[{"data":1,"prerenderedAt":1163},["ShallowReactive",2],{"header-counts":3,"footer-counts":6,"compare-msty-vs-open-webui":9,"compare-a-msty":10,"compare-b-open-webui":656},{"tools":4,"reviews":5},78,26,{"tools":4,"reviews":5,"playbooks":7,"news":8},22,21,null,{"id":11,"title":12,"alternatives":13,"api_compatible":9,"body":17,"category":580,"chinese_friendly":567,"cover":581,"description":582,"domestic":583,"extension":584,"faq":585,"free":583,"github":9,"languages":598,"lastVerified":9,"meta":601,"models":9,"navigation":602,"notSuitable":9,"opensource":583,"path":603,"pillar":604,"platforms":605,"priceTable":610,"pricing":626,"published":627,"relatedPlaybooks":628,"relatedReviews":9,"score":630,"self_host":602,"seo":633,"seoTitle":9,"slug":634,"sources":635,"stem":645,"suitable":9,"tagline":646,"tags":647,"updated":638,"verdict":653,"website":654,"__hash__":655},"tools\u002Ftools\u002Fagent\u002Fgeneral\u002Fmsty.md","Msty",[14,15,16],"coding\u002Flocal\u002Follama","coding\u002Flocal\u002Flm-studio","coding\u002Flocal\u002Fopen-webui",{"type":18,"value":19,"toc":565},"minimark",[20,25,29,32,35,112,115,141,147,151,156,182,187,213,216,240,243,418,421,477,481,507,510,531,534],[21,22,24],"h2",{"id":23},"tldr","TL;DR",[26,27,28],"p",{},"Msty 是 privacy-first 桌面 AI 工作站，macOS \u002F Windows \u002F Linux 原生 app + 浏览器，独立开发者出品。差异点：内置 MLX (Apple) \u002F llama.cpp \u002F Ollama 三种本地推理引擎，无需 CLI + Hosted Models（OpenAI \u002F Anthropic \u002F Gemini）一窗体并存 + Split Chats 同问题多模型并行 + Knowledge Stack（per-conversation RAG）+ Prompt \u002F Persona \u002F Skills 三个 Studios + Agent Mode 多步执行。Free 本地无限 \u002F Aurum $149·年 \u002F Lifetime $349 \u002F Enterprise $300\u002Fuser·年。",[26,30,31],{},"适合：隐私敏感 + 不愿数据上云；Mac mini \u002F Linux box 当私人 AI 服务器；想避开 Ollama CLI 的非工程师；多模型对比决策场景。不适合：硬件不行（7B+ 本地跑不动）；要 BYO API + 极简（用 Typing Mind）；要 mobile（无 iOS \u002F Android 移动 app）；团队协作（更适合 Claude Team）。",[21,33,34],{"id":34},"核心能力",[36,37,38,46,52,58,64,70,76,82,88,94,100,106],"ul",{},[39,40,41,45],"li",{},[42,43,44],"strong",{},"三引擎本地推理","：MLX（Apple）\u002F llama.cpp \u002F Ollama 开箱即用",[39,47,48,51],{},[42,49,50],{},"Hosted Models","：OpenAI \u002F Anthropic \u002F Gemini 一窗体接入",[39,53,54,57],{},[42,55,56],{},"Split Chats","：同问题同时跑多模型 + side-by-side 对比",[39,59,60,63],{},[42,61,62],{},"Knowledge Stack","：per-conversation RAG，文档 \u002F URL \u002F Obsidian vault \u002F YouTube transcript",[39,65,66,69],{},[42,67,68],{},"Prompt Studio","：变量 + 模板 + 测试",[39,71,72,75],{},[42,73,74],{},"Persona Studio","：自定义角色 + 工具 + context",[39,77,78,81],{},[42,79,80],{},"Skills Studio","：可复用能力包",[39,83,84,87],{},[42,85,86],{},"Agent Mode","：多步执行 + 工具调用",[39,89,90,93],{},[42,91,92],{},"Flowchart 对话","：分支可视化",[39,95,96,99],{},[42,97,98],{},"Real-time 数据","：实时 web fetch",[39,101,102,105],{},[42,103,104],{},"Offline-first","：零账号 \u002F 零 telemetry \u002F 零云依赖（Free）",[39,107,108,111],{},[42,109,110],{},"Cloud