 OpenDAN 的发展方向。你可以通过阅读这篇文章了解 SourceDAO 的规则（https:\u002F\u002Fgithub.com\u002Ffiatrete\u002FOpenDAN-Personal-AI-OS\u002Fissues\u002F25）。\n\nOpenDAN 的 DAO 治理页面正在开发中。正式上线后，所有贡献者将根据规则获得 DAO 代币。\n\n## **⭐Star 历史**\n\n[![Star History Chart](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ffiatrete_OpenDAN-Personal-AI-OS_readme_f0beef7449f3.png)](https:\u002F\u002Fstar-history.com\u002F#fiatrete\u002FOpenDAN-Personal-AI-Server-OS&Date)\n\n## **许可证**\n\n当前许可证为 MIT，但未来将过渡至 SourceDAO。","# OpenDAN-Personal-AI-OS 快速上手指南\n\n## 环境准备\n\n### 系统要求\n- 支持平台：PC \u002F Mac \u002F 树莓派 \u002F NAS（通过 Docker 兼容）\n- 推荐使用 Linux 或 macOS，Windows 用户建议启用 WSL2\n\n### 前置依赖\n1. **Docker**（推荐方式）  \n   版本需 ≥ 20.0，可通过以下命令验证：\n   ```bash\n   docker --version\n   ```\n   若未安装，请参考 [Docker 官方安装文档](https:\u002F\u002Fdocs.docker.com\u002Fengine\u002Finstall\u002F)。国内用户可使用阿里云等镜像加速安装。\n\n2. **OpenAI API Token**（可选但推荐）  \n   - 用于调用 GPT 系列模型（如未配置本地 LLaMa 模型）\n   - 可在 [OpenAI 平台](https:\u002F\u002Fbeta.openai.com\u002F) 申请\n   - 新用户若遇门槛，可加入官方内测群获取临时体验 Token（关注 [@openDAN_AI](https:\u002F\u002Ftwitter.com\u002FopenDAN_AI) 获取信息）\n\n> 💡 注：0.5.1 版本已支持本地运行开源模型（如 LLaMa），若仅使用本地模型，可不提供 OpenAI Token。\n\n---\n\n## 安装步骤\n\n### 方式一：通过 Docker（推荐）\n```bash\n# 拉取最新镜像\ndocker pull paios\u002Faios:latest\n```\n\n### 方式二：从源码安装（适用于二次开发）\n```bash\n# 克隆仓库\ngit clone https:\u002F\u002Fgithub.com\u002Ffiatrete\u002FOpenDAN-Personal-AI-OS.git\ncd OpenDAN-Personal-AI-OS\n\n# 创建并激活虚拟环境（需 Python ≥ 3.11）\nvirtualenv venv\nsource .\u002Fvenv\u002Fbin\u002Factivate\n\n# 安装依赖\npip install -r .\u002Fsrc\u002Frequirements.txt\n\n# 如提示缺少 ffmpeg，请从 https:\u002F\u002Fwww.ffmpeg.org\u002F 手动安装\n```\n\n---\n\n## 基本使用\n\n### 首次启动（Docker 方式）\n```bash\n# 挂载本地目录以持久化数据，并进入交互模式\ndocker run -v \u002Fyour\u002Flocal\u002Fmyai\u002F:\u002Froot\u002Fmyai --name aios -it paios\u002Faios:latest\n```\n> 将 `\u002Fyour\u002Flocal\u002Fmyai\u002F` 替换为你本地希望存储 AI 数据的路径（如 `~\u002Fmyai`）\n\n首次运行会引导完成初始化配置（如 API Token、默认 Agent 等）。\n\n### 后续启动\n```bash\n# 交互模式（带 Shell 界面）\ndocker start -ai aios\n\n# 后台服务模式（无 UI）\ndocker start aios\n```\n\n### 与 Jarvis 打个招呼\n成功启动后，你将进入 AIOS Shell，提示符类似：\n```\nusername@Jarvis\u002Fdefault >\n```\n输入：\n```text\nHello, Jarvis!\n```\n稍等片刻，若收到回复，说明 OpenDAN 已正常运行！\n\n> ✅ 提示：内置 Agent 包括：\n> - **Jarvis**：个人助理（日程、通讯管理）\n> - **Mia**：个人信息与知识库管理\n> - **Tracy**：私人英语教师\n> - **ai_bash**：开发者命令行助手（如 “Find FILES in ~\u002FDocuments that Contain OpenDAN”）","一位自由开发者兼内容创作者小李，日常需要同时处理编程任务、整理技术文档、学习英语，并为孩子制作睡前故事音频。