快速安装脚本需要预先装好 Docker；手动部署需先创建 n8n_data 卷并映射 /home/node/.n8n 以持久化数据；编辑器默认监听 5678 端口。
n8n
n8n-io活跃维护可视化搭建工作流并支持自定义代码的自动化平台，内置 AI 能力，提供 400+ 集成，可自托管或上云，用来把各类 API 和数据流串起来。
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
curl -fsSL https://get.n8n.io | sh 硬件要求按 README 说明
README 未说明显存或 GPU 要求；官方快速开始依赖 Docker，自托管部署在本地或服务器上运行。
有 Docker 镜像
可视化画布加自定义代码的 fair-code 工作流自动化平台，原生支持 AI Agent
可视化搭建工作流并支持自定义代码的自动化平台，内置 AI 能力，提供 400+ 集成，可自托管或上云，用来把各类 API 和数据流串起来。
核心能力
- 在可视化画布上编排多步 AI 工作流与 Agent
- 可接入 OpenAI、Anthropic、Google 或开源模型并随时切换
- 需要时用 JavaScript、Python 和 npm 包写自定义逻辑
- 内置 1500+ 集成与 9000+ 工作流模板
- 支持自托管，并提供基于角色的访问与审计日志
容易踩的坑
内容由模型根据 README 生成，可能不完整或不准确，以官方文档为准。看原文 README
查看更新说明
3.2.0 (2026-11-10)
Bug Fixes
- ai-builder: Return the raw body when fetch-url reads JSON, XML, CSV or YAML (#42949) (6640010)
- Align workflow history header dividers (#43167) (73698d6)
- Community package supportedNodesApiVersion v3 compatibility (246e5fd)
- Compression Node: Preserve custom gzip file names (#42063) (a196d7d)
- core: Apply the redaction policy to log streaming, telemetry and error reports (#42905) (c4c66d3)
- core: Decode webhook bodies in the declared charset (#42037) (71ea718)
- core: Exclude Nano Banana models from Gemini chat model pickers (#43082) (5038878)
- core: Expand default blocked IP ranges for outbound request guard (#38912) (40f71ab)
- core: Guard misconfigured s3 binary data mode at boot and normalize removed-mode detection (#37337) (561d084)
- core: Keep Anthropic thinking valid in agents after prompt rewrites and web search (#43160) (92b6fea)
- core: Keep observational memory running after a user stops a HITL card (#43192) (cf28f65)
- core: Keep retry backoff when a trigger fails right after reactivation (#43105) (b43750c)
- core: Keep the OAuth JWKS available when a retired signing key cannot be read (#42465) (7a15776)
- core: Keep the warning level of sub-workflow errors rebuilt for the parent (#42727) (4dcbe9e)
- core: Only allow users who can edit a workflow to own its migration findings (#43091) (1faa2fa)
- core: Retire stale scheduled tasks in repeated batches in each reaper pass (#43076) (505c0c0)
- core: Settle abandoned tool calls when an Agents runtime turn starts (#43194) (75b8ea0)
- core: Subscribe Telegram agent channels to button clicks (#43221) ([4cff3b3](https://github.com/n8n-io/n8n/commit/4cff3b3
- stable2026-11-10 · 2026-11-10 08:52 UTC
- betapre-release2026-11-10 · 2026-11-10 08:44 UTC
查看更新说明
2.48.0 (2026-11-10)
Bug Fixes
- ai-builder: Return the raw body when fetch-url reads JSON, XML, CSV or YAML (#42949) (6640010)
- Align workflow history header dividers (#43167) (73698d6)
- Compression Node: Preserve custom gzip file names (#42063) (a196d7d)
- core: Apply the redaction policy to log streaming, telemetry and error reports (#42905) (c4c66d3)
- core: Decode webhook bodies in the declared charset (#42037) (71ea718)
- core: Exclude Nano Banana models from Gemini chat model pickers (#43082) (5038878)
- core: Keep Anthropic thinking valid in agents after prompt rewrites and web search (#43160) (92b6fea)
- core: Keep observational memory running after a user stops a HITL card (#43192) (cf28f65)
- core: Keep retry backoff when a trigger fails right after reactivation (#43105) (b43750c)
- core: Keep the OAuth JWKS available when a retired signing key cannot be read (#42465) (7a15776)
- core: Keep the warning level of sub-workflow errors rebuilt for the parent (#42727) (4dcbe9e)
- core: Only allow users who can edit a workflow to own its migration findings (#43091) (1faa2fa)
- core: Retire stale scheduled tasks in repeated batches in each reaper pass (#43076) (505c0c0)
- core: Settle abandoned tool calls when an Agents runtime turn starts (#43194) (75b8ea0)
- core: Subscribe Telegram agent channels to button clicks (#43221) (4cff3b3)
- editor: Keep the API settings empty state in the header column (#43219) (c3ba6a3)
- editor: Polish skill files and version history (#43180) (4b7b145)
- editor: Update favicon and preview image branding (#43214) ([c2ea734](https://github.com/n8n-io/n8n/commit/c2ea734ba0f1cb116738c9962747516
查看更新说明
2.48.0 (2026-11-10)
Bug Fixes
- ai-builder: Return the raw body when fetch-url reads JSON, XML, CSV or YAML (#42949) (6640010)
- Align workflow history header dividers (#43167) (73698d6)
- Compression Node: Preserve custom gzip file names (#42063) (a196d7d)
