n8n
n8n is a workflow automation platform for building AI agents and multi-step automations on a visual canvas, with the option to drop into JavaScript or Python whenever the visual nodes are not enough. It ships with 1,500+ integrations and more than 9,000 community workflow templates, and you can run it self-hosted or on n8n Cloud.
It suits technical teams, ops engineers and solo builders who want to connect LLMs to the systems they already use: CRMs, databases, ticketing, chat and internal APIs. Typical projects include an AI agent that triages support tickets and drafts replies for human approval, a scheduled pipeline that pulls data from several SaaS tools and summarises it with a model, and internal automations that replace scripts scattered across cron jobs. Model providers (OpenAI, Anthropic, Google or open-source models) can be swapped without rebuilding the workflow.
Getting started: the install script `curl -fsSL https://get.n8n.io | sh` sets n8n up with Docker, or you can run the official Docker image directly and open the editor at http://localhost:5678. Self-hosting needs Docker; the cloud version needs nothing locally.
Features
Why choose it
Trade-offs
Maintenance check
- Last commit
- 2026-10-24
- Commits, last 90 days
- 100+
- Releases, last 90 days
- 30
- Latest release
- [email protected] (2026-10-23)
- Open issues
- 1226
- Recent issues with at least one comment
- 6/6
Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.
Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.
Most discussed open issues
- #14361 AI Agent doesn't store the Tool usages in memory57 comments · 2025-04-02
Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.
Who it fits
- You want a visual workflow builder with 1,500+ integrations, 9,000+ templates, and first-class AI agent, tool-calling, and human-approval nodes.
- You want the ability to drop in custom JavaScript or Python code steps inside visual workflows and self-host via Docker.
- You require an OSI-approved open-source license (such as MIT or Apache-2.0); n8n uses the fair-code Sustainable Use License.
- You want code-first durable execution without a visual canvas; Temporal or AutoKitteh are built for code-first workflows.
How it differs
vs Activepieces★ 25.2kn8n has a much larger integration library (1,500+ vs a few hundred) but uses the fair-code Sustainable Use License. Activepieces Community Edition is MIT licensed and automatically exposes every integration piece as an MCP server.
vs temporal★ 24.0kn8n is a visual workflow and integration platform with 1,500+ connectors; Temporal is a code-first durable execution engine for mission-critical backend services and long-running agent loops.
Compatibility
Quick start
Use cases
Alternatives
Featured in these lists
Comments
No comments yet. Be the first!