[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-aingdesk--AingDesk":3,"tool-aingdesk--AingDesk":61},[4,18,28,37,45,53],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":17},4358,"openclaw","openclaw\u002Fopenclaw","OpenClaw 是一款专为个人打造的本地化 AI 助手，旨在让你在自己的设备上拥有完全可控的智能伙伴。它打破了传统 AI 助手局限于特定网页或应用的束缚，能够直接接入你日常使用的各类通讯渠道，包括微信、WhatsApp、Telegram、Discord、iMessage 等数十种平台。无论你在哪个聊天软件中发送消息，OpenClaw 都能即时响应，甚至支持在 macOS、iOS 和 Android 设备上进行语音交互，并提供实时的画布渲染功能供你操控。\n\n这款工具主要解决了用户对数据隐私、响应速度以及“始终在线”体验的需求。通过将 AI 部署在本地，用户无需依赖云端服务即可享受快速、私密的智能辅助，真正实现了“你的数据，你做主”。其独特的技术亮点在于强大的网关架构，将控制平面与核心助手分离，确保跨平台通信的流畅性与扩展性。\n\nOpenClaw 非常适合希望构建个性化工作流的技术爱好者、开发者，以及注重隐私保护且不愿被单一生态绑定的普通用户。只要具备基础的终端操作能力（支持 macOS、Linux 及 Windows WSL2），即可通过简单的命令行引导完成部署。如果你渴望拥有一个懂你",349277,3,"2026-04-06T06:32:30",[13,14,15,16],"Agent","开发框架","图像","数据工具","ready",{"id":19,"name":20,"github_repo":21,"description_zh":22,"stars":23,"difficulty_score":24,"last_commit_at":25,"category_tags":26,"status":17},9989,"n8n","n8n-io\u002Fn8n","n8n 是一款面向技术团队的公平代码（fair-code）工作流自动化平台，旨在让用户在享受低代码快速构建便利的同时，保留编写自定义代码的灵活性。它主要解决了传统自动化工具要么过于封闭难以扩展、要么完全依赖手写代码效率低下的痛点，帮助用户轻松连接 400 多种应用与服务，实现复杂业务流程的自动化。\n\nn8n 特别适合开发者、工程师以及具备一定技术背景的业务人员使用。其核心亮点在于“按需编码”：既可以通过直观的可视化界面拖拽节点搭建流程，也能随时插入 JavaScript 或 Python 代码、调用 npm 包来处理复杂逻辑。此外，n8n 原生集成了基于 LangChain 的 AI 能力，支持用户利用自有数据和模型构建智能体工作流。在部署方面，n8n 提供极高的自由度，支持完全自托管以保障数据隐私和控制权，也提供云端服务选项。凭借活跃的社区生态和数百个现成模板，n8n 让构建强大且可控的自动化系统变得简单高效。",184740,2,"2026-04-19T23:22:26",[16,14,13,15,27],"插件",{"id":29,"name":30,"github_repo":31,"description_zh":32,"stars":33,"difficulty_score":10,"last_commit_at":34,"category_tags":35,"status":17},10095,"AutoGPT","Significant-Gravitas\u002FAutoGPT","AutoGPT 是一个旨在让每个人都能轻松使用和构建 AI 的强大平台，核心功能是帮助用户创建、部署和管理能够自动执行复杂任务的连续型 AI 智能体。它解决了传统 AI 应用中需要频繁人工干预、难以自动化长流程工作的痛点，让用户只需设定目标，AI 即可自主规划步骤、调用工具并持续运行直至完成任务。\n\n无论是开发者、研究人员，还是希望提升工作效率的普通用户，都能从 AutoGPT 中受益。开发者可利用其低代码界面快速定制专属智能体；研究人员能基于开源架构探索多智能体协作机制；而非技术背景用户也可直接选用预置的智能体模板，立即投入实际工作场景。\n\nAutoGPT 的技术亮点在于其模块化“积木式”工作流设计——用户通过连接功能块即可构建复杂逻辑，每个块负责单一动作，灵活且易于调试。同时，平台支持本地自托管与云端部署两种模式，兼顾数据隐私与使用便捷性。配合完善的文档和一键安装脚本，即使是初次接触的用户也能在几分钟内启动自己的第一个 AI 智能体。AutoGPT 正致力于降低 AI 应用门槛，让人人都能成为 AI 的创造者与受益者。",183572,"2026-04-20T04:47:55",[13,36,27,14,15],"语言模型",{"id":38,"name":39,"github_repo":40,"description_zh":41,"stars":42,"difficulty_score":10,"last_commit_at":43,"category_tags":44,"status":17},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,"2026-04-05T11:01:52",[14,15,13],{"id":46,"name":47,"github_repo":48,"description_zh":49,"stars":50,"difficulty_score":24,"last_commit_at":51,"category_tags":52,"status":17},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",161692,"2026-04-20T11:33:57",[14,13,36],{"id":54,"name":55,"github_repo":56,"description_zh":57,"stars":58,"difficulty_score":24,"last_commit_at":59,"category_tags":60,"status":17},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。",109154,"2026-04-18T11:18:24",[14,15,13],{"id":62,"github_repo":63,"name":64,"description_en":65,"description_zh":66,"ai_summary_zh":66,"readme_en":67,"readme_zh":68,"quickstart_zh":69,"use_case_zh":70,"hero_image_url":71,"owner_login":72,"owner_name":73,"owner_avatar_url":74,"owner_bio":73,"owner