- core: Apply the redaction policy to log streaming, telemetry and error reports (#42905) (c4c66d3)
- core: Decode webhook bodies in the declared charset (#42037) (71ea718)
- core: Exclude Nano Banana models from Gemini chat model pickers (#43082) (5038878)
- core: Keep Anthropic thinking valid in agents after prompt rewrites and web search (#43160) (92b6fea)
- core: Keep observational memory running after a user stops a HITL card (#43192) (cf28f65)
- core: Keep retry backoff when a trigger fails right after reactivation (#43105) (b43750c)
- core: Keep the OAuth JWKS available when a retired signing key cannot be read (#42465) (7a15776)
- core: Keep the warning level of sub-workflow errors rebuilt for the parent (#42727) (4dcbe9e)
- core: Only allow users who can edit a workflow to own its migration findings (#43091) (1faa2fa)
- core: Retire stale scheduled tasks in repeated batches in each reaper pass (#43076) (505c0c0)
- core: Settle abandoned tool calls when an Agents runtime turn starts (#43194) (75b8ea0)
- core: Subscribe Telegram agent channels to button clicks (#43221) (4cff3b3)
- editor: Keep the API settings empty state in the header column (#43219) (c3ba6a3)
- editor: Polish skill files and version history (#43180) (4b7b145)
- editor: Update favicon and preview image branding (#43214) ([c2ea734](https://github.com/n8n-io/n8n/commit/c2ea734ba0f1cb116738c9962747516
用户点评
登录用户的真实使用记录，可按版本和硬件筛选共 0 条
还没有人点评。第一个说出真实体验的人最有价值。
n8n – The Platform for AI Agents and Workflow Automation
Fair-code platform to build and deploy AI agents and workflows. Combine a visual canvas with custom code, run it self-hosted or in the cloud, and connect to 1500+ integrations. AI automation you can trust with real work, from prototype to production.
Key Capabilities
- AI-Native Automation Platform: Build and operationalize AI workflows and multi-step agents using your own data, models, and tools
- Model Flexibility, No Lock-In: Connect to OpenAI, Anthropic, Google, or open-source models and switch providers without changing your architecture
- From Prototype to Production: Design multi-step AI workflows with logic, tool use, human approvals, and full observability
- Code When You Need It: Combine visual building with JavaScript, Python, and npm packages for advanced AI workflows
- Enterprise-Ready AI: Self-host or deploy securely with role-based access, audit trails, and support for sensitive data
- Leverage What Already Exists: 1500+ integrations and 9,000+ workflow templates to connect AI with your existing systems
Quick Start
Try n8n instantly with our install script (requires Docker):
curl -fsSL https://get.n8n.io | sh
Or deploy manually with Docker:
docker volume create n8n_data
docker run -it --rm --name n8n -p 5678:5678 -v n8n_data:/home/node/.n8n docker.n8n.io/n8nio/n8n
Access the editor at http://localhost:5678
Resources
- 📚 Documentation
- 🔧 1500+ Integrations
- 💡 Example Workflows
- 🤖 AI & LangChain Guide
- 👥 Community Forum
- 📖 Community Tutorials
Support
Need help? Our community forum is the place to get support and connect with other users: community.n8n.io
License
n8n is fair-code distributed under the Sustainable Use License and n8n Enterprise License.
- Source Available: Always visible source code
- Self-Hostable: Deploy anywhere
- Extensible: Add your own nodes and functionality
Enterprise Licenses available for additional features and support.
Additional information about the license model can be found in the docs.
Contributing
Found a bug 🐛 or have a feature idea ✨? Check our Contributing Guide for a setup guide & best practices.
Join the Team
Want to shape the future of automation? Check out our job posts and join our team!
What does n8n mean?
Short answer: It means "nodemation" and is pronounced as n-eight-n.
Long answer: "I get that question quite often (more often than I expected) so I decided it is probably best to answer it here. While looking for a good name for the project with a free domain I realized very quickly that all the good ones I could think of were already taken. So, in the end, I chose nodemation. 'node-' in the sense that it uses a Node-View and that it uses Node.js and '-mation' for 'automation' which is what the project is supposed to help with. However, I did not like how long the name was and I could not imagine writing something that long every time in the CLI. That is when I then ended up on 'n8n'." - Jan Oberhauser, Founder and CEO, n8n.io