[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-kossakovsky--n8n-install":3,"tool-kossakovsky--n8n-install":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":70,"readme_en":71,"readme_zh":72,"quickstart_zh":73,"use_case_zh":74,"hero_image_url":75,"owner_login":76,"owner_name":77,"owner_avatar_url":78,"owner_bio":79,"owner_company":79,"owner_location":80,"owner_email":79,"owner_twitter":81,"owner_website":79,"owner_url":82,"languages":83,"stars":104,"forks":105,"last_commit_at":106,"license":107,"difficulty_score":10,"env_os":108,"env_gpu":109,"env_ram":110,"env_deps":111,"category_tags":116,"github_topics":117,"view_count":10,"oss_zip_url":79,"oss_zip_packed_at":79,"status":16,"created_at":138,"updated_at":139,"faqs":140,"releases":169},294,"kossakovsky\u002Fn8n-install","n8n-install","🚀 Self-hosted AI automation platform. Deploy n8n, Ollama, Flowise, RAG, Supabase & 30+ tools with one command. Auto HTTPS. Free Zapier\u002FMake alternative.","n8n-install 是一个强大的开源脚本，旨在帮助用户一键部署自托管的 AI 自动化平台。它能够将 n8n、Ollama、Flowise、Supabase 等 30 多种主流工具整合到一个 Docker Compose 环境中，极大简化了复杂系统的搭建过程。\n\n对于希望掌控数据隐私且不愿受限于商业云服务的用户来说，n8n-install 解决了手动配置多个服务、处理依赖冲突以及设置安全证书等繁琐问题。它让搭建私有化 AI 工作流变得像安装普通软件一样简单，同时确保了数据的本地化存储和安全传输。\n\n这款方案特别适合开发者、运维人员以及热衷于家庭实验室的技术爱好者。无论你是想利用 n8n 自动化日常任务，还是希望通过 Ollama 运行本地大模型，n8n-install 都能提供坚实的基础设施。技术上，n8n-install 支持交互式安装向导，自动配置 Let's Encrypt HTTPS 证书，并默认启用 n8n 的队列模式以优化性能。此外，内置的 Grafana 监控栈和可选的社区工作流导入功能，进一步提升了生产环境的可用性和扩展性。作为一个完全免费且遵循 Apache 2.0","n8n-install 是一个强大的开源脚本，旨在帮助用户一键部署自托管的 AI 自动化平台。它能够将 n8n、Ollama、Flowise、Supabase 等 30 多种主流工具整合到一个 Docker Compose 环境中，极大简化了复杂系统的搭建过程。\n\n对于希望掌控数据隐私且不愿受限于商业云服务的用户来说，n8n-install 解决了手动配置多个服务、处理依赖冲突以及设置安全证书等繁琐问题。它让搭建私有化 AI 工作流变得像安装普通软件一样简单，同时确保了数据的本地化存储和安全传输。\n\n这款方案特别适合开发者、运维人员以及热衷于家庭实验室的技术爱好者。无论你是想利用 n8n 自动化日常任务，还是希望通过 Ollama 运行本地大模型，n8n-install 都能提供坚实的基础设施。技术上，n8n-install 支持交互式安装向导，自动配置 Let's Encrypt HTTPS 证书，并默认启用 n8n 的队列模式以优化性能。此外，内置的 Grafana 监控栈和可选的社区工作流导入功能，进一步提升了生产环境的可用性和扩展性。作为一个完全免费且遵循 Apache 2.0 协议的解决方案，n8n-install 为用户提供了灵活、可控且高效的 AI 基础设施选择。","# Self-Hosted AI Automation Platform\n\n[![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fkossakovsky\u002Fn8n-install?style=social)](https:\u002F\u002Fgithub.com\u002Fkossakovsky\u002Fn8n-install\u002Fstargazers)\n[![License](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-Apache%202.0-blue.svg)](LICENSE)\n[![Docker](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fdocker-ready-blue?logo=docker)](https:\u002F\u002Fwww.docker.com\u002F)\n[![Ubuntu](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FUbuntu-24.04%20LTS-E95420?logo=ubuntu&logoColor=white)](https:\u002F\u002Fubuntu.com\u002F)\n[![n8n](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fn8n-compatible-orange)](https:\u002F\u002Fn8n.io)\n\n**Deploy 30+ AI and automation tools with a single command.** This open-source Docker Compose template creates a complete self-hosted environment with n8n (workflow automation), Flowise (AI agents), Ollama (local LLMs), vector databases (Qdrant, Weaviate), RAG engines, Supabase, monitoring stack, and more — all pre-configured behind Caddy reverse proxy with automatic HTTPS. Plus, optionally import 300+ community workflows during setup!\n\n## Table of Contents\n\n- [Key Features](#key-features)\n- [Why This Setup?](#why-this-setup)\n- [What's Included](#whats-included)\n- [Installation](#installation)\n- [Quick Start and Usage](#quick-start-and-usage)\n- [Upgrading](#upgrading)\n- [Quick Commands](#quick-commands-makefile)\n- [Troubleshooting](#troubleshooting)\n- [License](#license)\n\n## Key Features\n\n- **Private AI Homelab** — Run LLMs locally with Ollama, keep your data on your own servers\n- **ChatGPT Alternative** — Open WebUI provides a familiar chat interface for local AI models\n- **Workflow Automation** — n8n with 400+ integrations, scalable queue-based architecture\n- **AI Agents & RAG** — Flowise, Dify, LangChain, vector databases (Qdrant, Weaviate)\n- **One Command Install** — Interactive wizard, automatic secrets, zero manual configuration\n- **Auto HTTPS** — Caddy reverse proxy with automatic Let's Encrypt certificates\n- **Built-in Monitoring** — Grafana + Prometheus stack included\n- **Production Ready** — Scalable workers, health checks, proper service dependencies\n- **Free & Open Source** — No vendor lock-in, Apache 2.0 license\n\n---\n\n## Why This Setup?\n\nThis installer helps you create your own powerful, private AI workshop. Imagine having a suite of tools at your fingertips to:\n\n- Automate repetitive tasks.\n- Build smart assistants tailored to your needs.\n- Analyze information and gain insights.\n- Generate creative content.\n\nThis setup provides a comprehensive suite of cutting-edge services, all pre-configured to work together. Key advantages include:\n\n- **Rich Toolset:** Get a curated collection of powerful open-source tools for AI development, automation, and monitoring, all in one place.\n- **Scalable n8n Performance:** n8n runs in `queue` mode by default, leveraging Redis for task management and Postgres for data storage. You can dynamically specify the number of n8n workers and task runners during installation, allowing for robust parallel processing of your workflows to handle demanding loads.\n- **Full Control:** All of this is hosted by you, giving you full control over your data, operations, and how resources are allocated.\n\n## What's Included\n\n\n✅ **[Caddy](https:\u002F\u002Fcaddyserver.com\u002F), [Postgres](https:\u002F\u002Fwww.postgresql.org\u002F), and [Redis](https:\u002F\u002Fredis.io\u002F)** - Core services for web proxy, database, and caching, which are always included.\n\nThe installer also makes the following powerful open-source tools **available for you to select and deploy** via an interactive wizard during setup:\n\n✅ [**Appsmith**](https:\u002F\u002Fwww.appsmith.com\u002F) - An open-source low-code platform for building internal tools, dashboards, and admin panels with a drag-and-drop UI builder.\n\n✅ [**n8n**](https:\u002F\u002Fn8n.io\u002F) - A low-code platform with over 400 integrations and advanced AI components to automate workflows.\n\n✅ [**ComfyUI**](https:\u002F\u002Fgithub.com\u002Fcomfyanonymous\u002FComfyUI) - A powerful, node-based UI for Stable Diffusion workflows. Build and run image-generation pipelines visually, with support for custom nodes and extensions.\n\n✅ [**Crawl4ai**](https:\u002F\u002Fgithub.com\u002Funclecode\u002Fcrawl4ai) - A flexible web crawler designed for AI, enabling you to extract data from websites for your projects.\n\n✅ [**Docling**](https:\u002F\u002Fgithub.com\u002Fdocling-project\u002Fdocling-serve) - Universal document converter that transforms PDF, DOCX, PPTX, XLSX, HTML, and images into clean Markdown or JSON. Features advanced PDF parsing, OCR support, and a REST API with optional web UI. Perfect for document processing in n8n workflows.\n\n✅ [**Dify**](https:\u002F\u002Fdify.ai\u002F) - An open-source AI application development platform that provides comprehensive LLMOps capabilities, including workflow management, prompt engineering, RAG pipelines, and AI agent orchestration. Perfect for building production-ready AI applications.\n\n✅ [**Flowise**](https:\u002F\u002Fflowiseai.com\u002F) - A no-code\u002Flow-code AI agent builder that complements n8n perfectly, allowing you to create sophisticated AI applications with ease.\n\n✅ [**Gost**](https:\u002F\u002Fgithub.com\u002Fgo-gost\u002Fgost) - Versatile HTTP\u002FHTTPS proxy for routing AI service outbound traffic through a central proxy point\n\n✅ [**Gotenberg**](https:\u002F\u002Fgotenberg.dev\u002F) - A stateless API for converting HTML, Markdown, Word, Excel, and other documents to PDF, PNG, or JPEG. Available only within the Docker network for internal use by n8n workflows and other services.\n\n✅ [**Grafana**](https:\u002F\u002Fgrafana.com\u002F) - An open-source platform for visualizing monitoring data, helping you understand system performance at a glance.\n\n✅ [**Langfuse**](https:\u002F\u002Flangfuse.com\u002F) - An open-source platform to help you observe and understand how your AI agents are performing, making it easier to debug and improve them.