_company":73,"owner_location":73,"owner_email":73,"owner_twitter":73,"owner_website":73,"owner_url":75,"languages":76,"stars":101,"forks":102,"last_commit_at":103,"license":104,"difficulty_score":24,"env_os":105,"env_gpu":106,"env_ram":107,"env_deps":108,"category_tags":114,"github_topics":115,"view_count":24,"oss_zip_url":73,"oss_zip_packed_at":73,"status":17,"created_at":122,"updated_at":123,"faqs":124,"releases":165},10188,"aingdesk\u002FAingDesk","AingDesk","AingDesk是一款简单好用的AI助手，支持知识库、模型API、分享、联网搜索、智能体，它还在飞快成长中。 AingDesk is a simple and easy-to-use AI assistant that supports knowledge bases, model APIs, sharing, internet search, and intelligent agents. It is still growing rapidly.","AingDesk 是一款简单易用的 AI 助手软件，旨在让用户轻松构建属于自己的智能对话环境。它解决了普通用户在部署本地大模型、管理私有知识库以及创建智能体时面临的技术门槛高、操作复杂等痛点。无论是希望保护数据隐私的个人用户，还是想要快速验证想法的开发者，都能通过 AingDesk 实现“一键式”的本地模型部署与主流 API 接入。\n\n这款工具特别适合 AI 初学者、中小团队以及对数据安全有较高要求的研究人员使用。其核心亮点在于集成了本地知识库检索、联网搜索能力以及智能体（Agent）创作功能，让用户无需编写代码即可定制专属助手。此外，AingDesk 支持将配置好的智能服务在线分享，并具备 MCP 客户端特性，能够灵活连接外部工具。它不仅提供便捷的桌面客户端，还支持通过 Docker 进行服务器端部署，兼顾了个人使用的便利性与企业级应用的灵活性。作为一个正在快速成长的项目，AingDesk 正致力于让每个人都能低门槛地享受人工智能带来的效率提升。","# AingDesk\n![GitHub License](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002Faingdesk\u002Faingdesk)\n![GitHub Release](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002Faingdesk\u002Faingdesk)\n![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Faingdesk\u002Faingdesk?style=social)\n![GitHub forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Faingdesk\u002Faingdesk?style=social)\n![GitHub issues](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues\u002Faingdesk\u002Faingdesk)\n![GitHub last commit](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Faingdesk\u002Faingdesk)\n![GitHub all releases](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Faingdesk\u002Faingdesk\u002Ftotal)\n![Docker Pulls](https:\u002F\u002Fimg.shields.io\u002Fdocker\u002Fpulls\u002Faingdesk\u002Faingdesk)\n\n\n[简体中文](README.zh_cn.md) | [Official Website](https:\u002F\u002Fwww.aingdesk.com\u002F) | [Documentation](https:\u002F\u002Fdocs.aingdesk.com\u002F)\n\nAingDesk是一款简单好用的AI助手，支持知识库、模型API、分享、联网搜索、智能体，它还在飞快成长中。\n\nAingDesk is an easy-to-use AI assistant that supports knowledge bases, model APIs, sharing, web search, and intelligent agents. It's rapidly growing and improving.\n\n## 🚀 One-sentence Introduction  \n\nA user-friendly AI assistant software that supports local AI models, APIs, and knowledge base setup.\n\n## ✅ Core Features  \n\n- One-click deployment of local AI models and mainstream model APIs\n![Local model](.github\u002Fassets\u002Fimg\u002F1_en.png)\n- Local knowledge base\n![Knowledge base](.github\u002Fassets\u002Fimg\u002F3_en.png)\n- Intelligent agent creation\n![Intelligent agent](.github\u002Fassets\u002Fimg\u002F4_en.png)\n  \n- Can be shared online for others to use\n![Sharing](.github\u002Fassets\u002Fimg\u002F5_en.png)\n\n- Supports web search\n![Web search](.github\u002Fassets\u002Fimg\u002F6_en.png)\n\n- Supports server-side deployment \n\n- MCP Client\n![MCP Client](.github\u002Fassets\u002Fimg\u002F7_en.png)\n\n- Simultaneous