\n\n### 没有 OpenDAN-Personal-AI-OS 时\n- 需在多个平台间切换：用 ChatGPT 查命令、Notion 整理知识、Anki 背单词、Audacity 制作音频，操作繁琐且数据分散。\n- 本地技术文档无法被 AI 直接调用，每次查资料都要手动翻找文件夹或邮件。\n- 编写 Bash 命令时经常忘记参数，反复查阅手册或 Stack Overflow，效率低下。\n- 为孩子创作个性化童话需手动写脚本、生成语音、配图，流程复杂耗时。\n- 所有 AI 工具依赖云端服务，隐私敏感内容不敢上传，且无法离线使用。\n\n### 使用 OpenDAN-Personal-AI-OS 后\n- 在统一界面中调用 Jarvis（日程助理）、Mia（知识管家）、Tracy（英语老师）和 ai_bash（命令助手），无需跳转多个应用。\n- 通过内置文件爬虫自动构建本地知识库，Mia 可直接引用 ~\u002FDocuments 中的技术笔记回答问题。\n- 输入自然语言如“找出包含 OpenDAN 的 PDF”，ai_bash 自动生成并执行 find + grep 命令。\n- 启动 story_maker 工作流，Tracy 编写英文童话，Mia 补充角色设定，系统自动合成带语音的音频故事。\n- 所有模型和数据运行在本地 Docker 环境，支持 Raspberry Pi 部署，保障隐私且可离线使用。\n\nOpenDAN-Personal-AI-OS 将碎片化的 AI 能力整合为可协同的个人智能操作系统，真正实现“一个入口，掌控全部”。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Ffiatrete_OpenDAN-Personal-AI-OS_3015c05e.png","fiatrete","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Ffiatrete_67c1064e.jpg",null,"https:\u002F\u002Fgithub.com\u002Ffiatrete",[80,84,88,92,96,100,104],{"name":81,"color":82,"percentage":83},"Python","#3572A5",96.5,{"name":85,"color":86,"percentage":87},"CSS","#663399",1.2,{"name":89,"color":90,"percentage":91},"TypeScript","#3178c6",1,{"name":93,"color":94,"percentage":95},"JavaScript","#f1e05a",0.9,{"name":97,"color":98,"percentage":99},"Shell","#89e051",0.3,{"name":101,"color":102,"percentage":103},"HTML","#e34c26",0.1,{"name":105,"color":106,"percentage":103},"Dockerfile","#384d54",2018,213,"2026-04-02T09:53:11","MIT","Linux, macOS, Windows","未说明",{"notes":114,"python":115,"dependencies":116},"推荐使用 Docker 部署以避免依赖问题；若从源码安装，需手动安装 ffmpeg；首次运行需配置 OpenAI API Token 或本地模型（如 LLaMa）；支持 Raspberry Pi 和 NAS 等设备；本地知识库功能目前仅支持文本和常见图像格式。","3.11+",[117,118,119,120,121,122,123,124,125],"torch","transformers","accelerate","ffmpeg-python","langchain","sentence-transformers","llama-cpp-python","docker","virtualenv",[15,14,26,13],[128,129,130,131,132,133],"agent","ai","llm","os","autogpt","openai","2026-03-27T02:49:30.150509","2026-04-06T05:36:42.870841",[137,142,147,152,156,161],{"id":138,"question_zh":139,"answer_zh":140,"source_url":141},1641,"如何参与 OpenDAN MVP 开发并申请成为模块负责人（module-PM）？","你可以通过在 Issue #29 中申请成为特定模块的负责人（如 Compute Runtime），并简要介绍自己。项目采用“开源即挖矿”模式，模块开发工作量约为每人 2-3 周，完成后将获得 OpenDAN DAO Token 奖励。MVP 版本规划详见：https:\u002F\u002Fgithub.com\u002Ffiatrete\u002FOpenDAN-Personal-AI-OS\u002Fblob\u002FMVP\u002Fdoc\u002Fmvp\u002Fmvp%20plan.md。","https:\u002F\u002Fgithub.com\u002Ffiatrete\u002FOpenDAN-Personal-AI-OS\u002Fissues\u002F29",{"id":143,"question_zh":144,"answer_zh":145,"source_url":146},1642,"OpenDAN 是否计划采用 DAO 治理？