\n\n✅ [**Letta**](https:\u002F\u002Fdocs.letta.com\u002F) - An open-source agent server and SDK that can be connected to various LLM API backends (OpenAI, Anthropic, Ollama, etc.), enabling you to build and manage AI agents.\n\n✅ [**LightRAG**](https:\u002F\u002Fgithub.com\u002FHKUDS\u002FLightRAG) - A simple and fast graph-based Retrieval-Augmented Generation system with automatic knowledge graph extraction, dual-level retrieval mechanisms, and incremental updates. Supports multiple storage backends (PostgreSQL, Neo4j, JSON) and embedding models.\n\n✅ [**LibreTranslate**](https:\u002F\u002Fdocs.libretranslate.com\u002F) - Self-hosted translation API (50+ languages).\n\n✅ [**Neo4j**](https:\u002F\u002Fneo4j.com\u002F) - A graph database management system that allows you to model, store, and query data as a network of nodes and relationships.\n\n✅ [**NocoDB**](https:\u002F\u002Fnocodb.com\u002F) - An open source Airtable alternative that turns any database into a smart spreadsheet with a no-code interface for building collaborative apps.\n\n✅ [**Ollama**](https:\u002F\u002Follama.com\u002F) - Run Llama 3, Mistral, Gemma, and other large language models locally.\n\n✅ [**Open WebUI**](https:\u002F\u002Fopenwebui.com\u002F) - A user-friendly, ChatGPT-like interface to interact privately with your AI models and n8n agents.\n\n✅ [**PaddleOCR**](https:\u002F\u002Fwww.paddleocr.ai\u002Flatest\u002Fen\u002Findex.html) - A CPU-ready OCR API powered by PaddleX Basic Serving. \n\n✅ [**Portainer**](https:\u002F\u002Fwww.portainer.io\u002F) - A lightweight, secure web UI to manage your Docker environment (containers, images, volumes, networks) with ease.\n\n✅ [**Databasus**](https:\u002F\u002Fgithub.com\u002Fdatabasus\u002Fdatabasus) - Database backups & monitoring with a self-hosted UI.\n\n✅ [**Postiz**](https:\u002F\u002Fpostiz.com\u002F) - An open-source social media scheduling and publishing platform.\n\n✅ [**Prometheus**](https:\u002F\u002Fprometheus.io\u002F) - An open-source monitoring and alerting toolkit to keep an eye on system health.\n\n✅ [**Qdrant**](https:\u002F\u002Fqdrant.tech\u002F) - A high-performance open-source vector store, specialized for AI. While Supabase also offers vector capabilities, Qdrant is included for its speed, making it ideal for demanding AI tasks.\n\n✅ [**RAGApp**](https:\u002F\u002Fgithub.com\u002Fragapp\u002Fragapp) - Open-source application to build Retrieval-Augmented Generation (RAG) assistants over your data. Provides a web UI for chat and an HTTP API for integration with your workflows.\n\n✅ [**RAGFlow**](https:\u002F\u002Fragflow.io\u002F) - An open-source RAG engine based on deep document understanding with Elasticsearch backend, providing truthful question-answering capabilities with well-founded citations from complex formatted data.\n\n✅ [**SearXNG**](https:\u002F\u002Fsearxng.org\u002F) - A free, open-source internet metasearch engine. It aggregates results from numerous search services without tracking or profiling you, ensuring your privacy.\n\n✅ [**Supabase**](https:\u002F\u002Fsupabase.com\u002F) - An open-source alternative to Firebase, providing database storage, user authentication, and more. It's a popular choice for AI applications.\n\n✅ [**Uptime Kuma**](https:\u002F\u002Fgithub.com\u002Flouislam\u002Fuptime-kuma) - Self-hosted uptime monitoring tool with notifications\n\n✅ [**WAHA**](https:\u002F\u002Fwaha.devlike.pro\u002F) - WhatsApp HTTP API (REST API) that you can configure in a click! 3 engines: WEBJS (browser based), NOWEB (websocket nodejs), GOWS (websocket go).\n\n✅ [**Weaviate**](https:\u002F\u002Fweaviate.io\u002F) - An open-source AI-native vector database with a focus on scalability and ease of use. It can be used for RAG, hybrid search, and more.\n\n## Included Community Workflows\n\nGet started quickly with a vast library of pre-built automations (optional import during setup)! This collection includes over 300 workflows covering a wide range of use cases:\n\n🚦 **What's inside?**\n\n- **AI Agents & Chatbots:** RAG, LLM, LangChain, Ollama, OpenAI, Claude, Gemini, and more\n- **Gmail & Outlook:** Smart labeling, auto-replies, PDF handling, and email-to-Notion\n- **HR, E-commerce, IT, Security, Research, and more!**\n- **Notion, Airtable, Google Sheets:** Data sync, AI summaries, knowledge bases\n- **PDF, Image, Audio, Video:** Extraction, summarization, captioning, speech-to-text\n- **Slack, Mattermost:** Ticketing, feedback analysis, notifications\n- **Social Media:** LinkedIn, Pinterest, Instagram, Twitter\u002FX, YouTube, TikTok automations\n- **Telegram, WhatsApp, Discord:** Bots, notifications, voice, and image workflows\n- **WordPress, WooCommerce:** AI content, chatbots, auto-tagging\n\n## Installation\n\n### Prerequisites before Installation\n\n1.  **Domain Name:** You need a registered domain name (e.g., `yourdomain.com`).\n2.  **DNS Configuration:** Before running the installation script, you **must** configure DNS A-record for your domain, pointing to the public IP address of the server where you'll install this system. Replace `yourdomain.com` with your actual domain:\n    - **Wildcard Record:** `A *.yourdomain.com` -> `YOUR_SERVER_IP`\n3.  **VPS (Virtual Private Server):** A dedicated VPS with a public IP address is required. Home servers, shared hosting, or localhost setups are not supported.\n    - **Operating System:** Ubuntu 24.04 LTS, 64-bit\n    - For a minimal setup with **n8n, Monitoring, Databasus and Portainer**: **4 GB Memory \u002F 2 CPU Cores \u002F 40 GB Disk Space**\n    - For running **all available services**: at least **20 GB Memory \u002F 4 CPU Cores \u002F 60 GB Disk Space**\n\n### Running the Install\n\nThe recommended way to install is using the provided main installation script.\n\n1.  Connect to your server via SSH.\n2.  Run the following command:\n\n    ```bash\n    git clone https:\u002F\u002Fgithub.com\u002Fkossakovsky\u002Fn8n-install && cd n8n-install && sudo bash .\u002Fscripts\u002Finstall.sh\n    ```\n\nThis single command automates the entire setup process, including:\n\n- Preparing your system (updates, firewall configuration, and basic security enhancements like brute-force protection).\n- Installing Docker and Docker Compose (tools for running applications in isolated environments).\n- Generating a configuration file (`.env`) with necessary secrets and your domain settings.\n- Launching all the services.\n\nDuring the installation, the script will prompt you for:\n\n1.  Your **primary domain name** (Required, e.g., `yourdomain.com`). This is the domain for which you've configured the wildcard DNS record.\n2.  Your **email address** (Required, used for service logins like Flowise, Supabase dashboard, Grafana, and for SSL certificate registration with Let's Encrypt).\n3.  An optional **OpenAI API key** (Not required. If provided, it can be used by Supabase AI features and Crawl4ai. Press Enter to skip).\n4.  Whether you want to **import ~300 ready-made n8n community workflows** (y\u002Fn, Optional. This can take 20-30 minutes, depending on your server and network speed).\n5.  The **number of n8n workers** you want to run (Required, e.g., 1, 2, 3, 4. This determines how many workflows can be processed in parallel. Each worker automatically gets its own dedicated task runner sidecar for executing Code nodes. Defaults to 1 if not specified).\n6.  A **Service Selection Wizard** will then appear, allowing you to choose which of the available services (like Flowise, Supabase, Qdrant, Open WebUI, etc.) you want to deploy. Core services (Caddy, Postgres, Redis) will be set up to support your selections.\n\nUpon successful completion, the script will display a summary report. This report contains the access URLs and credentials for the deployed services. **Save this information in a safe place!**\n\n## Quick Start and Usage\n\nAfter successful installation, your services are up and running! Here's how to get started:\n\n1.  **Access Your Services:**\n    The installation script provided a summary report with all access URLs and credentials. Please refer to that report. The main services will be available at the following addresses (replace `yourdomain.com` with your actual domain):\n\n    - **n8n:** `n8n.yourdomain.com` (Log in with the email address you provided during installation and the initial password from the summary report. You may be prompted to change this password on first login.)