conversations with multiple models in a single session (coming soon)  \n\n## ✨ Product Highlights  \n- Simple and easy to use, beginner-friendly for AI newcomers  \n\n## 📥 Quick Installation\n\n### Client Version（MacOS, Windows） \n\n- [Download from official website](https:\u002F\u002Fwww.aingdesk.com\u002F)   \n- [Download from CNB](https:\u002F\u002Fcnb.cool\u002Faingdesk\u002FAingDesk\u002F-\u002Freleases\u002F)  \n- [Download from Github](https:\u002F\u002Fgithub.com\u002Faingdesk\u002FAingDesk\u002Freleases)  \n\n### Server Version\n\n#### Docker Run\n```bash \ndocker run -d \\\n  --name node \\\n  -v $(pwd)\u002Fdata:\u002Fdata \\\n  -v $(pwd)\u002Fuploads:\u002Fuploads \\\n  -v $(pwd)\u002Flogs:\u002Flogs \\\n  -v $(pwd)\u002Fbin:\u002Faingdesk\u002Fbin \\\n  -v $(pwd)\u002Fsys_data:\u002Fsys_data \\\n  -p 7071:7071 \\\n  -w \u002Faingdesk \\\n  aingdesk\u002Faingdesk\n```\n\n#### Docker Compose\n```bash\nmkdir -p aingdesk\ncd aingdesk\nwget https:\u002F\u002Fcnb.cool\u002Faingdesk\u002FAingDesk\u002F-\u002Fgit\u002Fraw\u002Fserver\u002Fdocker-compose.yml\n# Run\ndocker compose up -d\n# or\ndocker-compose up -d\n``` \n## Build\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Faingdesk\u002FAingDesk.git\ncd AingDesk\n# For macOS users, please remove the `@rollup\u002Frollup-win32-x64-msvc` dependency in [package.json](http:\u002F\u002F_vscodecontentref_\u002F0)\ncd frontend\nyarn\ncd ..\nyarn\nyarn dev\n```\n\n## Star History\n\n[![Star History Chart](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Faingdesk_AingDesk_readme_bdf368d8b776.png)](https:\u002F\u002Fwww.star-history.com\u002F#aingdesk\u002Faingdesk&Date)\n\n## Sponsor\n- CDN acceleration and security protection for this project are sponsored by Tencent EdgeOne.\n[![image](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Faingdesk_AingDesk_readme_f054e0ad5f80.png)](https:\u002F\u002Fedgeone.ai\u002F?from=github)\n","# AingDesk\n![GitHub 许可证](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002Faingdesk\u002Faingdesk)\n![GitHub 发布](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002Faingdesk\u002Faingdesk)\n![GitHub 星标](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Faingdesk\u002Faingdesk?style=social)\n![GitHub 分叉](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Faingdesk\u002Faingdesk?style=social)\n![GitHub 问题](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues\u002Faingdesk\u002Faingdesk)\n![GitHub 最近提交](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Faingdesk\u002Faingdesk)\n![GitHub 所有下载](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Faingdesk\u002Faingdesk\u002Ftotal)\n![Docker 拉取次数](https:\u002F\u002Fimg.shields.io\u002Fdocker\u002Fpulls\u002Faingdesk\u002Faingdesk)\n\n\n[简体中文](README.zh_cn.md) | [官方网站](https:\u002F\u002Fwww.aingdesk.com\u002F) | [文档](https:\u002F\u002Fdocs.aingdesk.com\u002F)\n\nAingDesk是一款简单好用的AI助手，支持知识库、模型API、分享、联网搜索、智能体，它还在飞快成长中。\n\nAingDesk 是一款易于使用的 AI 助手，支持知识库、模型 API、分享、网络搜索和智能体。它正在迅速发展和完善。\n\n## 🚀 一句话简介  \n\n一款用户友好的 AI 助手软件，支持本地 AI 模型、API 和知识库搭建。