Sync","（Aurum）：跨设备同步对话",[21,113,114],{"id":114},"价格",[36,116,117,123,129,135],{},[39,118,119,122],{},[42,120,121],{},"Free","：$0 永久；本地全功能 + 云 API 接入 + Split Chats + Knowledge Stack",[39,124,125,128],{},[42,126,127],{},"Aurum","：$149\u002F年；cloud sync + 高级 Knowledge + Studio Desktop alpha + 优先支持",[39,130,131,134],{},[42,132,133],{},"Lifetime","：$349 一次；Aurum 全部功能 + 终身更新",[39,136,137,140],{},[42,138,139],{},"Enterprise","：$300\u002Fuser·年；SSO + 私有部署 + 团队管理",[142,143,144],"blockquote",{},[26,145,146],{},"Lifetime 在 2 年用回本，重度用户首选。Free 已经足够个人 90% 场景。",[21,148,150],{"id":149},"实测macos-mac-mini-私人-ai-服务器","实测（macOS + Mac mini 私人 AI 服务器）",[26,152,153],{},[42,154,155],{},"亮点：",[36,157,158,161,164,167,170,173,176,179],{},[39,159,160],{},"装完立刻能用，无需 Ollama \u002F llama.cpp \u002F MLX 任何 CLI",[39,162,163],{},"Split Chats 对比 GPT-5 + Claude + Qwen2.5 + Llama 3.3 一目了然",[39,165,166],{},"Knowledge Stack 的 per-conversation 设计完美：每项目独立 RAG context",[39,168,169],{},"Prompt \u002F Persona \u002F Skills 三 Studio 解决重复 prompt 痛点",[39,171,172],{},"MLX 在 M1\u002FM2\u002FM3\u002FM4 上跑得快",[39,174,175],{},"中文 Qwen2.5 \u002F DeepSeek 走本地路径无外网依赖",[39,177,178],{},"Free 永久免费 + 本地无限 = 真正 zero-cost 路径",[39,180,181],{},"Lifetime $349 比 ChatGPT Plus 18 个月便宜",[26,183,184],{},[42,185,186],{},"踩坑：",[36,188,189,192,195,198,201,204,207,210],{},[39,190,191],{},"本地性能受硬件限制：M1 Air 跑 7B 慢，M3 Max \u002F Mac Studio \u002F 高端 GPU 更适合",[39,193,194],{},"插件 \u002F Skill 生态比 Typing Mind \u002F LM Studio 弱",[39,196,197],{},"桌面 only，无 iOS \u002F Android",[39,199,200],{},"llama.cpp 更新滞后官方上游 1-2 版本",[39,202,203],{},"Knowledge Stack 大文档（>100MB）切分偶尔失败",[39,205,206],{},"Agent Mode 仍在打磨，复杂任务稳定性不如 Claude",[39,208,209],{},"Studio Desktop（Aurum alpha）测试中，bug 偶发",[39,211,212],{},"中文 UI 不完整，部分功能仍是英文",[21,214,215],{"id":215},"上手",[217,218,219,222,225,228,231,234,237],"ol",{},[39,220,221],{},"msty.ai → 下载 macOS \u002F Windows \u002F Linux → 安装",[39,223,224],{},"Settings → Model Providers → Ollama 连本地（或直接装 Msty 自带 llama.cpp \u002F MLX）",[39,226,227],{},"装 1-2 个本地模型：Qwen2.5 7B（中文）+ Llama 3.3 8B（英文）",[39,229,230],{},"加云模型：OpenAI Key + Anthropic Key",[39,232,233],{},"新建 chat → 试 Split Chats：+ 第二个模型 → 同问题并行",[39,235,236],{},"Knowledge Stack → 上传项目文档 → 附加到 conversation",[39,238,239],{},"满意后 Free 用着，重度需要同步上 Lifetime $349",[21,241,242],{"id":242},"对比",[244,245,246,267],"table",{},[247,248,249],"thead",{},[250,251,252,256,258,261,264],"tr",{},[253,254,255],"th",{},"维度",[253,257,12],{},[253,259,260],{},"Ollama",[253,262,263],{},"LM Studio",[253,265,266],{},"Jan",[268,269,270,287,302,317,331,344,358,373,387,401],"tbody",{},[250,271,272,276,279,282,285],{},[273,274,275],"td",{},"GUI",[273,277,278],{},"✅ 颜值高",[273,280,281],{},"❌ CLI",[273,283,284],{},"✅",[273,286,284],{},[250,288,289,292,295,297,300],{},[273,290,291],{},"本地引擎",[273,293,294],{},"MLX\u002Fllama.cpp\u002FOllama",[273,296,260],{},[273,298,299],{},"llama.cpp",[273,301,299],{},[250,303,304,307,309,312,314],{},[273,305,306],{},"云模型",[273,308,284],{},[273,310,311],{},"❌",[273,313,311],{},[273,315,316],{},"部分",[250,318,319,321,324,326,328],{},[273,320,56],{},[273,322,323],{},"✅ 