\n    - **Appsmith:** `appsmith.yourdomain.com` (Low-code app builder)\n    - **ComfyUI:** `comfyui.yourdomain.com` (Node-based Stable Diffusion UI)\n    - **Databasus:** `databasus.yourdomain.com`\n    - **Dify:** `dify.yourdomain.com` (AI application development platform with comprehensive LLMOps capabilities)\n    - **Docling:** `docling.yourdomain.com` (Universal document converter with REST API; web UI available at `\u002Fui`)\n    - **Flowise:** `flowise.yourdomain.com` (Log in with the email address you provided during installation and the initial password from the summary report.)\n    - **Grafana:** `grafana.yourdomain.com`\n    - **Langfuse:** `langfuse.yourdomain.com`\n    - **Letta:** `letta.yourdomain.com`\n    - **LibreTranslate:** `translate.yourdomain.com`\n    - **LightRAG:** `lightrag.yourdomain.com`\n    - **Neo4j:** `neo4j.yourdomain.com`\n    - **NocoDB:** `nocodb.yourdomain.com`\n    - **Open WebUI:** `webui.yourdomain.com`\n    - **PaddleOCR:** `paddleocr.yourdomain.com`\n    - **Portainer:** `portainer.yourdomain.com` (Protected by Caddy basic auth; on first login, complete Portainer admin setup)\n    - **Postiz:** `postiz.yourdomain.com`\n    - **Prometheus:** `prometheus.yourdomain.com` (Typically used as a data source for Grafana)\n    - **Qdrant:** `qdrant.yourdomain.com`\n    - **RAGApp:** `ragapp.yourdomain.com`\n    - **RAGFlow:** `ragflow.yourdomain.com`\n    - **SearXNG:** `searxng.yourdomain.com`\n    - **Supabase (Dashboard):** `supabase.yourdomain.com`\n    - **Uptime Kuma:** `uptime-kuma.yourdomain.com` (Uptime monitoring dashboard)\n    - **WAHA:** `waha.yourdomain.com` (WhatsApp HTTP API; engines: WEBJS, NOWEB, GOWS)\n    - **Weaviate:** `weaviate.yourdomain.com`\n\n### Optional Internal Utility: Python Runner\n\n- **What it is**: An internal-only service to run your custom Python code inside the same Docker network as your other services (n8n, Postgres, Qdrant, etc.). No external ports are exposed, and it is not proxied by Caddy.\n- **How to enable**: Select “Python Runner” in the Service Selection Wizard during install\u002Fupdate, or add the profile manually: `COMPOSE_PROFILES=...,python-runner`.\n- **Where to put code**: Place your Python files in `python-runner\u002F`. The default entry point is `python-runner\u002Fmain.py`.\n- **Dependencies**: Add them to `python-runner\u002Frequirements.txt`; they will be installed automatically on container start.\n\n2.  **Explore n8n:**\n\n    - Log in to your n8n instance. This is your central hub for workflow automation.\n    - If you chose to import the community workflows during installation, you'll find over 300 examples in your \"Workflows\" section. These are a great way to learn and get ideas.\n    - Start building your first workflow! You have access to over 400 integrations and powerful AI tools.\n\n3.  **Utilize Integrated AI Tools:**\n\n    - **Connect n8n with Vector Stores:** Use n8n to connect to Qdrant (accessible via its own endpoint if needed, typically `qdrant.yourdomain.com`), Supabase, or Weaviate (`weaviate.yourdomain.com`) to store and retrieve information for your AI tasks like Retrieval Augmented Generation (RAG).\n    - **Build with Flowise:** Access Flowise at `flowise.yourdomain.com` to create AI agents and applications. You can trigger Flowise agents from n8n or vice-versa.\n    - **Interact with Open WebUI:** Use Open WebUI at `webui.yourdomain.com` as a chat interface for your local AI models or n8n agents (e.g., using the n8n_pipe integration if configured).\n    - **Configure LLMs:** If you wish to use large language models (LLMs) from providers like OpenAI, Anthropic, or locally via Ollama (if installed), you can easily configure credentials and connections within n8n nodes or in services like Flowise and Open WebUI.\n\n4.  **Check Monitoring (Optional):**\n    - Visit Grafana (`grafana.yourdomain.com`) to see dashboards monitoring your system's performance (data sourced from Prometheus).\n\t\n\n## Secure Access with Cloudflare Tunnel (Optional)\n\nCloudflare Tunnel provides zero-trust access to your services without exposing any ports on your server. All traffic is routed through Cloudflare's secure network, providing DDoS protection and hiding your server's IP address.\n\n### Benefits\n- **No exposed ports** - Ports 80\u002F443 can be completely closed\n- **DDoS protection** - Built-in Cloudflare protection\n- **IP hiding** - Your server's real IP is never exposed\n- **Zero-trust security** - Optional Cloudflare Access integration\n- **No public IP required** - Works on private networks\n\n### Setup Instructions\n\nSee the Cloudflare Tunnel guide: [cloudflare-instructions.md](cloudflare-instructions.md)\n\n\n### Using Libraries in n8n Code Nodes (v2.0+)\n\nn8n v2.0 uses external task runners to execute JavaScript and Python code in Code nodes. This setup pre-configures the following libraries via `n8n\u002FDockerfile.runner` and `n8n\u002Fn8n-task-runners.json`:\n\n**JavaScript libraries**:\n- **`cheerio`**: For parsing and manipulating HTML\u002FXML (e.g., web scraping).\n- **`axios`**: A promise-based HTTP client for making requests to external APIs.\n- **`moment`**: For parsing, validating, manipulating, and displaying dates\u002Ftimes.\n- **`lodash`**: A utility library for common programming tasks (arrays, objects, strings, etc.).\n\n### Pre-installed System Tools in n8n\n\nThe custom n8n Docker image (`n8n\u002FDockerfile.n8n`) includes the following system-level tools:\n\n- **`ffmpeg`**: A powerful multimedia framework for converting, recording, and streaming audio and video. Use it via the [Execute Command](https:\u002F\u002Fdocs.n8n.io\u002Fintegrations\u002Fbuiltin\u002Fcore-nodes\u002Fn8n-nodes-base.executecommand\u002F) node in n8n workflows for tasks like:\n  - Converting video\u002Faudio formats (e.g., MP4 to MP3)\n  - Extracting audio from video files\n  - Resizing or compressing media files\n  - Generating thumbnails from videos\n\n## Upgrading\n\nTo update all components (n8n, Open WebUI, etc.) to their latest versions and incorporate the newest changes from this installer project:\n\n```bash\nmake update\n```\n\n**For forks**: If you maintain a fork with custom changes and want to merge updates from upstream instead of resetting:\n\n```bash\nmake git-pull\n```\n\nThis script will:\n\n1.  Fetch the latest updates for the installer from the Git repository.\n2.  Temporarily stop the currently running services.\n3.  Download the latest versions of the Docker images for all services.\n4.  Ask if you want to re-run the n8n workflow import (useful if you skipped this during the initial installation or want to refresh the community workflows).\n5.  Restart all services with the new updates.\n\n## Cleaning up Docker\n\nIf you need to free up disk space, you can run the Docker cleanup command. This removes all unused Docker containers, images, and volumes.\n\n```bash\nmake clean\n```\n\nThis can be useful for removing old images and freeing up space, but be aware that it will remove all unused data.