# n8n

> n8n is a freemium hosted agent for workflow automation. Visual workflow and AI agent automation platform for technical teams, self-hostable. It is available on Web, API, CLI and self-hosted.

- **Kind:** Agent
- **Pricing:** Freemium
- **Platforms:** Web, API, CLI, self-hosted
- **Website:** https://n8n.io
- **Repository:** https://github.com/n8n-io/n8n
- **GitHub stars:** 210,918
- **Categories:** [workflow automation](https://ai-powered.com/categories/workflow-automation)
- **Listing updated:** 2026-11-18

## About

n8n lets teams wire AI models, agents and business systems together on a visual canvas, with the option to drop into JavaScript or Python when a step needs custom logic. Each run of a workflow is recorded so you can open any step, inspect its inputs and outputs, and re-run just the part that failed.

The platform offers 500+ native integrations on the website and 1500+ integrations according to the README, plus generic HTTP requests and MCP support in both directions, so agents can call n8n workflows as tools and n8n can call external MCP servers. Human approval steps can pause an agent before it takes a consequential action.

The README describes n8n as fair-code under the Sustainable Use License, with the source on GitHub and a self-hosted option via Docker. A hosted cloud version and a Business plan for self-hosted instances are also offered. It suits engineering and operations teams that want AI automation they can inspect and deploy on their own infrastructure.

## Features

- **Visual workflow builder:** Build multi-step workflows on a canvas and add custom JavaScript or Python steps where needed.
- **Step-level run history:** Open any past execution, see what each step received and returned, and re-run only the step that broke.
- **Human approval for AI actions:** Insert approval steps so a person can review agent tool calls before they run.
- **MCP client and server:** Expose workflows to MCP clients or call external MCP servers from within a workflow.
- **Self-hosting with Docker:** Run the full platform on your own infrastructure, including on-prem, to keep data in your environment.
- **Model provider flexibility:** Connect OpenAI, Anthropic, Google and open-source models and switch providers within the same workflow.

## Good for

- Triage incoming alerts with an AI agent and route them to the right team by severity
- Qualify inbound leads by answering messages with an agent and updating the CRM record
- Automate new-hire onboarding across Slack, Jira and Notion from one workflow
- Process refund requests with classification, approval and database updates
- Run a daily AI-generated news digest from several data sources

## FAQ

### Can I self-host n8n?

Yes. The README gives a Docker command for running it locally, and the website says it can be deployed on-prem or with Docker.

### Is the Business plan available on n8n Cloud?

Not yet. The pricing page says the Business plan is currently only available for self-hosted n8n, with a waitlist for the hosted version.

### How are executions counted?

According to the pricing page, an execution is a single run of the entire workflow regardless of how many steps it contains.

### Does the Business plan include dedicated support?

No. The pricing page says dedicated support is only included in the Enterprise plan; Business users get forum support.

### Is n8n free?

n8n has a free plan, with paid plans for more usage or features.

### What are the best alternatives to n8n?

The closest alternatives to n8n are nanobot, AgentPilot, heym, LLMStack and Magick.

## Where this comes from

- Description: written from the project's README and the project's website.

## Alternatives

- [nanobot](https://ai-powered.com/agents/nanobot): nanobot is an open-source agent for ai models and llm tooling.
- [AgentPilot](https://ai-powered.com/agents/agentpilot): AgentPilot is a freemium open-source agent for ai models and llm tooling.
- [heym](https://ai-powered.com/agents/heym): heym is a freemium agent framework for workflow automation.
- [LLMStack](https://ai-powered.com/agents/llmstack): LLMStack is an open-source agent for ai models and llm tooling.
- [Magick](https://ai-powered.com/agents/magick): Magick is an open-source agent for productivity.
- [dify](https://ai-powered.com/agents/dify): dify is a freemium agent framework for workflow automation.
- [eigent](https://ai-powered.com/agents/eigent): eigent is an open-source agent for personal assistants.
- [agent-framework](https://ai-powered.com/agents/agent-framework): agent-framework is an open-source agent framework for multi-agent frameworks.

---
Source: https://ai-powered.com/agents/n8n-2
