Illustration of what n8n does: Self-hostable workflow automation tool with a visual canvas, code steps and AI agents

n8n-io /

n8n

Self-hostable workflow automation tool with a visual canvas, code steps and AI agents

n8n lets you connect apps and services into automated workflows. You draw each workflow as a chain of nodes on a canvas. Each node does one job, such as fetching data, calling an API or asking a language model a question.

It also supports multi-step AI agents. Per the README, you can connect OpenAI, Anthropic, Google or open-source models and switch providers without redesigning the workflow. You can add logic, tool use and human approval steps.

Compared with purely no-code tools, n8n lets you drop into JavaScript, Python and npm packages when the visual nodes aren't enough. You can run it on your own server. The license is fair-code (Sustainable Use License), so the source is visible but it isn't a standard open-source license.

What it does

  • Visual canvas plus code

    Build workflows by connecting nodes, and add JavaScript, Python or npm packages for custom logic.

  • AI agents and workflows

    Build multi-step AI workflows with your own data, models and tools, including human approvals and observability.

  • Model flexibility

    Connect to OpenAI, Anthropic, Google or open-source models and change providers without changing the architecture.

  • 1500+ integrations and templates

    Connect to existing systems using the built-in integrations, and start from 9,000+ community workflow templates.

  • Self-host or cloud

    Run it yourself with Docker or use the hosted cloud. Enterprise options include role-based access and audit trails.

What you could build

  • Build an AI agent that answers questions using your own data and tools.
  • Automate routine tasks by moving data between apps such as CRMs, spreadsheets and chat tools.
  • Add a human approval step before an AI-generated action runs.
  • Self-host an automation server for data you don't want on a third-party service.
  • Start from a community template and adapt it to your own process.

Get started

Install Docker, then run either the install script or the Docker commands. Open http://localhost:5678 in your browser to reach the editor.

curl -fsSL https://get.n8n.io | sh
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

Commands are copied from the project's README. Read it on GitHub for the full setup.

More in Automation & workflows

    ↑↓ to move, Enter to open, Esc to close