\n\n## ✅ 核心功能  \n\n- 一键部署本地 AI 模型和主流模型 API\n![本地模型](.github\u002Fassets\u002Fimg\u002F1_en.png)\n- 本地知识库\n![知识库](.github\u002Fassets\u002Fimg\u002F3_en.png)\n- 智能体创建\n![智能体](.github\u002Fassets\u002Fimg\u002F4_en.png)\n  \n- 可以在线分享供他人使用\n![分享](.github\u002Fassets\u002Fimg\u002F5_en.png)\n\n- 支持网络搜索\n![网络搜索](.github\u002Fassets\u002Fimg\u002F6_en.png)\n\n- 支持服务器端部署 \n\n- MCP 客户端\n![MCP 客户端](.github\u002Fassets\u002Fimg\u002F7_en.png)\n\n- 单次会话中可同时与多个模型对话（即将推出）  \n\n## ✨ 产品亮点  \n- 简单易用，对 AI 新手非常友好  \n\n## 📥 快速安装\n\n### 客户端版本（MacOS、Windows） \n\n- [从官方网站下载](https:\u002F\u002Fwww.aingdesk.com\u002F)   \n- [从 CNB 下载](https:\u002F\u002Fcnb.cool\u002Faingdesk\u002FAingDesk\u002F-\u002Freleases\u002F)  \n- [从 Github 下载](https:\u002F\u002Fgithub.com\u002Faingdesk\u002FAingDesk\u002Freleases)  \n\n### 服务器版本\n\n#### Docker 运行\n```bash \ndocker run -d \\\n  --name node \\\n  -v $(pwd)\u002Fdata:\u002Fdata \\\n  -v $(pwd)\u002Fuploads:\u002Fuploads \\\n  -v $(pwd)\u002Flogs:\u002Flogs \\\n  -v $(pwd)\u002Fbin:\u002Faingdesk\u002Fbin \\\n  -v $(pwd)\u002Fsys_data:\u002Fsys_data \\\n  -p 7071:7071 \\\n  -w \u002Faingdesk \\\n  aingdesk\u002Faingdesk\n```\n\n#### Docker Compose\n```bash\nmkdir -p aingdesk\ncd aingdesk\nwget https:\u002F\u002Fcnb.cool\u002Faingdesk\u002FAingDesk\u002F-\u002Fgit\u002Fraw\u002Fserver\u002Fdocker-compose.yml\n# 运行\ndocker compose up -d\n# 或\ndocker-compose up -d\n``` \n## 构建\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Faingdesk\u002FAingDesk.git\ncd AingDesk\n# 对于 macOS 用户，请移除 [package.json](http:\u002F\u002F_vscodecontentref_\u002F0) 中的 `@rollup\u002Frollup-win32-x64-msvc` 依赖\ncd frontend\nyarn\ncd ..\nyarn\nyarn dev\n```\n\n## 星标历史\n\n[![星标历史图](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Faingdesk_AingDesk_readme_bdf368d8b776.png)](https:\u002F\u002Fwww.star-history.com\u002F#aingdesk\u002Faingdesk&Date)\n\n## 赞助商\n- 本项目的 CDN 加速和安全防护由腾讯 EdgeOne 赞助。\n[![图片](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Faingdesk_AingDesk_readme_f054e0ad5f80.png)](https:\u002F\u002Fedgeone.ai\u002F?from=github)","# AingDesk 快速上手指南\n\nAingDesk 是一款简单易用的 AI 助手平台，支持本地模型部署、主流模型 API 接入、知识库构建、智能体创建及联网搜索等功能。适合 AI 初学者及开发者快速搭建私有化 AI 服务。\n\n## 环境准备\n\n### 系统要求\n- **客户端版本**：macOS 或 Windows\n- **服务端版本**：支持 Docker 环境的 Linux\u002FmacOS\u002FWindows 服务器\n- **硬件建议**：若运行本地大模型，建议配备独立显卡（NVIDIA GPU）及充足内存\n\n### 前置依赖\n- **服务端部署**：需安装 Docker 及 Docker Compose\n- **源码构建**：需安装 Node.js 及 Yarn 包管理器\n\n## 安装步骤\n\n### 方案一：直接使用客户端（推荐新手）\n访问以下任一地址下载对应系统的安装包，安装后即可打开使用：\n- [官方网站下载](https:\u002F\u002Fwww.aingdesk.com\u002F)\n- [CNB 国内加速源下载](https:\u002F\u002Fcnb.cool\u002Faingdesk\u002FAingDesk\u002F-\u002Freleases\u002F)\n- [GitHub Releases 下载](https:\u002F\u002Fgithub.com\u002Faingdesk\u002FAingDesk\u002Freleases)\n\n### 方案二：Docker 服务端部署（推荐生产环境）\n\n#### 方式 A：使用 Docker 命令运行\n执行以下命令启动容器，自动挂载数据、日志及配置目录：\n\n```bash\ndocker run -d \\\n  --name node \\\n  -v $(pwd)\u002Fdata:\u002Fdata \\\n  -v $(pwd)\u002Fuploads:\u002Fuploads \\\n  -v $(pwd)\u002Flogs:\u002Flogs \\\n  -v $(pwd)\u002Fbin:\u002Faingdesk\u002Fbin \\\n  -v $(pwd)\u002Fsys_data:\u002Fsys_data \\\n  -p 7071:7071 \\\n  -w \u002Faingdesk \\\n  aingdesk\u002Faingdesk\n```\n\n#### 方式 B：使用 Docker Compose（推荐）\n利用国内镜像源获取配置文件并一键启动：\n\n```bash\nmkdir -p aingdesk\ncd aingdesk\nwget https:\u002F\u002Fcnb.cool\u002Faingdesk\u002FAingDesk\u002F-\u002Fgit\u002Fraw\u002Fserver\u002Fdocker-compose.yml\n# 启动服务\ndocker compose up -d\n# 或者使用旧版命令\ndocker-compose up -d\n```\n\n启动完成后，访问 `http:\u002F\u002F\u003C服务器 IP>:7071` 即可进入管理界面。