旗舰",[273,325,311],{},[273,327,316],{},[273,329,330],{},"–",[250,332,333,335,338,340,342],{},[273,334,62],{},[273,336,337],{},"✅ per-conv",[273,339,311],{},[273,341,311],{},[273,343,316],{},[250,345,346,349,352,354,356],{},[273,347,348],{},"Studios",[273,350,351],{},"✅ Prompt\u002FPersona\u002FSkills",[273,353,330],{},[273,355,330],{},[273,357,330],{},[250,359,360,363,365,368,370],{},[273,361,362],{},"开源",[273,364,311],{},[273,366,367],{},"✅ MIT",[273,369,311],{},[273,371,372],{},"✅ Apache 2.0",[250,374,375,378,381,383,385],{},[273,376,377],{},"起价",[273,379,380],{},"$0",[273,382,380],{},[273,384,380],{},[273,386,380],{},[250,388,389,392,395,397,399],{},[273,390,391],{},"终身",[273,393,394],{},"$349",[273,396,330],{},[273,398,330],{},[273,400,330],{},[250,402,403,406,409,412,415],{},[273,404,405],{},"适合",[273,407,408],{},"桌面颜值 + 多模型",[273,410,411],{},"CLI \u002F Server",[273,413,414],{},"模型市场",[273,416,417],{},"严格开源",[21,419,420],{"id":420},"避坑",[36,422,423,429,435,441,447,453,459,465,471],{},[39,424,425,428],{},[42,426,427],{},"硬件评估","：M1 Air 8GB 只跑 3B-7B，M3 Pro \u002F Max 跑 13B-30B 流畅",[39,430,431,434],{},[42,432,433],{},"Ollama 已装就连","：避免重复下模型，连本地 Ollama 复用 model library",[39,436,437,440],{},[42,438,439],{},"Knowledge Stack 文档","：单文档 \u003C50MB 最稳，大文件先切分",[39,442,443,446],{},[42,444,445],{},"Persona vs Skill","：Persona 是角色（完整 system + 模型）；Skill 是能力包；不要混用",[39,448,449,452],{},[42,450,451],{},"Split Chats 三个模型够","：4 个起每问 token 烧得快",[39,454,455,458],{},[42,456,457],{},"Aurum cloud sync 谨慎","：隐私敏感场景仍用 Free 本地",[39,460,461,464],{},[42,462,463],{},"Studio Desktop alpha","：稳定性不如 main 版本，重要工作不要全押",[39,466,467,470],{},[42,468,469],{},"本地中文模型","：Qwen2.5 7B \u002F DeepSeek 7B 中文最优，Llama 3.3 8B 英文最优",[39,472,473,476],{},[42,474,475],{},"MCP server","：当前不如 Claude Desktop 强，要 MCP 重度场景考虑 Claude Desktop \u002F Crush",[21,478,480],{"id":479},"适合-不适合","适合 \u002F 不适合",[36,482,483,486,489,492,495,498,501,504],{},[39,484,485],{},"✅ 隐私敏感 + 数据零云",[39,487,488],{},"✅ Mac mini \u002F Linux box 私人 AI 服务器",[39,490,491],{},"✅ 不愿学 Ollama CLI 的非工程师",[39,493,494],{},"✅ 多模型对比决策场景",[39,496,497],{},"❌ 硬件不行（8GB RAM）跑不动 7B+",[39,499,500],{},"❌ 要 mobile 移动主力",[39,502,503],{},"❌ 团队协作 + 共享 workspace",[39,505,506],{},"❌ 要 MCP 工具栈深度（用 Claude Desktop \u002F Crush）",[21,508,509],{"id":509},"相关阅读",[36,511,512,519,525],{},[39,513,514],{},[515,516,518],"a",{"href":517},"\u002Ftools\u002Fcoding\u002Flocal\u002Follama","Ollama 评测",[39,520,521],{},[515,522,524],{"href":523},"\u002Ftools\u002Fcoding\u002Flocal\u002Flm-studio","LM Studio 评测",[39,526,527],{},[515,528,530],{"href":529},"\u002Ftools\u002Fcoding\u002Flocal\u002Fopen-webui","Open WebUI 评测",[21,532,533],{"id":533},"来源",[217,535,536,544,551,558],{},[39,537,538,539],{},"Msty 官网 + Features（MLX \u002F llama.cpp \u002F Ollama \u002F Studios）",[515,540,541],{"href":541,"rel":542},"https:\u002F\u002Fmsty.ai\u002Fstudio\u002Ffeatures",[543],"nofollow",[39,545,546,547],{},"AI Chat Daily — Msty Review 2026（4.3\u002F5 评分 + Lifetime）",[515,548,549],{"href":549,"rel":550},"https:\u002F\u002Fwww.aichatdaily.com\u002Ftools\u002Fmsty",[543],[39,552,553,554],{},"ML Journey — Msty Multi-model Comparison Guide ",[515,555,556],{"href":556,"rel":557},"https:\u002F\u002Fmljourney.com\u002Fmsty-the-local-llm-app-that-lets-you-compare-models-side-by-side",[543],[39,559,560,561],{},"AISO Tools — Msty Pricing 2026 ",[515,562,563],{"href":563,"rel":564},"https:\u002F\u002Faisotools.com\u002Fpricing\u002Fmsty",[543],{"title":566,"searchDepth":567,"depth":567,"links":568},"",3,[569,571,572,573,574,575,576,577,578,579],{"id":23,"depth":570,"text":24},2,{"id":34,"depth":570,"text":34},{"id":114,"depth":570,"text":114},{"id":149,"depth":570,"text":150},{"id":215,"depth":570,"text":215},{"id":242,"depth":570,"text":242},{"id":420,"depth":570,"text":420},{"id":479,"depth":570,"text":480},{"id":509,"depth":570,"text":509},{"id":533,"depth":570,"text":533},"general","\u002Fimg\u002Ftools\u002Fmsty.webp","Msty 真实评测：privacy-first 桌面 AI 工作站，macOS \u002F Windows \u002F Linux 原生 app + 浏览器。差异点：内置 MLX (Apple) \u002F llama.cpp \u002F Ollama 三种本地推理引擎 + Hosted Models（OpenAI \u002F Anthropic \u002F Gemini）一窗体管理 + Split Chats 多模型同时跑同问题 + Knowledge Stack（per-conversation RAG，区别于 AnythingLLM workspace）+ Prompt \u002F Persona \u002F Skills 三个 Studios + Agent Mode 多步执行。Free 本地全功能 \u002F Aurum $5-149 \u002F Lifetime $349 \u002F Enterprise $300\u002Fuser·年。",false,"md",[586,589,592,595],{"q":587,"a":588},"和 Ollama \u002F LM Studio \u002F Jan \u002F AnythingLLM 怎么选？","Msty 强在『多模型 split chat 对比 + Knowledge Stack 灵活 per-conversation + UI 颜值』。Ollama 是 CLI + server，无 GUI 适合开发者。LM Studio 强在『模型市场 + 性能 profiling』。Jan 开源 + Apache 2.0 协议自由度高。AnythingLLM 强在 workspace + RAG agent。要桌面颜值 + 多模型对比 + 简单 RAG → Msty；要 CLI \u002F server → Ollama；要模型市场 → LM Studio；要严格开源 → Jan。",{"q":590,"a":591},"Knowledge Stack 怎么用？","上传文档 \u002F URL \u002F 文本到 Knowledge collection，per-conversation 附加。和 AnythingLLM 的 workspace 区别：Msty 是 conversation 级，每对话独立 context，不会跨对话泄露。多项目并行场景非常顺。Aurum 解锁更大 \u002F 更高级 Knowledge。",{"q":593,"a":594},"Split Chats 真的实用吗？","对，多模型决策场景非常有用：决定哪个模型适合任务（同问题看 GPT-5 \u002F Claude \u002F Llama 3 输出）；本地 vs 云模型质量评估；事实问题模型分歧检测（多个模型给同样答案 = 更可信）。日常使用确实降低选错模型成本。",{"q":596,"a":597},"中国大陆能用吗？","本地模式完全离线可用（Ollama \u002F llama.cpp \u002F MLX 本地模型 + Qwen \u002F DeepSeek 中文模型）。云模式接 OpenAI \u002F Anthropic 需要海外网络 + 卡。Aurum 订阅需海外支付。