Open-source platform combining AI agents and workflow automation, self-hostable or embeddable in SaaS products, with 250+ connectors.
- Stars
- 207,982
- Forks
- 61,183
- Open issues
- 1,209
- Last commit
- yesterday
What is it?
n8n is a workflow automation platform for building AI agents and multi-step automations. You design workflows on a visual canvas and can add custom JavaScript, Python, or npm packages where the built-in nodes are not enough. It can run self-hosted or on n8n's cloud service.
For AI work, n8n connects to models from OpenAI, Anthropic, Google, and open-source providers, and lets you switch providers without rebuilding the workflow. Workflows can include logic, tool use, and human approval steps, and the project includes MCP client and server support.
The platform provides more than 1500 integrations with existing business systems and a library of over 9,000 community workflow templates. Self-hosted deployments support role-based access and audit trails. The code is distributed under a fair-code license, with source code visible and extensible through custom nodes.
Key features
- 01Visual canvas for building workflows, with optional custom JavaScript or Python code
- 02Connects to OpenAI, Anthropic, Google and open-source models with easy provider switching
- 03Supports multi-step AI agents with tool use and human approval steps
- 04Offers 1500+ integrations with existing business systems
- 05Can be self-hosted with Docker or used through n8n Cloud
- 06Supports MCP client and server
Use cases
- Automating business processes that connect several SaaS tools and internal APIs
- Building AI agents that call company data and tools with human review steps
- Prototyping integrations and then moving them to a self-hosted production environment
Quick start
- 1
Try n8n instantly with the install script (requires Docker)
Install with the official instructions in the README - 2
Or deploy manually with Docker: create a volume
docker volume create n8n_data - 3
Start the n8n container
docker run -it --rm --name n8n -p 5678:5678 -v n8n_data:/home/node/.n8n docker.n8n.io/n8nio/n8n - 4
Open the editor at http://localhost:5678
Things to know
- Licensed under the Sustainable Use License, which is fair-code rather than OSI open source.
- Some advanced features require a paid Enterprise License.
Topics
FAQ
- What is n8n?
- Fair-code workflow automation platform for building AI agents and workflows, combining a visual canvas with custom code and 1500+ integrations. n8n is a workflow automation platform for building AI agents and multi-step automations. You design workflows on a visual canvas and can add custom JavaScript, Python, or npm packages where the built-in nodes are not enough. It can run self-hosted or on n8n's cloud service.
- Is n8n free to use? What license does it have?
- n8n is open source under the Other license. Check the license terms before using it in commercial products.
- Is n8n still maintained?
- Actively maintained. The last commit to n8n was on Oct 19, 2026.
- What can I use n8n for?
- Automating business processes that connect several SaaS tools and internal APIs Building AI agents that call company data and tools with human review steps Prototyping integrations and then moving them to a self-hosted production environment
- How do I install n8n?
- Try n8n instantly with the install script (requires Docker) Or deploy manually with Docker: create a volume: docker volume create n8n_data Start the n8n container: docker run -it --rm --name n8n -p 5678:5678 -v n8n_data:/home/node/.n8n docker.n8n.io/n8nio/n8n Open the editor at http://localhost:5678
- Where can I get n8n?
- The source code and installation instructions are on GitHub: https://github.com/n8n-io/n8n
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A self-hostable open-source visual platform for building automations, integrations, scheduled jobs and HTTP-backed workflows, with AI-assisted flow generation.
A self-improving AI agent that creates and refines skills from experience, runs on many model providers, and works through CLI and messaging apps.
Self-hosted auth gateway that lets AI agents call 1,000+ SaaS providers through SDK, CLI, MCP, HTTP, and OpenAPI without handing over credentials.
Self-hostable open-source platform for running AI agents on any model and any machine, with tools, permissions and streaming built in.
Open-source low-code platform for building internal apps, AI agents and workflow automations, with self-hosting and a model-agnostic design.