\n\n### 方案三：源码构建（开发者模式）\n如需二次开发，可克隆源码进行构建：\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Faingdesk\u002FAingDesk.git\ncd AingDesk\n# macOS 用户请注意：需先在 package.json 中移除 @rollup\u002Frollup-win32-x64-msvc 依赖\ncd frontend\nyarn\ncd ..\nyarn\nyarn dev\n```\n\n## 基本使用\n\n1. **访问界面**：浏览器打开安装后提供的地址（默认端口 7071）。\n2. **配置模型**：\n   - 进入设置页面，选择“本地模型”一键部署，或填入主流大模型 API Key（如 OpenAI、DeepSeek 等）。\n3. **创建知识库**：\n   - 上传本地文档（PDF, Word, TXT 等），系统将自动建立向量索引，实现基于私有数据的问答。\n4. **构建智能体**：\n   - 在“智能体”模块中，设定角色提示词，绑定知识库与联网搜索插件，即可创建专属 AI 助手。\n5. **分享协作**：\n   - 创建完成后，可生成分享链接发送给团队成员，无需对方部署即可直接使用你配置好的 AI 能力。","某中小型电商公司的运营团队需要快速构建一个能回答内部产品参数、售后政策及实时市场动态的智能客服系统，以辅助人工客服提升响应效率。\n\n### 没有 AingDesk 时\n- **数据孤岛严重**：产品文档散落在 PDF 和 Wiki 中，客服每次回答需手动检索多个文件，耗时且易出错。\n- **开发门槛高**：若要实现自动问答，需专门招募开发人员调用大模型 API 并编写代码搭建知识库，成本高、周期长。\n- **信息滞后**：无法直接联网获取最新的竞品动态或物流公告，导致回复内容缺乏时效性。\n- **协作困难**：训练好的智能助手难以一键分享给团队成员试用，每个人都要重复配置环境。\n\n### 使用 AingDesk 后\n- **知识统一接入**：利用本地知识库功能，一键上传所有产品手册和政策文档，AI 即刻学会内部业务逻辑，回答精准度大幅提升。\n- **零代码部署**：运营人员无需懂编程，通过图形界面即可配置模型 API 和智能体，半天内便上线了专属客服助手。\n- **实时联网增强**：开启联网搜索功能，助手能自动抓取最新的市场资讯和物流状态，确保回复内容既专业又及时。\n- **便捷共享协作**：通过分享功能生成链接，整个客服团队可立即在同一平台上使用该智能体，并基于实际反馈共同优化提示词。\n\nAingDesk 将原本需要数周开发的智能客服系统简化为“上传文档 + 点击配置”的分钟级任务，让非技术团队也能轻松驾驭企业级 AI 应用。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Faingdesk_AingDesk_0852d53e.png","aingdesk",null,"https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Faingdesk_acd8c3d5.png","https:\u002F\u002Fgithub.com\u002Faingdesk",[77,81,85,89,93,97],{"name":78,"color":79,"percentage":80},"TypeScript","#3178c6",76.2,{"name":82,"color":83,"percentage":84},"Vue","#41b883",19.8,{"name":86,"color":87,"percentage":88},"JavaScript","#f1e05a",1.8,{"name":90,"color":91,"percentage":92},"Shell","#89e051",1.3,{"name":94,"color":95,"percentage":96},"SCSS","#c6538c",0.5,{"name":98,"color":99,"percentage":100},"HTML","#e34c26",0.3,2487,279,"2026-04-19T05:08:17","MIT","Linux, macOS, Windows","未说明（支持本地模型部署，具体显卡需求取决于所选用的本地大模型）","未说明",{"notes":109,"python":107,"dependencies":110},"提供客户端版本（支持 macOS 和 Windows）及服务端版本。服务端推荐通过 Docker 或 Docker Compose 一键部署，需映射数据、上传、日志等目录。若从源码构建前端，macOS 用户需在 package.json 中移除特定的 Windows Rollup 依赖。项目支持接入本地 AI 模型及主流模型 API，并具备知识库、智能体、联网搜索及 MCP 客户端功能。",[111,112,113],"Docker","Node.js (隐含，用于 yarn 构建)","yarn",[36,14],[116,117,118,119,120,121],"deepseek","electron","llm","localai","nodejs","ollama","2026-03-27T02:49:30.150509","2026-04-20T20:44:05.787981",[125,130,135,140,145,150,155,160],{"id":126,"question_zh":127,"answer_zh":128,"source_url":129},45717,"如何配置 AingDesk 连接局域网内其他机器部署的 Ollama（自定义 IP 和端口）？","该功能已在 v1.1.7 版本中解决。您可以更新到最新版本，在设置中自定义 Ollama 的 IP 地址和端口，从而支持局域网内的远程模型调用，无需仅在本地机器安装。","https:\u002F\u002Fgithub.com\u002Faingdesk\u002FAingDesk\u002Fissues\u002F25",{"id":131,"question_zh":132,"answer_zh":133,"source_url":134},45718,"使用 Docker 启动容器时频繁重启并报错'ENOENT: no such file or directory, open \u002Fdata\u002Fbin\u002Fbun.zip'怎么办？","这是路径配置问题。