\n\n## Quick Commands (Makefile)\n\nThe project includes a Makefile for simplified command execution:\n\n### Installation & Updates\n\n| Command               | Description                                          |\n| --------------------- | ---------------------------------------------------- |\n| `make install`        | Full installation                                    |\n| `make update`         | Update system and services (resets to origin)        |\n| `make update-preview` | Preview available updates without applying (dry-run) |\n| `make git-pull`       | Update for forks (merges from upstream\u002Fmain)         |\n| `make clean`          | Remove unused Docker resources                       |\n\n### Monitoring & Logs\n\n| Command                 | Description                                              |\n| ----------------------- | -------------------------------------------------------- |\n| `make logs`             | View logs (all services)                                 |\n| `make logs s=\u003Cservice>` | View logs for specific service (e.g., `make logs s=n8n`) |\n| `make status`           | Show container status                                    |\n| `make monitor`          | Live CPU\u002Fmemory monitoring                               |\n| `make restart`          | Restart all services                                     |\n| `make stop`             | Stop all services                                        |\n| `make start`            | Start all services                                       |\n| `make show-restarts`    | Show restart count per container                         |\n| `make import`           | Import n8n workflows from backup                         |\n| `make import n=10`      | Import first N workflows only                            |\n\n### Diagnostics & Configuration\n\n| Command          | Description                                                        |\n| ---------------- | ------------------------------------------------------------------ |\n| `make doctor`    | Run system diagnostics (checks DNS, SSL, containers, disk, memory) |\n| `make setup-tls` | Configure custom TLS certificates for corporate\u002Finternal use       |\n\nRun `make help` for the full list of available commands.\n\n## Community Ports\n\n- [n8n-installer-arch](https:\u002F\u002Fgithub.com\u002Fndrewpj\u002Fn8n-installer-arch) by [@ndrewpj](https:\u002F\u002Fgithub.com\u002Fndrewpj) - Adapted for Arch-based Linux distributions (Arch Linux, CachyOS, Manjaro)\n\n## Important Links\n\n- Based on a project by [coleam00](https:\u002F\u002Fgithub.com\u002Fcoleam00\u002Flocal-ai-packaged)\n- [Original Starter Kit](https:\u002F\u002Fgithub.com\u002Fn8n-io\u002Fself-hosted-ai-starter-kit) by the n8n team\n\n## Troubleshooting\n\nHere are solutions to common issues you might encounter:\n\n### Sites not loading even after following the instructions\n\n- **Symptom:** Your domains\u002Fsites do not open or return errors even though you completed all installation steps.\n- **Likely cause:** Your VPS does not have enough resources for the set of services you selected.\n- **What to try:**\n  1. Check current CPU and RAM usage (e.g., with `top`\u002F`htop`, `free -h`, and `docker stats`). If resources are saturated, upgrade the server or reduce the number of running services.\n  2. Try a minimal configuration — start only `n8n` and verify it comes up. If it works in this minimal setup, enable other services gradually while monitoring the load.\n\n### Temporary \"Dangerous Site\" Warning in Browser\n\n- **Symptom:** Immediately after deploying the services, your browser (e.g., Chrome) might display a \"Dangerous Site\" or similar security warning when you try to access your services. This warning typically disappears after some time (e.g., within a few hours or by the next day).\n- **Cause:** This can happen for a couple of reasons:\n  1.  **Brief use of a self-signed certificate:** When Caddy (the web server managing your SSL certificates) starts up for a new domain, it might briefly use a temporary, self-signed certificate while it's in the process of requesting and obtaining a valid SSL certificate from Let's Encrypt.\n  2.  **Delay in applying the new certificate:** There might also be a short delay before the newly obtained certificate from Let's Encrypt is fully applied and recognized by all systems.\n- **Solution:** This is usually a temporary issue and resolves itself. Give it some time. If the warning persists for more than 24 hours, check your Caddy logs for any errors related to certificate acquisition and ensure your DNS settings are correctly pointing your domain to the server's IP address. You can also try clearing your browser's cache or using an incognito\u002Fprivate window to re-check.\n\n### General Issues\n\n- **VPN Conflicts:** Using a VPN might interfere with downloading Docker images. If you encounter issues pulling images, try temporarily disabling your VPN.\n- **Server Requirements:** If you experience unexpected issues, ensure your server meets the minimum hardware and operating system requirements (including version) as specified in the \"Prerequisites before Installation\" section.\n\n### Update Script Not Working\n\n- **Symptom:** The `make update` command fails, shows errors, or doesn't apply the latest changes.\n- **Cause:** This can happen if your local repository has diverged from the upstream, has uncommitted changes, or is in an inconsistent state.\n- **Solution:** Run the following command to force-sync your local installation with the latest version:\n\n  ```bash\n  git config pull.rebase true && git fetch origin && git checkout main && git reset --hard \"origin\u002Fmain\" && make update\n  ```\n\n  **Warning:** This will discard any local changes you've made to the installer files. If you've customized any scripts or configurations, back them up first.\n\n## Recommended Reading\n\nn8n offers excellent resources for getting started with its AI capabilities:\n\n- [AI agents for developers: from theory to practice with n8n](https:\u002F\u002Fblog.n8n.io\u002Fai-agents\u002F)\n- [Tutorial: Build an AI workflow in n8n](https:\u002F\u002Fdocs.n8n.io\u002Fadvanced-ai\u002Fintro-tutorial\u002F)\n- [Langchain Concepts in n8n](https:\u002F\u002Fdocs.n8n.io\u002Fadvanced-ai\u002Flangchain\u002Flangchain-n8n\u002F) (Langchain is a framework n8n uses for some AI features)\n- [Demonstration of key differences between agents and chains](https:\u002F\u002Fdocs.n8n.io\u002Fadvanced-ai\u002Fexamples\u002Fagent-chain-comparison\u002F)\n- [What are vector databases?](https:\u002F\u002Fdocs.n8n.io\u002Fadvanced-ai\u002Fexamples\u002Funderstand-vector-databases\u002F) (Explains tools like Supabase and Qdrant in more detail)\n\n## More AI Templates\n\nFor more AI workflow ideas, visit the [**official n8n AI template gallery**](https:\u002F\u002Fn8n.io\u002Fworkflows\u002F?categories=AI). From each workflow, select the **Use workflow** button to automatically import it into your n8n instance.\n\n### AI Templates (Examples from n8n.io)\n\n- [AI Agent Chat](https:\u002F\u002Fn8n.io\u002Fworkflows\u002F1954-ai-agent-chat\u002F)\n- [AI chat with any data source (using the n8n workflow tool)](https:\u002F\u002Fn8n.io\u002Fworkflows\u002F2026-ai-chat-with-any-data-source-using-the-n8n-workflow-tool\u002F)\n- [Chat with OpenAI Assistant (by adding a memory)](https:\u002F\u002Fn8n.io\u002Fworkflows\u002F2098-chat-with-openai-assistant-by-adding-a-memory\u002F)\n- [Use an open-source LLM (via HuggingFace)](https:\u002F\u002Fn8n.io\u002Fworkflows\u002F1980-use-an-open-source-llm-via-huggingface\u002F)\n- [Chat with PDF docs using AI (quoting sources)](https:\u002F\u002Fn8n.io\u002Fworkflows\u002F2165-chat-with-pdf-docs-using-ai-quoting-sources\u002F)\n- [AI agent that can scrape webpages](https:\u002F\u002Fn8n.io\u002Fworkflows\u002F2006-ai-agent-that-can-scrape-webpages\u002F)\n- [Tax Code Assistant](https:\u002F\u002Fn8n.io\u002Fworkflows\u002F2341-build-a-tax-code-assistant-with-qdrant-mistralai-and-openai\u002F)\n- [Breakdown Documents into Study Notes with MistralAI and Qdrant](https:\u002F\u002Fn8n.io\u002Fworkflows\u002F2339-breakdown-documents-into-study-notes-using-templating-mistralai-and-qdrant\u002F)\n- [Financial Documents Assistant using Qdrant and MistralAI](https:\u002F\u002Fn8n.io\u002Fworkflows\u002F2335-build-a-financial-documents-assistant-using-qdrant-and-mistralai\u002F)\n- [Recipe Recommendations with Qdrant and Mistral](https:\u002F\u002Fn8n.io\u002Fworkflows\u002F2333-recipe-recommendations-with-qdrant-and-mistral\u002F)\n\n## Tips & Tricks\n\n### Accessing Files on the Server\n\nThe installer creates a `shared` folder (by default, located in the same directory where you ran the installation script). This folder is accessible by the n8n application.\nWhen you build automations in n8n that need to read or write files on your server, use the path `\u002Fdata\u002Fshared` inside your n8n workflows. This path in n8n points to the `shared` folder on your server.