最佳路径：本地 Free + Ollama + Qwen2.5\u002FDeepSeek 中文，零订阅 + 零外网依赖。",[599,600],"en","multi",{},true,"\u002Ftools\u002Fagent\u002Fgeneral\u002Fmsty","agent",[606,607,608,609],"macos","windows","linux","web",[611,614,618,622],{"plan":121,"price":380,"features":612,"notes":613},"本地模型 + 云 API 接入 + Split Chats + Knowledge Stack（无限）+ 无账号","永久免费",{"plan":127,"price":615,"features":616,"notes":617},"$149\u002F年","Free 全部 + cloud sync + 高级 Knowledge + 优先支持 + Studio Desktop alpha","每用户",{"plan":133,"price":619,"features":620,"notes":621},"$349 一次","Aurum 终身授权","永久 + 所有更新",{"plan":139,"price":623,"features":624,"notes":625},"$300\u002Fuser·年","SSO + 团队管理 + 私有部署支持","需联系销售","Free 本地无限 \u002F Aurum $149·年（cloud sync）\u002F Lifetime $349 一次买断 \u002F Enterprise $300·user·年","2026-06-19",[629],"onboarding\u002Flocal-ai-workstation",{"power":631,"ux":632,"price":632,"cn_support":567,"stability":631},4,5,{"title":12,"description":582},"agent\u002Fgeneral\u002Fmsty",[636,639,641,643],{"name":637,"url":541,"accessed":638},"Msty 官网 + Features","2026-06-24",{"name":640,"url":549,"accessed":638},"AI Chat Daily — Msty Review 2026 4.3\u002F5",{"name":642,"url":556,"accessed":638},"ML Journey — Msty Local LLM Comparison Guide",{"name":644,"url":563,"accessed":638},"AISO Tools — Msty Pricing 2026","tools\u002Fagent\u002Fgeneral\u002Fmsty","本地优先 + 多模型并行的桌面 AI——Split Chats \u002F Knowledge Stack \u002F Agent Mode 三件套",[648,649,650,651,652],"local-first","multi-model","privacy","knowledge-base","msty","Ollama \u002F LM Studio 的『精品桌面应用版』——拒绝 CLI + 拒绝云上传 + 多模型同窗对比的最佳选择。Mac mini \u002F Linux 私人 AI 服务器场景神器。要团队协作 + 云同步建议 Claude Team \u002F ChatGPT Team。","https:\u002F\u002Fmsty.ai","niNqR8c2HfHsRBNs01ip9Crt9cywkIdrVITosmvDYyA",{"id":657,"title":658,"alternatives":659,"api_compatible":9,"body":662,"category":1105,"chinese_friendly":631,"cover":1106,"description":1107,"domestic":583,"extension":584,"faq":1108,"free":583,"github":9,"languages":1121,"lastVerified":9,"meta":1123,"models":9,"navigation":602,"notSuitable":9,"opensource":602,"path":529,"pillar":1124,"platforms":1125,"priceTable":1128,"pricing":1138,"published":627,"relatedPlaybooks":1139,"relatedReviews":9,"score":1142,"self_host":602,"seo":1143,"seoTitle":1144,"slug":16,"sources":1145,"stem":1152,"suitable":9,"tagline":1153,"tags":1154,"updated":638,"verdict":1160,"website":1161,"__hash__":1162},"tools\u002Ftools\u002Fcoding\u002Flocal\u002Fopen-webui.md","Open WebUI",[660,661,14,15],"coding\u002Flocal\u002Flobe-chat","coding\u002Flocal\u002Fcherry-studio",{"type":18,"value":663,"toc":1093},[664,666,669,672,674,736,738,741,745,749,778,782,807,809,843,845,972,974,1017,1019,1042,1044,1068,1070],[21,665,24],{"id":23},[26,667,668],{},"Open WebUI（原 Ollama WebUI）是 MIT 开源、自托管 AI 平台，最常见用法是 Docker 跑起来给 Ollama 套一个 ChatGPT 风格前端。GitHub 126k+ stars、282M+ Docker pulls，事实上的本地 AI 前端首选。支持任意 OpenAI 兼容后端 + RAG 知识库 + 多用户账号 + 工具调用 + MCP-OpenAPI 代理 + 联网搜索 + 语音 + 图像生成。",[26,670,671],{},"适合：团队 \u002F 家庭 \u002F 公司部署一份共享、要 Web 端访问、多用户分账号、SearXNG 联网搜索、Confluence \u002F S3 \u002F GitHub 数据源同步。