请确保使用正确的 docker-compose.yml 配置，将数据目录正确映射。参考配置如下：\n```yaml\nservices:\n  aingdesk:\n    image: docker.cnb.cool\u002Faingdesk\u002Faingdesk:latest\n    container_name: aingdesk\n    restart: unless-stopped\n    privileged: true\n    ports:\n      - \"7071:7071\"\n    volumes:\n      - .\u002Fdata:\u002Fdata\n      - .\u002Fuploads:\u002Fuploads\n      - .\u002Flogs:\u002Flogs\n    environment:\n      - TZ=Asia\u002FShanghai\n```\n注意 bun 二进制文件应位于 `\u002Fdata\u002Faingdesk\u002Fdata\u002Fbin` 目录下（取决于您的宿主机挂载路径）。","https:\u002F\u002Fgithub.com\u002Faingdesk\u002FAingDesk\u002Fissues\u002F121",{"id":136,"question_zh":137,"answer_zh":138,"source_url":139},45719,"AingDesk 支持多用户管理吗？如何添加新用户？","服务端版本（v1.1.8 及以上）已增加用户管理模块。如果您使用 Docker 部署，请拉取最新镜像。更新日志包括：优化知识库、增加 MCP 客户端模块、增加用户管理模块以及同步 PC 端其它功能。管理员可以在服务端配置公共模型和知识库，普通用户可使用系统对话。","https:\u002F\u002Fgithub.com\u002Faingdesk\u002FAingDesk\u002Fissues\u002F49",{"id":141,"question_zh":142,"answer_zh":143,"source_url":144},45720,"嵌入文件时 LanceDB 占用过多硬盘空间（产生大量中间文件），如何解决？","最新版本已对此进行优化：一是实施了数据压缩，二是增加了定期删除旧版本数据库的机制。此外，您现在可以在设置中调整数据存储位置。由于 RAG 需要自助学习模型不断生成新版本数据库，完全删除中间文件不可行，但新版本会自动清理旧版本以节省空间。","https:\u002F\u002Fgithub.com\u002Faingdesk\u002FAingDesk\u002Fissues\u002F23",{"id":146,"question_zh":147,"answer_zh":148,"source_url":149},45721,"模型安装界面一直卡住或 Ollama 安装失败怎么办？","此问题在 v1.1.6 及后续版本中已优化。如果仍然遇到下载停滞（例如只下载了几 KB），建议手动前往 Ollama 官网 (https:\u002F\u002Follama.com\u002Fdownload) 下载安装包进行手动安装，然后在 AingDesk 中配置已安装的 Ollama 路径。","https:\u002F\u002Fgithub.com\u002Faingdesk\u002FAingDesk\u002Fissues\u002F3",{"id":151,"question_zh":152,"answer_zh":153,"source_url":154},45722,"如何在内网部署并让多人通过浏览器链接共享使用智能体（无需每人安装软件）？","AingDesk 现已支持服务端部署模式，满足企业内网共享需求。您可以通过 Docker 部署服务端（文档见：https:\u002F\u002Fdocs.aingdesk.com\u002Fzh-Hans\u002FInstallation\u002Fdocker）。部署后，创建好智能体和提示词，即可生成链接分享给局域网内的其他人，他们只需在浏览器打开链接即可使用，无需重复安装软件或配置提示词。","https:\u002F\u002Fgithub.com\u002Faingdesk\u002FAingDesk\u002Fissues\u002F26",{"id":156,"question_zh":157,"answer_zh":158,"source_url":159},45723,"深色模式颜色太黑、缺少“关于”页面或切换语言后描述未更新等界面细节如何调整？","维护者已在后续版本中优化了深色模式（调整为非纯黑，参考 Dracula\u002FCatppuccin 风格），增加了“关于”页面，并修复了切换语言后大模型介绍仍显示中文的问题。同时增加了对 Apple Silicon 内存预加载策略导致的模型推荐不匹配问题的处理。请更新至最新版本体验改进。","https:\u002F\u002Fgithub.com\u002Faingdesk\u002FAingDesk\u002Fissues\u002F7",{"id":161,"question_zh":162,"answer_zh":163,"source_url":164},45724,"是否支持本地知识库管理和 API 调用？","是的，知识库管理和 API 调用功能均已支持。知识库功能允许上传和管理本地文件用于 RAG 检索，API 功能允许外部程序调用本地部署的模型。这些功能已在 v1.1.0 及后续版本中上线。","https:\u002F\u002Fgithub.com\u002Faingdesk\u002FAingDesk\u002Fissues\u002F6",[166,171,176,181,186,191,196,201,206,211,216,221,226,231,236,241,246,251,256,261],{"id":167,"version":168,"summary_zh":169,"released_at":170},360669,"v1.2.4","- 增加对通义千问3模型的支持\n- 优化部分搜索引擎的结果解析\n- 为纯图片PDF添加OCR支持（macOS需手动安装Poppler）\n- 提升在代理场景中使用搜索引擎的效果\n- 优化MCP工具调用结果的解析\n- 修复已知的各种Bug","2025-05-27T08:00:52",{"id":172,"version":173,"summary_zh":174,"released_at":175},360670,"v1.2.3","- 修复与 OpenAI GPT-O3 的兼容性问题\n- 解决使用第三方嵌入模型创建知识库时出现“模型未找到”错误的问题\n- 优化模型选择器","2025-04-18T03:37:39",{"id":177,"version":178,"summary_zh":179,"released_at":180},360671,"v1.2.2","- 添加自动更新机制（仅限 Windows 版本）\n- 修复知识库、智能体和工具联合调用时的问题\n- 解决其他已知问题","2025-04-16T06:41:02",{"id":182,"version":183,"summary_zh":184,"released_at":185},360672,"v1.2.1","- 增加 MCP 客户端功能（在设置中配置 MCP 服务器，然后在对话中选择该工具）\n- 优化模型选择器\n- 其他细节调整\n\n> 在 Ollama 中选择工具后，内容需待模型完全响应才会显示；在线模型支持实时输出。","2025-04-14T10:40:51",{"id":187,"version":188,"summary_zh":189,"released_at":190},360673,"v1.2.0","- 优化了默认文档分块效果。