如何参与治理规则设计？","是的，项目计划建立 DAO 实现去中心化治理。社区成员可参与投票决策、贡献建议，并共同制定治理规则。维护者 @maxwilliamdev 表示愿意牵头起草 DAO 规则，并强调 AI 与 DAO 具有天然兼容性。具体区块链技术选型和投票机制仍在讨论中。","https:\u002F\u002Fgithub.com\u002Ffiatrete\u002FOpenDAN-Personal-AI-OS\u002Fissues\u002F1",{"id":148,"question_zh":149,"answer_zh":150,"source_url":151},1643,"在新版本中如何为用户自定义的 Agent 扩展功能？","在 v0.5.2 中，Function 和 Action 能力已升级。虽然插件系统尚未实现，但开发者可通过组合现有函数来构建 Agent。项目方计划后续发布详细文档说明扩展方法。注意：不建议完全依赖 AI 自动生成代码，应区分仅组合函数的 Agent 与允许写代码的 Agent 两类。","https:\u002F\u002Fgithub.com\u002Ffiatrete\u002FOpenDAN-Personal-AI-OS\u002Fissues\u002F114",{"id":153,"question_zh":154,"answer_zh":155,"source_url":141},1644,"Compute Runtime 模块的作用是什么？它和 App Runtime 有何区别？","Compute Runtime（原名模块）的目标是高效利用计算资源，而 App Runtime 的目标是实现应用隔离。两者分工不同：前者专注算力调度，后者专注运行环境安全隔离。",{"id":157,"question_zh":158,"answer_zh":159,"source_url":160},1645,"如何查看 OpenDAN NoC 版本各贡献者的贡献比例及奖励分配？","NoC 版本贡献比例如下：@fiatrete 45%、@maxwilliamdev 20%、@troy6en\u002F@DiligentCatCat\u002F@Synthintel0 各 10%、@suntodai 5%。同意该分配的贡献者需在 Issue #42 中回复“agree”并提供 ETH 地址以接收代币奖励。","https:\u002F\u002Fgithub.com\u002Ffiatrete\u002FOpenDAN-Personal-AI-OS\u002Fissues\u002F42",{"id":162,"question_zh":163,"answer_zh":164,"source_url":141},1646,"项目是否有典型使用场景或模块交互流程说明？","维护者建议先构建一个涵盖尽可能多模块的典型用例，并描述各模块间的工作流和交互方式，以帮助理解整体架构。目前 pseudocode 和关键场景文档正在准备中，社区可等待后续发布。",[166,171,176],{"id":167,"version":168,"summary_zh":169,"released_at":170},101158,"0.5.1","The first version of OpenDAN MVP (0.5.1), driven by the new contributor waterflier, has been merged into the Master branch. This version has realized many concepts proposed in the PoC version of OpenDAN and completed the basic framework of the OS, especially defining the application form on AIOS. Currently, the 0.5.1 version operates in an \"all-in-one\" mode. For 0.5.2, we will advance the formal implementation of the OpenDAN OS kernel based on the partial framework code of the [CYFS Owner Online Device(OOD) OS](https:\u002F\u002Fgithub.com\u002Fbuckyos\u002FCYFS) that has already been completed.","2024-04-23T11:50:26",{"id":172,"version":173,"summary_zh":174,"released_at":175},101159,"0.0.4","Add `remove_bg` function.\r\n\r\nNow you can send a picture first, and then make Jarvis help you remove the background of an image.\r\n\r\nOr tell Jarvis to remove the background image of the image generated by stable_diffusion","2023-06-20T10:29:01",{"id":177,"version":178,"summary_zh":179,"released_at":180},101160,"0.0.3","Using GPT function API","2023-06-16T09:46:36"]