n8n

Source-available workflow automation with native AI agent nodes

AI Agents & AutomationFree planOverseasβ˜…β˜…β˜…β˜…β˜… 5.0

What is n8n?

n8n is a workflow automation platform you can self-host, combining a visual node editor with the ability to drop into JavaScript or Python when a step needs custom logic. It has grown into a common home for AI work: agent nodes, vector database connectors, memory, tool calling and model providers are first-class building blocks rather than add-ons, so a retrieval or agent workflow can sit next to ordinary business automation. Fair-code licensing and self-hosting matter to teams with data residency rules, and the node library covers hundreds of services.

Last updated: 2026-09-20. This site only provides an index; for exact features, pricing, and licensing, see the official website.

Key features

  • Visual node-based workflow editor with branching and loops
  • Native AI agent, chain and memory nodes with tool calling
  • Self-hosting with Docker plus a managed cloud option
  • Custom code steps in JavaScript or Python inside a workflow
  • Hundreds of integration nodes for common business services
  • Vector store and embedding connectors for retrieval workflows

Pros & cons

Strengths

  • Self-hosting keeps sensitive data inside your own infrastructure
  • AI agents and ordinary automation live in one workflow
  • Code steps prevent the visual editor from becoming a dead end

Watch out for

  • Self-hosting means you own upgrades and uptime
  • Complex workflows need real engineering discipline
  • The learning curve is steeper than simpler no-code tools

Best for & use cases

technical teams, self-hosted automation, ai agent workflows and internal tooling

If you're comparing similar products, check the alternatives below, or browse all tools in the AI Agents & Automation category.

FAQ

Is n8n free?

The community edition is free to self-host under a fair-code licence. Managed cloud and enterprise plans are paid, and larger teams usually move to those for support and lower operational effort.

How does it differ from Zapier?

The main difference is depth and hosting. n8n supports loops, custom code and self-hosting, which suits technical teams, while Zapier leans toward simpler setups and the broadest app catalogue.

Can it run AI agents?

Yes. Agent, memory, tool and model-provider nodes are part of the platform, so a workflow can retrieve documents, call an LLM and then act on the result in another system.