不适合：单人桌面体验（用 Cherry Studio）、零运维 \u002F 不愿碰 Docker。",[21,673,34],{"id":34},[36,675,676,682,688,694,700,706,712,718,724,730],{},[39,677,678,681],{},[42,679,680],{},"多模型后端","：Ollama \u002F OpenAI \u002F vLLM \u002F Anthropic \u002F Groq \u002F LocalAI \u002F 任意 OpenAI 兼容",[39,683,684,687],{},[42,685,686],{},"多用户 + RBAC","：注册 \u002F 邀请 \u002F 角色权限 \u002F 工作区隔离",[39,689,690,693],{},[42,691,692],{},"RAG 知识库","：上传文档 \u002F 网址 \u002F SearXNG 联网搜索 → 向量化 → 对话引用",[39,695,696,699],{},[42,697,698],{},"Tools \u002F Functions","：Python 写函数即扩展（联网 \u002F 计算器 \u002F 自定义 API）",[39,701,702,705],{},[42,703,704],{},"mcpo","：MCP-to-OpenAPI 代理，任意 MCP 服务器接进来",[39,707,708,711],{},[42,709,710],{},"oikb","：知识库同步本地文件夹 \u002F GitHub \u002F S3 \u002F Confluence 等 40+ 源",[39,713,714,717],{},[42,715,716],{},"open-terminal \u002F cptr","：给 AI 真实终端 + 文件 + 沙箱执行",[39,719,720,723],{},[42,721,722],{},"图像生成","：Stable Diffusion \u002F DALL·E \u002F 自托管接入",[39,725,726,729],{},[42,727,728],{},"语音输入 \u002F TTS","：内置",[39,731,732,735],{},[42,733,734],{},"企业 LTS","：custom branding + SLA + 长期支持版本（联系销售）",[21,737,114],{"id":114},[26,739,740],{},"完全免费、MIT 开源、商用免费。Enterprise 提供品牌定制 + SLA + LTS。",[21,742,744],{"id":743},"实测ubuntu-2404-ollama-后端-5-人小团队","实测（Ubuntu 24.04 + Ollama 后端 + 5 人小团队）",[26,746,747],{},[42,748,155],{},[36,750,751,759,762,769,772,775],{},[39,752,753,754,758],{},"单条 ",[755,756,757],"code",{},"docker run"," 五分钟上线",[39,760,761],{},"自带的多用户 + 角色权限省去重新搭 Auth",[39,763,764,765,768],{},"RAG 直传 30 个 PDF 后向量化顺利，对话中 ",[755,766,767],{},"#知识库"," 引用准确",[39,770,771],{},"mcpo 把 GitHub MCP 服务器接进来，团队对话里直接 issue \u002F PR 操作",[39,773,774],{},"模型切换流畅，OpenAI + Ollama 并存",[39,776,777],{},"SearXNG 联网搜索给模型实时信息，过时知识截止问题缓解",[26,779,780],{},[42,781,186],{},[36,783,784,787,794,801,804],{},[39,785,786],{},"Docker 镜像 ~1.5GB，首次拉取偏慢",[39,788,789,790,793],{},"默认 ",[755,791,792],{},"0.0.0.0"," 公网暴露要加 HTTPS + 反代",[39,795,796,797,800],{},"嵌入模型 ",[755,798,799],{},"sentence-transformers"," 中文效果一般，建议换 bge-m3",[39,802,803],{},"多用户共享 Ollama 时并发吞吐瓶颈在 Ollama，不在 Open WebUI（生产用 vLLM 后端）",[39,805,806],{},"版本升级要看 changelog，部分 minor 含 breaking 改动",[21,808,215],{"id":215},[217,810,811,817,824,827,830,833,836],{},[39,812,813,814],{},"装 Docker → ",[755,815,816],{},"docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:\u002Fapp\u002Fbackend\u002Fdata --name open-webui --restart always ghcr.io\u002Fopen-webui\u002Fopen-webui:main",[39,818,819,820,823],{},"浏览器开 ",[755,821,822],{},"http:\u002F\u002Flocalhost:3000"," → 注册第一个账号（管理员）",[39,825,826],{},"设置 → Connections → 连接 Ollama \u002F 加 OpenAI Key",[39,828,829],{},"Models → Pull \u002F Discover 模型",[39,831,832],{},"Workspaces → 建知识库 → 上传文档",[39,834,835],{},"Tools → 启用 \u002F 写自定义函数",[39,837,838,839,842],{},"生产部署：Nginx 反代 + Let's Encrypt + 备份 ",[755,840,841],{},"\u002Fapp\u002Fbackend\u002Fdata"," volume",[21,844,242],{"id":242},[244,846,847,863],{},[247,848,849],{},[250,850,851,853,855,858,861],{},[253,852,255],{},[253,854,658],{},[253,856,857],{},"LobeChat",[253,859,860],{},"Cherry Studio",[253,862,263],{},[268,864,865,881,896,911,925,940,956],{},[250,866,867,870,873,876,879],{},[273,868,869],{},"形态",[273,871,872],{},"Docker \u002F 桌面",[273,874,875],{},"Web + 桌面",[273,877,878],{},"桌面",[273,880,878],{},[250,882,883,886,889,891,894],{},[273,884,885],{},"多用户",[273,887,888],{},"✅ 一等",[273,890,284],{},[273,892,893],{},"无",[273,895,893],{},[250,897,898,901,904,906,908],{},[273,899,900],{},"RAG",[273,902,903],{},"✅ 强 + oikb",[273,905,284],{},[273,907,284],{},[273,909,910],{},"弱",[250,912,913,916,919,921,923],{},[273,914,915],{},"工具 \u002F MCP",[273,917,918],{},"✅ mcpo",[273,920,284],{},[273,922,284],{},[273,924,910],{},[250,926,927,930,933,936,938],{},[273,928,929],{},"自托管",[273,931,932],{},"✅ Docker \u002F K8s",[273,934,935],{},"✅ Docker",[273,937,893],{},[273,939,893],{},[250,941,942,945,948,951,954],{},[273,943,944],{},"GitHub Stars",[273,946,947],{},"126k+",[273,949,950],{},"72k+",[273,952,953],{},"60k+",[273,955,330],{},[250,957,958,961,964,966,969],{},[273,959,960],{},"开源协议",[273,962,963],{},"MIT",[273,965,963],{},[273,967,968],{},"AGPL-3.0",[273,970,971],{},"闭源（免费）",[21,973,420],{"id":420},[36,975,976,982,990,999,1005,1011],{},[39,977,978,981],{},[42,979,980],{},"不要裸 0.0.0.0 + HTTP 暴露公网","：默认无 HTTPS，必上反代 + 强密码 + 速率限制",[39,983,984,989],{},[42,985,986,987,842],{},"备份 ",[755,988,841],{},"：知识库 \u002F 用户 \u002F 对话全在里面",[39,991,992,995,996,998],{},[42,993,994],{},"中文 RAG 换嵌入模型","：默认 ",[755,997,799],{}," 中文一般，配 bge-m3 或硅基流动嵌入 API",[39,1000,1001,1004],{},[42,1002,1003],{},"mcpo 工具范围谨慎","：MCP 给 AI 真实能力，第三方服务器审一遍",[39,1006,1007,1010],{},[42,1008,1009],{},"后端吞吐看 Ollama","：5+ 并发上 vLLM 后端，Ollama 单 worker 会排队",[39,1012,1013,1016],{},[42,1014,1015],{},"升级前看 changelog","：weekly 更新，偶有 breaking",[21,1018,480],{"id":479},[36,1020,1021,1024,1027,1030,1033,1036,1039],{},[39,1022,1023],{},"✅ 团队 \u002F 家庭 \u002F 公司多人共享 AI 平台",[39,1025,1026],{},"✅ 要 Web 端访问 \u002F 移动端兼容",[39,1028,1029],{},"✅ 自托管 \u002F 完全控制数据",[39,1031,1032],{},"✅ MCP \u002F 工具调用刚需",[39,1034,1035],{},"❌ 单人桌面体验（用 Cherry Studio）",[39,1037,1038],{},"❌ 零运维 \u002F 不愿碰 Docker",[39,1040,1041],{},"❌ iOS 原生 App 主力",[21,1043,509],{"id":509},[36,1045,1046,1052,1058,1062],{},[39,1047,1048],{},[515,1049,1051],{"href":1050},"\u002Ftools\u002Fcoding\u002Flocal\u002Flobe-chat","LobeChat 评测",[39,1053,1054],{},[515,1055,1057],{"href":1056},"\u002Ftools\u002Fcoding\u002Flocal\u002Fcherry-studio","Cherry Studio 评测",[39,1059,1060],{},[515,1061,518],{"href":517},[39,1063,1064],{},[515,1065,1067],{"href":1066},"\u002Fplaybook\u002Fonboarding\u002Frag-pipeline-build","RAG Pipeline 搭建 Playbook",[21,1069,533],{"id":533},[217,1071,1072,1079,1086],{},[39,1073,1074,1075],{},"Open WebUI 官方文档 ",[515,1076,1077],{"href":1077,"rel":1078},"https:\u002F\u002Fdocs.openwebui.com\u002F",[543],[39,1080,1081,1082],{},"Local AI Master — Open WebUI Setup Guide 2026 ",[515,1083,1084],{"href":1084,"rel":1085},"https:\u002F\u002Flocalaimaster.com\u002Fblog\u002Fopen-webui-setup-guide",[543],[39,1087,1088,1089],{},"AIToolDiscovery — Set Up Open-WebUI with Ollama 