LLM Deploy
n8n-io/n8n
n8n-io/n8n· TypeScript
Self-hostable visual workflow builder with 400+ integrations and native MCP client/server support.
GitHub stats
- Stars
- 186,112
- Forks
- 57,230
- Watchers
- 1,071
- Open issues
- 1,570
meta
- License
- NOASSERTION
- Primary language
- TypeScript
- Last commit
- 2026-04-29
- Stats fetched at
- 2026-04-29
n8n is a fair-code workflow automation platform that lets you wire APIs, databases, and LLM calls together via a node-based canvas, while still allowing custom JS/Python code blocks where the visual editor falls short. It ships with 400+ pre-built integrations and first-class AI nodes (LangChain-based agents, vector stores, MCP client and server). Run it via Docker, npm, or their cloud — most teams self-host to keep credentials and data in-house. Common use: glue Slack/Sheets/CRM events to LLM agents without writing a full backend.
Editor's verdict
Pick n8n over Zapier/Make when you need self-hosting, want to avoid per-task pricing, or need real code escape hatches; pick it over raw LangGraph/LangChain when business stakeholders need to read or edit the flow. The fair-code license isn't OSI-approved — check the Sustainable Use License before embedding it in a commercial product. Skip it if your "agent" needs tight loops, complex state machines, or sub-second latency; n8n shines for event-driven glue, not for latency-sensitive inference pipelines.