\n\n**n8n components that interact with the server's filesystem:**\n\n- [Read\u002FWrite Files from Disk](https:\u002F\u002Fdocs.n8n.io\u002Fintegrations\u002Fbuiltin\u002Fcore-nodes\u002Fn8n-nodes-base.filesreadwrite\u002F)\n- [Local File Trigger](https:\u002F\u002Fdocs.n8n.io\u002Fintegrations\u002Fbuiltin\u002Fcore-nodes\u002Fn8n-nodes-base.localfiletrigger\u002F) (To start workflows when files change)\n- [Execute Command](https:\u002F\u002Fdocs.n8n.io\u002Fintegrations\u002Fbuiltin\u002Fcore-nodes\u002Fn8n-nodes-base.executecommand\u002F) (To run command-line tools)\n\n## Contributors\n\nWant to see who has contributed to this project? Check out the [**GitHub Contributors Page**](https:\u002F\u002Fgithub.com\u002Fkossakovsky\u002Fn8n-install\u002Fgraphs\u002Fcontributors)!\n\n## Telemetry\n\nThis installer collects anonymous usage statistics via [Scarf](https:\u002F\u002Fscarf.sh) to help improve the project. **No personal data is collected.**\n\nData collected:\n- Event type (install\u002Fupdate start\u002Fcomplete)\n- Installer version\n- Selected services\n- OS type (e.g., ubuntu-24.04)\n- Random installation ID (to correlate start\u002Fcomplete events)\n- Country (determined by Scarf from IP, not stored by us)\n\nTo opt out, add to your `.env` file after installation:\n```\nSCARF_ANALYTICS=false\n```\n\n## License\n\nThis project (originally created by the n8n team, with further development by contributors - see \"Important Links\") is licensed under the Apache License 2.0. See the [LICENSE](LICENSE) file for details.\n","# 自托管（Self-Hosted）AI 自动化平台\n\n[![GitHub stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fkossakovsky\u002Fn8n-install?style=social)](https:\u002F\u002Fgithub.com\u002Fkossakovsky\u002Fn8n-install\u002Fstargazers)\n[![License](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-Apache%202.0-blue.svg)](LICENSE)\n[![Docker](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fdocker-ready-blue?logo=docker)](https:\u002F\u002Fwww.docker.com\u002F)\n[![Ubuntu](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FUbuntu-24.04%20LTS-E95420?logo=ubuntu&logoColor=white)](https:\u002F\u002Fubuntu.com\u002F)\n[![n8n](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fn8n-compatible-orange)](https:\u002F\u002Fn8n.io)\n\n**通过一条命令部署 30+ AI 和自动化工具。** 这个开源的 Docker Compose 模板创建了一个完整的自托管（Self-Hosted）环境，包含 n8n（工作流自动化）、Flowise（AI 代理）、Ollama（本地大语言模型 \u002F Local LLMs）、向量数据库（Vector Databases）（Qdrant、Weaviate）、RAG 引擎、Supabase、监控栈（Monitoring Stack）等——所有服务均预配置在 Caddy 反向代理（Reverse Proxy）之后，并支持自动 HTTPS。此外，安装过程中还可选择导入 300+ 社区工作流！\n\n## Table of Contents\n\n- [主要功能](#key-features)\n- [为什么选择此方案？](#why-this-setup)\n- [包含内容](#whats-included)\n- [安装](#installation)\n- [快速开始与使用](#quick-start-and-usage)\n- [升级](#upgrading)\n- [快捷命令](#quick-commands-makefile)\n- [故障排除](#troubleshooting)\n- [许可证](#license)\n\n## 主要功能\n\n- **私有 AI 家庭实验室（Private AI Homelab）** —— 使用 Ollama 本地运行大语言模型（LLMs），将数据保留在自己的服务器上\n- **ChatGPT 替代品** —— Open WebUI 为本地 AI 模型提供熟悉的聊天界面\n- **工作流自动化** —— n8n 拥有 400+ 集成，可扩展的基于队列的架构\n- **AI 代理与 RAG** —— Flowise, Dify, LangChain, 向量数据库（Qdrant, Weaviate）\n- **一键安装** —— 交互式向导，自动生成密钥，零手动配置\n- **自动 HTTPS** —— Caddy 反向代理，配备自动 Let's Encrypt 证书\n- **内置监控** —— 包含 Grafana + Prometheus 栈\n- **生产就绪** —— 可扩展的工作者（Workers），健康检查，正确的服务依赖\n- **免费且开源** —— 无供应商锁定，Apache 2.0 许可证\n\n---\n\n## 为什么选择此方案？\n\n此安装程序帮助您创建自己强大、私有的 AI 工作室。想象一下，您手边有一套工具可以：\n\n- 自动化重复性任务。\n- 构建量身定制的智能助手。\n- 分析信息并获得洞察。\n- 生成创意内容。\n\n此设置提供了一套全面的尖端服务，所有服务均预配置为协同工作。主要优势包括：\n\n- **丰富的工具集：** 获取精选的强大开源工具集合，用于 AI 开发、自动化和监控，全部集中在一个地方。\n- **可扩展的 n8n 性能：** n8n 默认以 `` `queue` `` 模式运行，利用 Redis 进行任务管理，Postgres 进行数据存储。您可以在安装期间动态指定 n8n 工作者（Workers）和任务运行器的数量，从而实现对工作流的稳健并行处理，以应对高负载需求。\n- **完全控制：** 所有内容均由您托管，让您完全掌控数据、操作以及资源分配方式。\n\n## 包含内容\n\n✅ **[Caddy](https:\u002F\u002Fcaddyserver.com\u002F), [Postgres](https:\u002F\u002Fwww.postgresql.org\u002F) 和 [Redis](https:\u002F\u002Fredis.io\u002F)** - Web 代理、数据库和缓存的核心服务，始终包含在内。\n\n安装程序还允许您通过设置过程中的交互式向导选择并部署以下强大的开源工具：\n\n✅ [**Appsmith**](https:\u002F\u002Fwww.appsmith.com\u002F) - 一个开源低代码平台，用于构建内部工具、仪表板和 Admin 面板，配备拖拽式 UI（用户界面）构建器。\n\n✅ [**n8n**](https:\u002F\u002Fn8n.io\u002F) - 一个拥有超过 400 种集成和高级 AI 组件的低代码平台，用于自动化工作流。\n\n✅ [**ComfyUI**](https:\u002F\u002Fgithub.com\u002Fcomfyanonymous\u002FComfyUI) - 一个功能强大、基于节点的 Stable Diffusion 工作流 UI。可视化构建和运行图像生成管道，支持自定义节点和扩展。\n\n✅ [**Crawl4ai**](https:\u002F\u002Fgithub.com\u002Funclecode\u002Fcrawl4ai) - 专为 AI 设计的灵活网络爬虫，使您能够从网站提取数据以用于项目。\n\n✅ [**Docling**](https:\u002F\u002Fgithub.com\u002Fdocling-project\u002Fdocling-serve) - 通用文档转换器，可将 PDF、DOCX、PPTX、XLSX、HTML 和图像转换为干净的 Markdown 或 JSON。具备高级 PDF 解析、OCR（光学字符识别）支持和带有可选 Web UI 的 REST API（接口）。非常适合 n8n 工作流中的文档处理。\n\n✅ [**Dify**](https:\u002F\u002Fdify.ai\u002F) - 一个开源 AI 应用开发平台，提供全面的 LLMOps（大语言模型运维）能力，包括工作流管理、提示词工程、RAG（检索增强生成）管道和 AI Agent（智能体）编排。非常适合构建生产级 AI 应用。\n\n✅ [**Flowise**](https:\u002F\u002Fflowiseai.com\u002F) - 一个无代码\u002F低代码 AI Agent 构建器，与 n8n 完美互补，让您轻松创建复杂的 AI 应用。\n\n✅ [**Gost**](https:\u002F\u002Fgithub.com\u002Fgo-gost\u002Fgost) - 多功能 HTTP\u002FHTTPS 代理，用于将 AI 服务的出站流量路由到中央代理点。\n\n✅ [**Gotenberg**](https:\u002F\u002Fgotenberg.dev\u002F) - 一个无状态 API（接口），用于将 HTML、Markdown、Word、Excel 和其他文档转换为 PDF、PNG 或 JPEG。仅在 Docker（容器平台）网络内可用，供 n8n 工作流和其他服务内部使用。\n\n✅ [**Grafana**](https:\u002F\u002Fgrafana.com\u002F) - 一个开源平台，用于可视化监控数据，帮助您一目了然地了解系统性能。\n\n✅ [**Langfuse**](https:\u002F\u002Flangfuse.com\u002F) - 一个开源平台，帮助您观察和理解 AI Agent 的性能表现，使其更易于调试和改进。\n\n✅ [**Letta**](https:\u002F\u002Fdocs.letta.com\u002F) - 一个开源 Agent 服务器和 SDK（软件开发工具包），可连接到各种 LLM（大语言模型）API 后端（OpenAI、Anthropic、Ollama 等），使您能够构建和管理 AI Agent。\n\n✅ [**LightRAG**](https:\u002F\u002Fgithub.com\u002FHKUDS\u002FLightRAG) - 一个简单快速的基于图的 RAG（检索增强生成）系统，具有自动知识图谱提取、双层检索机制和增量更新功能。支持多种存储后端（PostgreSQL、Neo4j、JSON）和嵌入模型。\n\n✅ [**LibreTranslate**](https:\u002F\u002Fdocs.libretranslate.com\u002F) - 自托管翻译 API（支持 50+ 种语言）。\n\n✅ [**Neo4j**](https:\u002F\u002Fneo4j.com\u002F) - 一个图数据库管理系统，允许您将数据建模、存储和查询为节点和关系组成的网络。\n\n✅ [**NocoDB**](https:\u002F\u002Fnocodb.com\u002F) - 一个开源的 Airtable 替代品，可将任何数据库转变为智能电子表格，并提供无代码界面以构建协作应用。\n\n✅ [**Ollama**](https:\u002F\u002Follama.com\u002F) - 在本地运行 Llama 3、Mistral、Gemma 和其他大语言模型。\n\n✅ [**Open WebUI**](https:\u002F\u002Fopenwebui.com\u002F) - 一个用户友好、类似 ChatGPT 的界面，用于私密地与您的 AI 模型和 n8n Agent 交互。\n\n✅ [**PaddleOCR**](https:\u002F\u002Fwww.paddleocr.ai\u002Flatest\u002Fen\u002Findex.html) - 由 PaddleX Basic Serving 驱动的 CPU 就绪型 OCR API。\n\n✅ [**Portainer**](https:\u002F\u002Fwww.portainer.io\u002F) - 一个轻量级、安全的 Web UI，用于轻松管理您的 Docker 环境（容器、镜像、卷、网络）。\n\n✅ [**Databasus**](https:\u002F\u002Fgithub.com\u002Fdatabasus\u002Fdatabasus) - 带有自托管 UI 的数据库备份和监控。\n\n✅ [**Postiz**](https:\u002F\u002Fpostiz.com\u002F) - 一个开源社交媒体排期和发布平台。\n\n✅ [**Prometheus**](https:\u002F\u002Fprometheus.io\u002F) - 一个开源监控和告警工具包，用于关注系统健康状态。\n\n✅ [**Qdrant**](https:\u002F\u002Fqdrant.tech\u002F) - 一个高性能开源向量存储库，专为 AI 设计。虽然 Supabase 也提供向量功能，但 Qdrant 因其速度而被包含在内，是要求苛刻的 AI 任务的理想选择。\n\n✅ [**RAGApp**](https:\u002F\u002Fgithub.com\u002Fragapp\u002Fragapp) - 开源应用程序，用于基于您的数据构建 RAG（检索增强生成）助手。提供用于聊天的 Web UI 和用于与工作流集成的 HTTP API。\n\n✅ [**RAGFlow**](https:\u002F\u002Fragflow.io\u002F) - 一个基于深度文档理解的开源 RAG 引擎，采用 Elasticsearch 后端，提供基于复杂格式化数据的可靠引用和真实问答能力。\n\n✅ [**SearXNG**](https:\u002F\u002Fsearxng.org\u002F) - 一个免费、开源的互联网元搜索引擎。它聚合来自众多搜索服务的结果，不跟踪或分析您，确保您的隐私。\n\n✅ [**Supabase**](https:\u002F\u002Fsupabase.com\u002F) - 一个开源的 Firebase 替代品，提供数据库存储、用户认证等功能。它是 AI 应用的热门选择。\n\n✅ [**Uptime Kuma**](https:\u002F\u002Fgithub.com\u002Flouislam\u002Fuptime-kuma) - 带有通知功能的自托管正常运行时间监控工具。\n\n✅ [**WAHA**](https:\u002F\u002Fwaha.devlike.pro\u002F) - 可一键配置的 WhatsApp HTTP API（REST API 接口）！3 个引擎：WEBJS（基于浏览器）、NOWEB（websocket nodejs）、GOWS（websocket go）。\n\n✅ [**Weaviate**](https:\u002F\u002Fweaviate.io\u002F) - 一个开源的 AI 原生向量数据库，专注于可扩展性和易用性。可用于 RAG、混合搜索等。\n\n## 包含的社区工作流\n\n利用庞大的预构建自动化库快速上手（设置期间可选择导入）！此集合包含超过 300 个工作流，涵盖广泛的使用场景：\n\n🚦 **包含什么？**\n\n- **AI Agent 和聊天机器人：** RAG、LLM、LangChain、Ollama、OpenAI、Claude、Gemini 等\n- **Gmail 和 Outlook：** 智能标签、自动回复、PDF 处理和邮件转 Notion\n- **HR、电子商务、IT、安全、研究等！**\n- **Notion、Airtable、Google Sheets：** 数据同步、AI 摘要、知识库\n- **PDF、图像、音频、视频：** 提取、摘要、字幕、语音转文字\n- **Slack、Mattermost：** 工单、反馈分析、通知\n- **社交媒体：** LinkedIn、Pinterest、Instagram、Twitter\u002FX、YouTube、TikTok 自动化\n- **Telegram、WhatsApp、Discord：** 机器人、通知、语音和图像工作流\n- **WordPress、WooCommerce：** AI 内容、聊天机器人、自动标签\n\n## 安装\n\n### 安装前的准备工作\n\n1.  **域名：** 您需要一个已注册的域名（例如 `yourdomain.com`）。\n2.  **DNS 配置（域名系统）：** 在运行安装脚本之前，您**必须**为您的域名配置 DNS A 记录，指向您将安装此系统的服务器的公网 IP 地址。