2026 ",[515,1090,1091],{"href":1091,"rel":1092},"https:\u002F\u002Fwww.aitooldiscovery.com\u002Fhow-to\u002Fsetup-open-webui-ollama",[543],{"title":566,"searchDepth":567,"depth":567,"links":1094},[1095,1096,1097,1098,1099,1100,1101,1102,1103,1104],{"id":23,"depth":570,"text":24},{"id":34,"depth":570,"text":34},{"id":114,"depth":570,"text":114},{"id":743,"depth":570,"text":744},{"id":215,"depth":570,"text":215},{"id":242,"depth":570,"text":242},{"id":420,"depth":570,"text":420},{"id":479,"depth":570,"text":480},{"id":509,"depth":570,"text":509},{"id":533,"depth":570,"text":533},"local","\u002Fimg\u002Ftools\u002Fopen-webui.webp","Open WebUI 2026 真实评测：MIT 开源、自托管 ChatGPT 替代和 Ollama Web 前端。支持 Docker 一行部署、Ollama\u002FOpenAI\u002FvLLM 多后端、RAG 知识库、多用户、联网搜索、工具调用和 MCP-to-OpenAPI，适合团队私有 AI 平台。",[1109,1112,1115,1118],{"q":1110,"a":1111},"Docker 一行命令真的够用吗？","够。`docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:\u002Fapp\u002Fbackend\u002Fdata --name open-webui --restart always ghcr.io\u002Fopen-webui\u002Fopen-webui:main`，5 分钟可上线、能多人注册、能接 Ollama \u002F OpenAI。生产再加反代 + HTTPS + 备份。",{"q":1113,"a":1114},"支持哪些模型后端？","Ollama（首选）+ 任何 OpenAI 兼容 endpoint：OpenAI 官方 \u002F Anthropic（OpenAI 兼容代理）\u002F vLLM \u002F Groq \u002F LocalAI \u002F 自建 baseURL。可同时配多个，对话中切换。",{"q":1116,"a":1117},"RAG \u002F 知识库怎么做？","内置：上传 PDF \u002F DOCX \u002F TXT、网址抓取、SearXNG 联网搜索 → 自动向量化 → 在对话中 `#` 引用知识库。配套 oikb 项目可同步本地文件夹 \u002F GitHub \u002F S3 \u002F Confluence 等 40+ 数据源。",{"q":1119,"a":1120},"MCP 怎么接？","通过 mcpo（官方的 MCP-to-OpenAPI 代理）把任意 MCP 服务器暴露成 OpenAPI 工具，再在 Open WebUI 注册即可。无需写 glue code。",[599,1122],"zh",{},"coding",[1126,608,606,607,1127],"docker","kubernetes",[1129,1134],{"plan":1130,"price":1131,"features":1132,"notes":1133},"开源版","免费","全功能 \u002F 多用户 \u002F RAG \u002F Tools \u002F 联网搜索 \u002F MCP-OpenAPI 代理 \u002F Docker \u002F K8s","MIT 协议",{"plan":139,"price":1135,"features":1136,"notes":1137},"咨询","Custom branding \u002F SLA \u002F LTS 长期支持版本","邮件官方","完全免费（MIT 开源） \u002F Enterprise SLA 联系",[1140,1141],"onboarding\u002Frag-pipeline-build","onboarding\u002Fclaude-code-getting-started",{"power":632,"ux":631,"price":632,"cn_support":631,"stability":632},{"title":658,"description":1107},"Open WebUI 评测 2026：自托管 ChatGPT 替代，Ollama 前端部署指南",[1146,1148,1150],{"name":1147,"url":1077,"accessed":638},"Open WebUI 官方文档",{"name":1149,"url":1084,"accessed":638},"Local AI Master — Open WebUI Setup Guide 2026",{"name":1151,"url":1091,"accessed":638},"AIToolDiscovery — Open-WebUI with Ollama 2026","tools\u002Fcoding\u002Flocal\u002Fopen-webui","自托管的 ChatGPT 替代：Ollama \u002F OpenAI 兼容、多用户、RAG、126k+ GitHub stars",[1105,1155,1126,1156,1157,1158,1159],"self-host","rag","multi-user","ollama","open-source","自托管多用户 AI 前端的事实标准。团队 \u002F 家庭 \u002F 公司部署一份共享，多模型聚合 + RAG + 工具调用全有。单机 \u002F 桌面体验首选 Cherry Studio \u002F LobeChat。","https:\u002F\u002Fdocs.openwebui.com","JCKn_X0aojpl94LKJcqlbs0XSTAxv8S8JgKy70WtsO0",1784565440445]