- 提升了知识库全文搜索的准确性。- 修复了使用多个分隔符时分块不完整的问题。- 解决了一些界面交互问题。","2025-04-08T03:31:13",{"id":192,"version":193,"summary_zh":194,"released_at":195},360674,"v1.1.9","- 将知识库精度配置改为自动模式\n- 修复知识库召回配置未生效的问题\n- 解决因修改数据目录而导致的问题\n- 修复调用某些在线模型时出现的错误\n- 增加对 macOS x64 版本的支持","2025-04-03T06:01:17",{"id":197,"version":198,"summary_zh":199,"released_at":200},360675,"v1.1.8","1. 提升了知识库的准确性和性能  \n2. 优化了知识库的文档分块及召回设置配置  \n3. 新增了修改数据存储目录的功能  \n4. 修复了无法解析 .doc 文件的问题  \n5. 优化了上下文嵌入流程，以减少幻觉现象  \n6. 其他已知问题修复","2025-04-02T11:58:15",{"id":202,"version":203,"summary_zh":204,"released_at":205},360676,"v1.1.7","特性：新增并优化多项功能  \n- 增加对 Mermaid 标准语法输出格式的解析支持  \n- 引入自定义 Ollama 服务接口地址的配置选项，以提升灵活性  \n- 同步并维护最新的 Ollama 模型库列表  \n\n修复：解决现有问题  \n- 在模型调用失败时显示错误信息，便于排查问题  \n- 修复 Ollama 模型存储目录配置未立即生效的问题","2025-03-21T10:45:20",{"id":207,"version":208,"summary_zh":209,"released_at":210},360677,"v1.1.6","1. 修复了在某些场景下知识库文档嵌入会无限等待的问题。\n2. 增加了检测嵌入模型可用性的机制。\n3. 改进了 PDF 解析器，提升了易用性，并更好地保留格式。\n4. 新增了选择模型安装位置的功能。","2025-03-20T03:04:55",{"id":212,"version":213,"summary_zh":214,"released_at":215},360678,"v1.1.5","特性：新增功能并修复相关问题  \n- 添加智能代理功能模块  \n\n修复：解决非多模态模型在处理图片附件时的错误  \n- 修复非多模态模型在处理图片附件时抛出错误的问题","2025-03-15T04:03:13",{"id":217,"version":218,"summary_zh":219,"released_at":220},360679,"v1.1.4","chore: optimize certain features and fix related issues\r\n- Automatically use OCR model to extract text from images when uploading to non-vision models, then pass the context to the large model\r\n- Fix issue where images failed to be passed to third-party models\r\n- Fix failure in extracting DOC\u002FPDF\u002FMD documents caused by image extraction errors\r\n\r\nfix: resolve document and image processing issues\r\n- Ensure successful extraction of documents even if image extraction fails","2025-03-15T03:37:12",{"id":222,"version":223,"summary_zh":224,"released_at":225},360680,"v1.1.3","feat: add new features and enhance version stability\r\n- Add conversation attachment functionality\r\n- Add option for conversation without memory\r\n- Introduce automatic context fine-tuning mechanism for ollama (2048-4096\u002F\u003C=4b 8192)\r\n- Allow selection of third-party models and knowledge bases in sharing functionality\r\n- Adjust knowledge base initialization interaction logic\r\n\r\nfix: resolve multiple issues\r\n- Fix ollama installation failure for certain installation paths\r\n- Fix issue where close button does not fully exit the application on MacOS\r\n- Fix PDF parsing issue in knowledge base on MacOS\r\n- Update to the latest ollama version and model list\r\n- Resolve other known issues","2025-03-13T12:51:37",{"id":227,"version":228,"summary_zh":229,"released_at":230},360681,"v1.1.2","- Add third-party API integration