将 `yourdomain.com` 替换为您实际的域名：\n    - **泛解析记录：** `A *.yourdomain.com` -> `YOUR_SERVER_IP`\n3.  **VPS（虚拟专用服务器）：** 需要一台带有公网 IP 地址的专用 VPS。不支持家庭服务器、共享主机或本地主机（localhost）设置。\n    - **操作系统：** Ubuntu 24.04 LTS（长期支持版），64 位\n    - 对于包含 **n8n、监控、Databasus 和 Portainer** 的最小化设置：**4 GB 内存 \u002F 2 核 CPU \u002F 40 GB 磁盘空间**\n    - 用于运行 **所有可用服务**：至少需要 **20 GB 内存 \u002F 4 核 CPU \u002F 60 GB 磁盘空间**\n\n### 运行安装\n\n推荐的安装方式是使用提供的主安装脚本。\n\n1.  通过 SSH（安全外壳协议）连接到您的服务器。\n2.  运行以下命令：\n\n    ```bash\n    git clone https:\u002F\u002Fgithub.com\u002Fkossakovsky\u002Fn8n-install && cd n8n-install && sudo bash .\u002Fscripts\u002Finstall.sh\n    ```\n\n此单一命令可自动化整个设置过程，包括：\n\n- 准备您的系统（更新、防火墙配置以及基本的安全增强措施，如暴力破解防护）。\n- 安装 Docker 和 Docker Compose（用于在隔离环境中运行应用程序的工具）。\n- 生成包含必要密钥和您域名设置的配置文件（`.env`）。\n- 启动所有服务。\n\n在安装过程中，脚本将提示您输入：\n\n1.  您的 **主域名**（必需，例如 `yourdomain.com`）。这是您已配置泛解析记录的域名。\n2.  您的 **电子邮件地址**（必需，用于 Flowise、Supabase 仪表板、Grafana 等服务登录，以及用于 Let's Encrypt 的 SSL（安全套接层）证书注册）。\n3.  可选的 **OpenAI API（应用程序接口）密钥**（非必需。如果提供，可用于 Supabase AI 功能和 Crawl4ai。按 Enter 键跳过）。\n4.  您是否要 **导入约 300 个现成的 n8n 社区工作流**（y\u002Fn，可选。根据服务器和网络速度，这可能需要 20-30 分钟）。\n5.  您想要运行的 **n8n Worker 数量**（必需，例如 1, 2, 3, 4。这决定了可以并行处理多少个工作流。每个 Worker 会自动获得其专用的任务运行器侧边车 (sidecar) 以执行 Code 节点。如果未指定，默认为 1）。\n6.  随后将出现 **服务选择向导**，允许您选择要部署的可用服务（如 Flowise、Supabase、Qdrant、Open WebUI 等）。核心服务（Caddy、Postgres、Redis）将为您所选的服务进行设置。\n\n安装成功完成后，脚本将显示一份摘要报告。该报告包含已部署服务的访问 URL（统一资源定位符）和凭据。**请将此信息保存在安全的地方！**\n\n## 快速开始与使用\n\n安装成功后，您的服务即可正常运行！以下是入门指南：\n\n1.  **访问您的服务：**\n    安装脚本提供了一份包含所有访问 URL 和凭据的摘要报告。请参考该报告。主要服务将在以下地址可用（将 `yourdomain.com` 替换为您实际的域名）：\n\n    - **n8n：** `n8n.yourdomain.com`（使用您在安装期间提供的电子邮件地址和摘要报告中的初始密码登录。首次登录时可能会被要求更改此密码。）\n    - **Appsmith：** `appsmith.yourdomain.com`（低代码应用构建器）\n    - **ComfyUI：** `comfyui.yourdomain.com`（基于节点的 Stable Diffusion UI（用户界面））\n    - **Databasus：** `databasus.yourdomain.com`\n    - **Dify：** `dify.yourdomain.com`（具有全面 LLMOps 能力的 AI 应用程序开发平台）\n    - **Docling：** `docling.yourdomain.com`（带有 REST API 的通用文档转换器；Web UI 位于 `\u002Fui`）\n    - **Flowise：** `flowise.yourdomain.com`（使用您在安装期间提供的电子邮件地址和摘要报告中的初始密码登录。）\n    - **Grafana：** `grafana.yourdomain.com`\n    - **Langfuse：** `langfuse.yourdomain.com`\n    - **Letta：** `letta.yourdomain.com`\n    - **LibreTranslate：** `translate.yourdomain.com`\n    - **LightRAG：** `lightrag.yourdomain.com`\n    - **Neo4j：** `neo4j.yourdomain.com`\n    - **NocoDB：** `nocodb.yourdomain.com`\n    - **Open WebUI：** `webui.yourdomain.com`\n    - **PaddleOCR：** `paddleocr.yourdomain.com`\n    - **Portainer：** `portainer.yourdomain.com`（受 Caddy 基本认证保护；首次登录时，完成 Portainer 管理员设置）\n    - **Postiz：** `postiz.yourdomain.com`\n    - **Prometheus：** `prometheus.yourdomain.com`（通常用作 Grafana 的数据源）\n    - **Qdrant：** `qdrant.yourdomain.com`\n    - **RAGApp：** `ragapp.yourdomain.com`\n    - **RAGFlow：** `ragflow.yourdomain.com`\n    - **SearXNG：** `searxng.yourdomain.com`\n    - **Supabase（仪表板）：** `supabase.yourdomain.com`\n    - **Uptime Kuma：** `uptime-kuma.yourdomain.com`（在线监控仪表板）\n    - **WAHA：** `waha.yourdomain.com`（WhatsApp HTTP API；引擎：WEBJS, NOWEB, GOWS）\n    - **Weaviate：** `weaviate.yourdomain.com`\n\n### 可选内部工具：Python Runner\n\n- **它是什么**：一个仅限内部使用的服务，用于在与您的其他服务（n8n、Postgres、Qdrant 等）相同的 Docker 网络内运行您的自定义 Python 代码。不暴露任何外部端口，也不由 Caddy 代理。\n- **如何启用**：在安装\u002F更新期间的“服务选择向导”中选择\"Python Runner\"，或手动添加配置文件：`COMPOSE_PROFILES=...,python-runner`。\n- **代码存放位置**：将您的 Python 文件放置在 `python-runner\u002F` 目录中。默认入口点是 `python-runner\u002Fmain.py`。\n- **依赖项**：将它们添加到 `python-runner\u002Frequirements.txt`；它们将在容器启动时自动安装。\n\n2.  **探索 n8n：**\n\n    - 登录您的 n8n 实例。这是您工作流自动化的中心枢纽。\n    - 如果您在安装期间选择导入社区工作流，您将在“工作流”部分找到超过 300 个示例。这些是学习和获取灵感的好方法。\n    - 开始构建您的第一个工作流！您可以访问超过 400 种集成和强大的 AI 工具。\n\n3.  **利用集成的 AI 工具：**\n\n    - **将 n8n 与向量存储（Vector Stores）连接**：使用 n8n 连接到 Qdrant（如有需要可通过其自有端点访问，通常是 `qdrant.yourdomain.com`）、Supabase 或 Weaviate（`weaviate.yourdomain.com`），以存储和检索信息用于您的 AI 任务，如检索增强生成（RAG）。\n    - **使用 Flowise 构建**：在 `flowise.yourdomain.com` 访问 Flowise 以创建 AI 代理（Agents）和应用。您可以从 n8n 触发 Flowise 代理，反之亦然。\n    - **与 Open WebUI 交互**：在 `webui.yourdomain.com` 使用 Open WebUI 作为您本地 AI 模型或 n8n 代理的聊天界面（例如，如果已配置，可使用 n8n_pipe 集成）。\n    - **配置大语言模型（LLMs）**：如果您希望使用来自 OpenAI、Anthropic 等提供商的大型语言模型（LLMs），或通过 Ollama（如果已安装）本地使用，您可以在 n8n 节点内或在 Flowise 和 Open WebUI 等服务中轻松配置凭证和连接。\n\n4.  **检查监控（可选）：**\n    - 访问 Grafana（`grafana.yourdomain.com`）查看监控系统性能的仪表板（数据源自 Prometheus）。\n\t\n\n## 使用 Cloudflare Tunnel 进行安全访问（可选）\n\nCloudflare Tunnel 提供对您服务的零信任（Zero-trust）访问，而无需在服务器上暴露任何端口。所有流量都通过 Cloudflare 的安全网络路由，提供分布式拒绝服务（DDoS）防护并隐藏服务器的 IP 地址。\n\n### 优势\n- **无暴露端口** - 80\u002F443 端口可以完全关闭\n- **DDoS 防护** - 内置 Cloudflare 保护\n- **IP 隐藏** - 服务器的真实 IP 永远不会暴露\n- **零信任安全** - 可选的 Cloudflare Access 集成\n- **无需公网 IP** - 适用于私有网络\n\n### 设置说明\n\n请参阅 Cloudflare Tunnel 指南：[cloudflare-instructions.md](cloudflare-instructions.md)\n\n\n### 在 n8n 代码节点中使用库 (v2.0+)\n\nn8n v2.0 使用外部任务运行器在代码节点中执行 JavaScript 和 Python 代码。此设置通过 `n8n\u002FDockerfile.runner` 和 `n8n\u002Fn8n-task-runners.json` 预配置了以下库：\n\n**JavaScript 库**：\n- **`cheerio`**：用于解析和操作 HTML\u002FXML（例如网页抓取）。\n- **`axios`**：基于 Promise 的 HTTP 客户端，用于向外部 API 发起请求。\n- **`moment`**：用于解析、验证、操作和显示日期\u002F时间。\n- **`lodash`**：用于常见编程任务（数组、对象、字符串等）的工具库。\n\n### n8n 中预安装的系统工具\n\n自定义 n8n Docker 镜像（`n8n\u002FDockerfile.n8n`）包含以下系统级工具：\n\n- **`ffmpeg`**：强大的多媒体框架，用于转换、录制和流式传输音频和视频。通过 n8n 工作流中的 [Execute Command](https:\u002F\u002Fdocs.n8n.io\u002Fintegrations\u002Fbuiltin\u002Fcore-nodes\u002Fn8n-nodes-base.executecommand\u002F) 节点使用它来执行任务，例如：\n  - 转换视频\u002F音频格式（例如 MP4 转 MP3）\n  - 从视频文件中提取音频\n  - 调整媒体文件大小或压缩\n  - 从视频中生成缩略图\n\n## 升级\n\n要将所有组件（n8n、Open WebUI 等）更新到最新版本并纳入此安装程序项目的最新更改：\n\n```bash\nmake update\n```\n\n**对于 Fork**：如果您维护带有自定义更改的 Fork 并希望合并来自上游的更新而不是重置：\n\n```bash\nmake git-pull\n```\n\n此脚本将：\n\n1.  从 Git 仓库获取安装程序的最新更新。\n2.  暂时停止当前运行的服务。\n3.  下载所有服务的 Docker 镜像最新版本。\n4.  询问您是否要重新运行 n8n 工作流导入（如果您在初始安装时跳过了此步骤或想刷新社区工作流，这很有用）。\n5.  使用新更新重启所有服务。\n\n## 清理 Docker\n\n如果您需要释放磁盘空间，可以运行 Docker 清理命令。这将移除所有未使用的 Docker 容器、镜像和卷。\n\n```bash\nmake clean\n```\n\n这对于移除旧镜像和释放空间很有用，但请注意它将移除所有未使用的数据。\n\n## 快速命令 (Makefile)\n\n该项目包含一个用于简化命令执行的 Makefile：\n\n### 安装与更新\n\n| 命令               | 描述                                          |\n| --------------------- | ---------------------------------------------------- |\n| `make install`        | 完整安装                                    |\n| `make update`         | 更新系统和服 务（重置为原始版本）        |\n| `make update-preview` | 预览可用更新而不应用（试运行） |\n| `make git-pull`       | 针对 Fork 的更新（从 upstream\u002Fmain 合并）         |\n| `make clean`          | 移除未使用的 Docker 资源                       |\n\n### 监控与日志\n\n| 命令                 | 描述                                              |\n| ----------------------- | -------------------------------------------------------- |\n| `make logs`             | 查看日志（所有服务）                                 |\n| `make logs s=\u003Cservice>` | 查看特定服务的日志（例如 `make logs s=n8n`） |\n| `make status`           | 显示容器状态                                    |\n| `make monitor`          | 实时 CPU\u002F内存监控                               |\n| `make restart`          | 重启所有服务                                     |\n| `make stop`             | 停止所有服务                                        |\n| `make start`            | 启动所有服务                                       |\n| `make show-restarts`    | 显示每个容器的重启次数                         |\n| `make import`           | 从备份导入 n8n 工作流                         |\n| `make import n=10`      | 仅导入前 N 个工作流                            |\n\n### 诊断与配置\n\n| 命令          | 描述                                                        |\n| ---------------- | ------------------------------------------------------------------ |\n| `make doctor`    | 运行系统诊断（检查 DNS（域名系统）、SSL（安全套接层）、容器、磁盘、内存） |\n| `make setup-tls` | 为企业\u002F内部使用配置自定义 TLS（传输层安全）证书       |\n\n运行 `make help` 以获取所有可用命令的完整列表。\n\n## 社区移植版本\n\n- [n8n-installer-arch](https:\u002F\u002Fgithub.com\u002Fndrewpj\u002Fn8n-installer-arch) 由 [@ndrewpj](https:\u002F\u002Fgithub.com\u002Fndrewpj) 提供 - 适用于基于 Arch 的 Linux 发行版（Arch Linux, CachyOS, Manjaro）\n\n## 重要链接\n\n- 基于 [coleam00](https:\u002F\u002Fgithub.com\u002Fcoleam00\u002Flocal-ai-packaged) 的项目\n- n8n 团队提供的 [原始入门套件](https:\u002F\u002Fgithub.com\u002Fn8n-io\u002Fself-hosted-ai-starter-kit)\n\n## 故障排除\n\n以下是您可能遇到的一些常见问题的解决方案：\n\n### 即使遵循说明后网站仍无法加载\n\n- **症状：** 尽管您已完成所有安装步骤，但您的域名\u002F网站仍无法打开或返回错误。\n- **可能原因：** 您的 VPS（虚拟专用服务器）资源不足以支持您选择的服务集。\n- **尝试方法：**\n  1. 检查当前的 CPU 和 RAM 使用情况（例如使用 `top`\u002F`htop`, `free -h`, 和 `docker stats`）。如果资源已饱和，请升级服务器或减少运行的服务数量。\n  2. 尝试最小化配置 —— 仅启动 `n8n` 并验证其是否正常运行。如果在此最小设置下工作正常，请在监控负载的同时逐步启用其他服务。\n\n### 浏览器中临时的“危险网站”警告\n\n- **症状：** 部署服务后立即，当您尝试访问服务时，浏览器（如 Chrome）可能会显示“危险网站”或类似的安全警告。此警告通常在一段时间后消失（例如几小时内或第二天）。\n- **原因：** 这可能由以下几个原因导致：\n  1. **短暂使用自签名证书：** 当 Caddy（管理您 SSL 证书的 Web 服务器）为新域名启动时，在向 Let's Encrypt（证书颁发机构）请求并获得有效 SSL 证书的过程中，它可能会短暂使用临时的自签名证书。\n  2. **应用新证书的延迟：** 从 Let's Encrypt 获得的新证书完全应用并被所有系统识别之前，可能会有短暂的延迟。\n- **解决方案：** 这通常是一个临时问题，会自动解决。请耐心等待。如果警告持续超过 24 小时，请检查您的 Caddy 日志是否有与证书获取相关的错误，并确保您的 DNS（域名系统）设置正确地将域名指向服务器的 IP 地址。您也可以尝试清除浏览器缓存或使用无痕\u002F隐私窗口重新检查。\n\n### 一般问题\n\n- **VPN 冲突：** 使用 VPN 可能会干扰 Docker（容器引擎）镜像的下载。如果您在拉取镜像时遇到问题，请尝试暂时禁用 VPN。\n- **服务器要求：** 如果您遇到意外问题，请确保您的服务器满足“安装前先决条件”部分中指定的最低硬件和操作系统要求（包括版本）。\n\n### 更新脚本无法工作\n\n- **症状：** `make update` 命令失败、显示错误或未应用最新更改。\n- **原因：** 如果您的本地仓库与上游分支出现分歧、存在未提交的更改或处于不一致状态，可能会发生这种情况。\n- **解决方案：** 运行以下命令强制将本地安装与最新版本同步：\n\n  ```bash\n  git config pull.rebase true && git fetch origin && git checkout main && git reset --hard \"origin\u002Fmain\" && make update\n  ```\n\n  **警告：** 这将丢弃您对安装程序文件所做的任何本地更改。如果您已自定义任何脚本或配置，请先备份它们。\n\n## 推荐阅读\n\nn8n 提供了出色的资源以帮助初学者掌握其 AI 功能：\n\n- [面向开发者的 AI 代理：从理论到实践与 n8n](https:\u002F\u002Fblog.n8n.io\u002Fai-agents\u002F)\n- [教程：在 n8n 中构建 AI 工作流](https:\u002F\u002Fdocs.n8n.io\u002Fadvanced-ai\u002Fintro-tutorial\u002F)\n- [n8n 中的 Langchain 概念](https:\u002F\u002Fdocs.n8n.io\u002Fadvanced-ai\u002Flangchain\u002Flangchain-n8n\u002F)（Langchain 是 n8n 用于某些 AI 功能的框架）\n- [代理与工作链关键差异演示](https:\u002F\u002Fdocs.n8n.io\u002Fadvanced-ai\u002Fexamples\u002Fagent-chain-comparison\u002F)\n- [什么是向量数据库（Vector Databases）？](https:\u002F\u002Fdocs.n8n.io\u002Fadvanced-ai\u002Fexamples\u002Funderstand-vector-databases\u002F)（更详细地解释了 Supabase 和 Qdrant 等工具）\n\n## 更多 AI 模板\n\n如需更多 AI 工作流创意，请访问 [**官方 n8n AI 模板画廊**](https:\u002F\u002Fn8n.io\u002Fworkflows\u002F?categories=AI)。在每个工作流中，选择 **Use workflow** 按钮即可自动将其导入到您的 n8n 实例中。\n\n### AI 模板（来自 n8n.io 的示例）\n\n- [AI 代理聊天](https:\u002F\u002Fn8n.io\u002Fworkflows\u002F1954-ai-agent-chat\u002F)\n- [使用任意数据源进行 AI 聊天（使用 n8n 工作流工具）](https:\u002F\u002Fn8n.io\u002Fworkflows\u002F2026-ai-chat-with-any-data-source-using-the-n8n-workflow-tool\u002F)\n- [与 OpenAI Assistant 聊天（通过添加记忆功能）](https:\u002F\u002Fn8n.io\u002Fworkflows\u002F2098-chat-with-openai-assistant-by-adding-a-memory\u002F)\n- [使用开源 LLM（大语言模型）（通过 HuggingFace）](https:\u002F\u002Fn8n.io\u002Fworkflows\u002F1980-use-an-open-source-llm-via-huggingface\u002F)\n- [使用 AI 与 PDF 文档聊天（引用来源）](https:\u002F\u002Fn8n.io\u002Fworkflows\u002F2165-chat-with-pdf-docs-using-ai-quoting-sources\u002F)\n- [可抓取网页的 AI 代理](https:\u002F\u002Fn8n.io\u002Fworkflows\u002F2006-ai-agent-that-can-scrape-webpages\u002F)\n- [税法代码助手](https:\u002F\u002Fn8n.io\u002Fworkflows\u002F2341-build-a-tax-code-assistant-with-qdrant-mistralai-and-openai\u002F)\n- [使用 MistralAI 和 Qdrant 将文档分解为学习笔记](https:\u002F\u002Fn8n.io\u002Fworkflows\u002F2339-breakdown-documents-into-study-notes-using-templating-mistralai-and-qdrant\u002F)\n- [使用 Qdrant 和 MistralAI 的财务文档助手](https:\u002F\u002Fn8n.io\u002Fworkflows\u002F2335-build-a-financial-documents-assistant-using-qdrant-and-mistralai\u002F)\n- [使用 Qdrant 和 Mistral 的食谱推荐](https:\u002F\u002Fn8n.io\u002Fworkflows\u002F2333-recipe-recommendations-with-qdrant-and-mistral\u002F)\n\n## 技巧与窍门\n\n### 访问服务器上的文件\n\n安装程序 (installer) 会创建一个 `shared` 文件夹（默认位于您运行安装脚本的同一目录中）。此文件夹可供 n8n 应用程序访问。\n当您在 n8n 中构建需要读取或写入服务器上文件的自动化流程时，请在您的 n8n 工作流 (workflows) 中使用路径 `\u002Fdata\u002Fshared`。n8n 中的此路径指向服务器上的 `shared` 文件夹。\n\n**与服务器文件系统 (filesystem) 交互的 n8n 组件：**\n\n- [从磁盘读\u002F写文件](https:\u002F\u002Fdocs.n8n.io\u002Fintegrations\u002Fbuiltin\u002Fcore-nodes\u002Fn8n-nodes-base.filesreadwrite\u002F)\n- [本地文件触发器](https:\u002F\u002Fdocs.n8n.io\u002Fintegrations\u002Fbuiltin\u002Fcore-nodes\u002Fn8n-nodes-base.localfiletrigger\u002F)（在文件更改时启动工作流）\n- [执行命令](https:\u002F\u002Fdocs.n8n.io\u002Fintegrations\u002Fbuiltin\u002Fcore-nodes\u002Fn8n-nodes-base.executecommand\u002F)（运行命令行工具）\n\n## 贡献者\n\n想看看谁为这个项目做出了贡献？查看 [**GitHub 贡献者页面**](https:\u002F\u002Fgithub.com\u002Fkossakovsky\u002Fn8n-install\u002Fgraphs\u002Fcontributors)！\n\n## 遥测 (Telemetry)\n\n此安装程序通过 [Scarf](https:\u002F\u002Fscarf.sh) 收集匿名使用统计数据，以帮助改进项目。**不收集任何个人数据。**\n\n收集的数据：\n- 事件类型（安装\u002F更新开始\u002F完成）\n- 安装程序版本\n- 选定的服务\n- 操作系统类型（例如：ubuntu-24.04）\n- 随机安装 ID（用于关联开始\u002F完成事件）\n- 国家（由 Scarf 根据 IP 确定，我们不会存储）\n\n要退出，请在安装后将以下内容添加到您的 `.env` 文件中：\n```\nSCARF_ANALYTICS=false\n```\n\n## 许可证 (License)\n\n本项目（最初由 n8n 团队创建，后续由贡献者开发 - 参见“重要链接”）根据 Apache License 2.0（Apache 许可证 2.0）许可。详见 [LICENSE](LICENSE) 文件。","# n8n-install 快速上手指南\n\n**n8n-install** 是一个自托管的 AI 自动化平台部署工具。它通过一条命令即可在服务器上一键部署包含 n8n、Flowise、Ollama、向量数据库等在内的 30+ 种 AI 与自动化工具，并自动配置 Caddy 反向代理与 HTTPS。\n\n## 环境准备\n\n在开始安装之前，请确保您的服务器满足以下要求：\n\n### 1. 操作系统\n- **推荐系统**: Ubuntu 24.04 LTS (64-bit)\n- **不支持**: 家庭服务器、共享主机或 localhost 环境。\n\n### 2. 网络与域名\n- **公网 IP**: 必须拥有具有公网 IP 的 VPS。\n- **域名配置**: 需拥有一个已注册的域名，并在 DNS 服务商处配置 **泛解析记录 (Wildcard A Record)**：\n  - 记录类型：`A`\n  - 主机记录：`*`\n  - 记录值：`YOUR_SERVER_IP` (替换为您的服务器公网 IP)\n  - 示例：`*.yourdomain.com` -> `1.2.3.4`\n\n### 3. 硬件资源\n根据您计划部署的服务规模，建议配置如下：\n- **最小配置** (仅核心服务 n8n, Monitoring, Databasus, Portainer):\n  - 内存：4 GB\n  - CPU: 2 核\n  - 磁盘：40 GB\n- **全量配置** (运行所有可用服务):\n  - 内存：至少 20 GB\n  - CPU: 4 核\n  - 磁盘：60 GB\n\n> **注意**: 由于涉及从 GitHub 和 Docker Hub 拉取镜像，请确保服务器网络连接稳定。如遇国内网络访问问题，可考虑配置网络加速。\n\n## 安装步骤\n\n1. **SSH 连接服务器**\n   使用终端工具登录到您的 Ubuntu 服务器。\n\n2. **执行安装脚本**\n   复制并运行以下命令。该脚本会自动更新系统、安装 Docker、生成配置文件并启动所有服务。\n\n   ```bash\n   git clone https:\u002F\u002Fgithub.com\u002Fkossakovsky\u002Fn8n-install && cd n8n-install && sudo bash .\u002Fscripts\u002Finstall.sh\n   ```\n\n3. **跟随交互式向导**\n   脚本运行过程中会提示您输入以下信息：\n   - **Primary Domain Name**: 您配置的域名（例如 `yourdomain.com`）。\n   - **Email Address**: 用于服务登录及 SSL 证书注册（如 Let's Encrypt）。\n   - **其他配置**: 根据提示确认密码或特定服务选项。\n\n   等待脚本完成所有服务的部署与初始化。\n\n## 基本使用\n\n安装完成后，您可以通过浏览器访问以下服务：\n\n### 1. 访问工作流自动化平台 (n8n)\n- **地址**: `https:\u002F\u002Fyourdomain.com`\n- **用途**: 创建和管理自动化工作流，集成 400+ 种应用。\n- **初始设置**: 首次访问可能需要创建管理员账户。\n\n### 2. 访问本地 AI 聊天界面 (Open WebUI)\n- **地址**: `https:\u002F\u002Fyourdomain.com\u002Fopen-webui` (具体路径视配置而定，通常可通过主菜单跳转)\n- **用途**: 提供类似 ChatGPT 的界面，用于与本地运行的 Ollama 模型进行对话。\n\n### 3. 导入社区工作流\n- 在安装过程中或后续设置里，您可以选择导入 **300+ 社区预置工作流**。\n- 涵盖场景包括：AI 智能体、邮件处理、Notion\u002FAirtable 数据同步、社交媒体自动化等。\n\n### 4. 监控与管理\n- **Portainer**: 管理 Docker 容器与环境。\n- **Grafana\u002FPrometheus**: 查看系统性能监控数据。\n- **Uptime Kuma**: 监控服务在线状态。\n\n---\n*更多高级配置与自定义选项请参考官方完整文档。*","某初创公司的技术负责人计划搭建一套私有化智能客服系统，利用本地大模型分析客户工单并自动归档，同时确保敏感数据完全不出内网，避免云厂商泄露风险。\n\n### 没有 n8n-install 时\n- 需手动编写 Docker Compose 文件，逐个配置 n8n、Ollama、Postgres 等组件，环境搭建耗时数天。\n- 每个服务需单独申请和配置 SSL 证书，HTTPS 设置繁琐，容易因配置错误导致服务不可用。\n- 各容器间网络隔离复杂，调试 n8n 调用本地模型时的连接问题耗费大量精力。\n- 缺乏统一的监控方案，系统运行状态全靠人工检查，故障发现滞后影响业务连续性。\n\n### 使用 n8n-install 后\n- 通过一条命令启动交互式向导，一键部署全套 AI 自动化栈，环境准备时间从几天缩短至几分钟。\n- Caddy 反向代理自动签发 Let's Encrypt 证书，所有服务统一域名访问，安全配置实现零门槛。\n- 预配置好服务依赖与内部网络，n8n 可直接无缝调用本地 Ollama 模型，无需手动调试连通性。\n- 内置 Grafana + Prometheus 监控栈，实时可视化工作流执行效率与资源占用，运维更加省心。\n\nn8n-install 让私有化 AI 自动化部署变得像搭积木一样简单，不仅解决了多组件集成的技术难题，更彻底释放了团队在基础设施上的维护成本。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fkossakovsky_n8n-install_b0eb7b37.png","kossakovsky","Yury Kossakovsky","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fkossakovsky_9d6ecc57.jpg",null,"Calgary","ikossakovski","https:\u002F\u002Fgithub.com\u002Fkossakovsky",[84,88,92,96,100],{"name":85,"color":86,"percentage":87},"Shell","#89e051",68.5,{"name":89,"color":90,"percentage":91},"JavaScript","#f1e05a",16.5,{"name":93,"color":94,"percentage":95},"Python","#3572A5",8.5,{"name":97,"color":98,"percentage":99},"HTML","#e34c26",5.2,{"name":101,"color":102,"percentage":103},"Makefile","#427819",1.2,791,213,"2026-04-04T18:05:22","Apache-2.0","Ubuntu 24.04 LTS","未说明","最低 4GB \u002F 全服务推荐 20GB",{"notes":112,"python":109,"dependencies":113},"仅限 VPS 环境（不支持家庭服务器\u002F本地主机），需公网 IP；必须配置域名及泛解析 DNS 记录（A *.yourdomain.com）；基于 Docker Compose 自动化部署，包含 30+ 开源工具（如 Ollama, n8n, Supabase）；自动配置 HTTPS 及监控栈；最小配置需 4GB 内存，运行所有服务需 20GB 内存。",[114,115],"Docker","Docker Compose",[13,15,53,26,51,14],[118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137],"automation","docker","flowise","homelab","make-alternative","n8n","no-code","ollama","qdrant","rag","self-hosted","vector-database","zapier-alternative","ai-agents","open-webui","ai","chatgpt-alternative","dify","llm","local-llm","2026-03-27T02:49:30.150509","2026-04-06T07:13:17.373907",[141,146,151,155,160,164],{"id":142,"question_zh":143,"answer_zh":144,"source_url":145},972,"在 Ubuntu 24.04 或 25.04 上安装时遇到 supabase-analytics 容器健康检查失败怎么办？","运行更新脚本进行修复：`sudo bash .