functionality\r\n- Optimize default recall parameters for the knowledge base","2025-03-12T04:20:41",{"id":232,"version":233,"summary_zh":234,"released_at":235},360682,"v1.1.1","- Add knowledge base functionality\r\n- Optimize scrolling overhead in conversation context\r\n- Improve interaction experience\r\n- Add dedicated prompts for the qwq model\r\n- Update ollama model list","2025-03-07T11:28:13",{"id":237,"version":238,"summary_zh":239,"released_at":240},360683,"v1.0.7","1. Adjusted the behavior of the close button to directly exit the program (reverting the previous change).\r\n2. Fixed the issue where some models installed via `ollama pull` could not be recognized, such as the `latest` version.\r\n3. Resolved the issue where the model list could only be retrieved after restarting the process when the Ollama service was stopped.\r\n4. Adjusted the automatic setting of the environment variable `OLLAMA_HOST=127.0.0.1` for Ollama installations via AingDesk to prevent potential malicious exploitation.","2025-02-26T03:54:55",{"id":242,"version":243,"summary_zh":244,"released_at":245},360684,"v1.0.6","1. Optimized exclusive prompts for deepseek-r1.\r\n    \r\n2. Fixed the issue where the default backend language was English on macOS.\r\n\r\n3. Improved the Ollama download mechanism with automatic node switching and resumable downloads.\r\n\r\n4. Adjusted the behavior of the close button so that clicking it minimizes the program to the system tray instead of exiting.\r\n\r\n5. Added a caching mechanism for web searches.\r\n\r\n6. Adjusted the regeneration strategy for user queries during web searches.\r\n\r\n7. Fixed the issue where the left and right spacing in the chat window was disproportionately large.\r\n\r\n8. Resolved the issue where chat scrolling during the generation phase did not behave as expected.","2025-02-25T02:55:58",{"id":247,"version":248,"summary_zh":249,"released_at":250},360685,"v1.0.5","1. Optimize the internet search results.\r\n2. Fix the issue of response language when using non - Chinese languages.\r\n3. Fix the problem that the regeneration function doesn't meet expectations.","2025-02-22T10:31:28",{"id":252,"version":253,"summary_zh":254,"released_at":255},360686,"v1.0.4","1. Add an internet search function.\r\n2. Optimize the default prompt for deepseek-r1.\r\n3. Fix the issue where the interface is redirected upon clicking the link.","2025-02-22T03:50:18",{"id":257,"version":258,"summary_zh":259,"released_at":260},360687,"v1.0.3","1. Added an automatic node selection mechanism when downloading Ollama, which automatically selects the fastest node.\r\n2. Optimized the network stability of the sharing channel.\r\n3. Fixed the issue where multiple users could not converse simultaneously when using the same sharing link.","2025-02-20T11:12:56",{"id":262,"version":263,"summary_zh":264,"released_at":265},360688,"v1.0.2","**Version 1.0.2 Released:**\r\n1. Optimized software performance, reducing CPU usage.\r\n2. Fixed an issue where the first-time sharing link could not be opened or used.\r\n3. Resolved a potential freezing issue on macOS.","2025-02-20T03:01:13"]