\u002Fscripts\u002Fupdate.sh`。该问题已在维护者修复后解决，执行更新命令后重新安装即可正常工作。","https:\u002F\u002Fgithub.com\u002Fkossakovsky\u002Fn8n-install\u002Fissues\u002F11",{"id":147,"question_zh":148,"answer_zh":149,"source_url":150},973,"配置 Cloudflare Tunnel 后无法访问服务地址（连接被拒绝）？","这通常是因为 Cloudflare 的 'Always Use HTTPS' 设置未开启。请在 Cloudflare Dashboard 的 SSL\u002FTLS → Edge Certificates 中启用 'Always Use HTTPS' 选项。","https:\u002F\u002Fgithub.com\u002Fkossakovsky\u002Fn8n-install\u002Fissues\u002F26",{"id":152,"question_zh":153,"answer_zh":154,"source_url":150},974,"Cloudflare 的 SSL\u002FTLS 模式和 DNS 记录应如何正确配置以确保服务可达？","1. SSL\u002FTLS 模式需设置为 'Full' 或 'Full (strict)'，不能是 'Off' 或 'Flexible'；2. 确保 DNS 记录处于‘代理’状态（显示为橙色云朵），而不是仅 DNS 解析（灰色云朵）。",{"id":156,"question_zh":157,"answer_zh":158,"source_url":159},975,"项目默认支持哪些语言的 OCR 文本识别？","默认支持简体中文、繁体中文、英语、日语和拼音。如需使用其他语言（如俄语），需自行配置 OCR 管道和语言模型。","https:\u002F\u002Fgithub.com\u002Fkossakovsky\u002Fn8n-install\u002Fissues\u002F4",{"id":161,"question_zh":162,"answer_zh":163,"source_url":159},976,"如何自定义配置 OCR 模型或修改支持的语言列表？","编辑 `paddlex\u002Focr_config.yml` 配置文件。可根据需求调整检测器、识别模型及布局结构，详细配置参数请参考 PaddleOCR 官方文档。",{"id":165,"question_zh":166,"answer_zh":167,"source_url":168},977,"通过 HTTP 节点加载大文件（如 40MB+）时出现超时或任务被拒绝错误？","尝试在环境变量中设置 `N8N_DEFAULT_BINARY_DATA_MODE=filesystem` 和 `N8N_BINARY_DATA_TTL=86400`。若仍无效，可能是主机网络限制，建议更换服务器环境测试。","https:\u002F\u002Fgithub.com\u002Fkossakovsky\u002Fn8n-install\u002Fissues\u002F7",[170,175,180,185,190,195,200,205,210,215,220,225,230,235,240,245,250,255],{"id":171,"version":172,"summary_zh":173,"released_at":174},100611,"v1.4.2","### Fixed\n- **n8n** - Make `N8N_PAYLOAD_SIZE_MAX` configurable via `.env` (was hardcoded to 256, ignoring user overrides)\n- **Uptime Kuma** - Fix healthcheck failure (`wget: not found`) by switching to Node.js-based check","2026-03-28T23:55:37",{"id":176,"version":177,"summary_zh":178,"released_at":179},100612,"v1.4.1","## Fixed\n- **Supabase Storage** - Fix crash-loop (`Region is missing`) by adding missing S3 storage configuration variables (`REGION`, `GLOBAL_S3_BUCKET`, `STORAGE_TENANT_ID`) from upstream Supabase\n- **Supabase** - Sync new environment variables to existing `supabase\u002Fdocker\u002F.env` during updates (previously only populated on first install)","2026-03-23T22:24:32",{"id":181,"version":182,"summary_zh":183,"released_at":184},100613,"v1.4.0","## Added\n- **Uptime Kuma** — Self-hosted uptime monitoring with 90+ notification services\n- **pgvector** — Switch PostgreSQL image to `pgvector\u002Fpgvector` for vector similarity search support\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fkossakovsky\u002Fn8n-install\u002Fcompare\u002Fv1.3.3...v1.4.0","2026-03-16T02:23:39",{"id":186,"version":187,"summary_zh":188,"released_at":189},100614,"v1.3.3","### Fixed\n- **Postiz** - Generate `postiz.env` file to prevent `dotenv-cli` crash in backend container (#40). Handles edge case where Docker creates the file as a directory, and quotes values to prevent misparses.","2026-02-28T04:11:15",{"id":191,"version":192,"summary_zh":193,"released_at":194},100615,"v1.3.2","### Fixed\n- **Docker Compose** - Respect `docker-compose.override.yml` for user customizations (#44). All compose file assembly points now include the override file when present.","2026-02-28T02:15:21",{"id":196,"version":197,"summary_zh":198,"released_at":199},100616,"v1.3.1","### Fixed\n- **Installer** - Skip n8n workflow import and worker configuration prompts when n8n profile is not selected","2026-02-28T02:15:20",{"id":201,"version":202,"summary_zh":203,"released_at":204},100617,"v1.3.0","## Added\n- **Appsmith** - Low-code platform for building internal tools, dashboards, and admin panels","2026-02-28T01:51:23",{"id":206,"version":207,"summary_zh":208,"released_at":209},100618,"v1.2.8","### Fixed\n- **Ragflow** - Fix nginx config mount path (`sites-available\u002Fdefault` → `conf.d\u002Fdefault.conf`) and backend port (`SVR_HTTP_PORT: 80` → `9380`) to resolve default \"Welcome to nginx!\" page and 502 Bad Gateway on API requests (#41)","2026-02-28T01:20:20",{"id":211,"version":212,"summary_zh":213,"released_at":214},100619,"v1.2.7","### Fixed\n- **Docker** - Limit parallel image pulls (`COMPOSE_PARALLEL_LIMIT=3`) to prevent `TLS handshake timeout` errors when many services are selected","2026-02-27T23:57:04",{"id":216,"version":217,"summary_zh":218,"released_at":219},100620,"v1.2.6","### Changed\n- **ComfyUI** - Update Docker image to CUDA 12.8 (`cu128-slim`)","2026-02-11T00:10:14",{"id":221,"version":222,"summary_zh":223,"released_at":224},100621,"v1.2.5","### Fixed\n- **n8n** - Use static ffmpeg binaries for Alpine\u002Fmusl compatibility (fixes glibc errors)","2026-02-04T03:16:04",{"id":226,"version":227,"summary_zh":228,"released_at":229},100622,"v1.2.4","### Fixed\n- **Postiz** - Fix `BACKEND_INTERNAL_URL` to use `localhost` instead of Docker hostname (internal nginx requires localhost)\n\nThis fixes connection refused errors (502 Bad Gateway) when accessing Postiz registration\u002Flogin pages.","2026-01-30T21:11:14",{"id":231,"version":232,"summary_zh":233,"released_at":234},100623,"v1.2.3","### Fixed\n- **Gost proxy** - Add Telegram domains to `GOST_NO_PROXY` bypass list for n8n Telegram triggers","2026-01-29T23:28:26",{"id":236,"version":237,"summary_zh":238,"released_at":239},100624,"v1.2.2","### Fixed\n- **Custom TLS** - Fix certificate file permissions for Docker. Files are now set to 644 so Caddy container can read them regardless of host UID.\n- **Custom TLS** - Fix duplicate hostname error when using custom certificates. Changed architecture from generating separate site blocks to using a shared TLS snippet that all services import.","2026-01-27T00:52:44",{"id":241,"version":242,"summary_zh":243,"released_at":244},100625,"v1.2.1","## Fixed\n\n- **Postiz** - Added Temporal server and UI for workflow orchestration, which was required for Postiz to function properly\n\n### Changes\n\n- Added Temporal server with Elasticsearch for advanced visibility\n- Added Temporal Web UI for workflow monitoring\n- Fixed Temporal healthcheck and integration issues\n- Fixed Caddy redirect loop for welcome page\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fkossakovsky\u002Fn8n-install\u002Fcompare\u002Fv1.2.0...v1.2.1","2026-01-18T03:11:11",{"id":246,"version":247,"summary_zh":248,"released_at":249},100626,"v1.2.0","### Added\n- Changelog section on Welcome Page dashboard","2026-01-12T17:10:25",{"id":251,"version":252,"summary_zh":253,"released_at":254},100627,"v1.1.0","## Added\n\n- **Custom TLS certificates** - Support for corporate\u002Finternal certificates via `caddy-addon\u002F` mechanism\n- New `make stop` and `make start` commands for stopping\u002Fstarting all services without restart\n- New `make setup-tls` command and `scripts\u002Fsetup_custom_tls.sh` helper script for easy certificate configuration\n- New `make git-pull` command for fork workflows - merges from upstream instead of hard reset","2026-01-11T20:20:31",{"id":256,"version":257,"summary_zh":258,"released_at":259},100628,"v1.0.0","First official stable release of n8n-install.\n\n## What's Included\n\n- 30+ self-hosted AI and automation services\n- Interactive installation wizard\n- Automatic HTTPS via Caddy reverse proxy\n- Queue-based n8n with scalable workers\n- Comprehensive monitoring stack (Prometheus, Grafana)\n- Vector databases (Qdrant, Weaviate)\n- AI platforms (Flowise, Dify, Ollama, Open WebUI)\n- And much more\n\nSee [README](https:\u002F\u002Fgithub.com\u002Fkossakovsky\u002Fn8n-install#readme) for full details.","2026-01-07T22:54:58"]