n8n
Also known as: n8n Community, n8n Cloud
Open-source workflow automation with a self-hostable engine, native AI nodes, and LLM-integrated workflow building.
n8n, pronounced n-eight-n, is an open-source workflow automation platform with native AI capabilities, built for technical teams who want the speed of no-code with the option to drop into real code. Founded in 2019 and developed under a source-available fair-code license, it lets users connect hundreds of apps and services on a visual node-based canvas, and write JavaScript or Python, add npm packages, or build custom nodes wherever a workflow needs logic that drag-and-drop cannot express. Workflows support branching, loops, error handling, and version control, so automations stay reliable in production.
Two design choices set n8n apart. First, it can be fully self-hosted, so a team runs automation on its own infrastructure, including air-gapped deployments, and credentials and data never leave their environment, which matters for regulated industries with frameworks like HIPAA. Second, its pricing is based on workflow executions rather than per-task or per-operation, so a long, multi-step AI workflow costs the same as a simple two-step one, which makes complex automation far cheaper at scale.
n8n treats AI as a first-class part of the canvas rather than a bolt-on action. Its AI Agent node, built on LangChain, creates autonomous agents that reason about a goal and decide which tools to call and in what order, assembled from modular sub-nodes for memory, tools, output parsing, and retrieval. Teams can build RAG pipelines against vector databases like Pinecone and Qdrant, route different steps to different model providers including OpenAI, Anthropic, Google, and local models through Ollama, and keep humans in the loop with approval steps, all while every step of an agent's reasoning is traceable on the canvas.
Through native Model Context Protocol support, any n8n workflow can be exposed as a tool that an external AI model can call, positioning n8n as the action layer behind an LLM's reasoning. For organizations, it adds SSO, role-based access, encrypted secret storage, audit logs, and Git-based controls. n8n is most at home with developers and technical teams running many workflows or AI agent pipelines who value cost control and ownership of their data.
Vendor details
Canonical URL
https://n8n.io/
Category
Agent builder
Company status
independent
Use cases & customers
Target customers
Deployment options
In practice
You can't send customer data through a third-party cloud for compliance reasons. n8n self-hosts on your own infrastructure, even air-gapped, so credentials and payloads never leave your environment while you still automate across hundreds of apps.
Your AI workflow has twenty steps and per-task pricing would bankrupt it. n8n charges per execution, so a long multi-step agent pipeline costs the same as a two-step one, making complex automation viable at scale.
You want an agent that triages support tickets by querying a database and drafting a reply, with a human approving before send. n8n's AI Agent node reasons over the goal, calls the tools, and pauses for approval.
Agentic Index coverage score
11.5 / 14 capabilities · 82%
| Integrations & Tool CallingAgentic AI Index Expansion Evidence Report | Full |
|---|---|
| Workflow OrchestrationAgentic AI Index Expansion Evidence Report | Full |
| Knowledge Grounding & RAGAgentic AI Index Expansion Evidence Report | Full |
| Human Oversight & GuardrailsAgentic AI Index Expansion Evidence Report | Full |
| Security, Identity & GovernanceAgentic AI Index Expansion Evidence Report | Full |
| Observability & AuditabilityAgentic AI Index Expansion Evidence Report | Full |
| Memory & State PersistenceAgentic AI Index Expansion Evidence Report | Partial |
| Deployment & Data ResidencyAgentic AI Index Expansion Evidence Report | Full |
| Prebuilt Agents, Templates & PacksAgentic AI Index Expansion Evidence Report | Full |
| Triggers & Channel CoverageAgentic AI Index Expansion Evidence Report | Full |
| Model Flexibility & RoutingAgentic AI Index Expansion Evidence Report | Partial |
| APIs, SDKs & MCP ExtensibilityAgentic AI Index Expansion Evidence Report | Partial |
| Testing, Debugging & OptimizationAgentic AI Index Expansion Evidence Report | Full |
| Browser & Computer UseAgentic AI Index Expansion Evidence Report | Unable to verify |
The Agentic Index coverage score grades every vendor Full, Partial or Unable to verify against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Recent platform changes
n8n released version 2.32, which introduces granular scope selection for Model Context Protocol (MCP) OAuth consent. Users can restrict external MCP clients to specific resources, such as workflows or data tables, using Read-only or Custom presets. The update also adds detailed MCP connection tracking, enables publishing agents directly from the AI Agent builder, and expands node capabilities for Telegram and Google Calendar.
Bears on: MCP / tool calling / API
View sourcen8n released version 2.31.0, featuring a comprehensive overhaul of its Notion integration. The updated node migrates to a newer Notion API, replacing legacy database queries with Data Sources, and introduces native support for markdown operations, JSON blocks, and database file downloads.
Bears on: Workflow orchestration
View sourcen8n shipped reliability fixes for binary-data temp-directory cleanup and webhook close-function draining to prevent MCP connection leaks.
Bears on: MCP / tool calling
View sourcePricing
From €20/mo (annual) · free self-host
runs
Included quota
Self-hosted Community Edition (free): unlimited executions/workflows/users, all integrations (you supply the server, ~$3-$20/mo). Cloud Starter (€20/mo annual): 2,500 executions/mo, 5 concurrent, unlimited workflows. Cloud Pro (€50/mo annual): 10,000 executions/mo, 20 concurrent, admin roles, global variables, 7-day insights. Business (€667/mo annual, self-hosted, <100 employees): 40,000 executions/mo, 6 projects, SSO (SAML/LDAP), Git version control, multi-environment, 30-day insights. Enterprise: unlimited executions, advanced roles, dedicated support, custom deployment.
What is public
n8n (n8n.io, by Berlin-based n8n GmbH - fair-code workflow automation, visual + code, AI-native) prices in EUR and bills by EXECUTIONS (one full workflow run = one execution, regardless of node count). Self-hosted Community Edition is free forever (unlimited executions/workflows/users). Cloud (EU/Frankfurt): Starter €20/mo annual (€24 monthly, 2,500 executions), Pro €50/mo annual (€60 monthly, 10,000 executions). Self-hosted Business - €667/mo annual (€800 monthly, 40,000 executions, SSO/Git). Enterprise custom (unlimited). 14-day free trial on all Cloud plans; no permanent free Cloud tier (removed late 2025).
Billing mechanics
Billed per EXECUTION - a single end-to-end run of a workflow counts as one execution no matter how many steps/nodes it has or how much data it moves (a 2-step and a 50-step workflow each burn one execution per run). Only SUCCESSFUL executions count (failed/test runs are free, since late 2025). This is far cheaper at scale than Zapier (per task/step) or Make (per operation). Active-workflow limits were removed across all plans (April 2026) - you pay purely on executions. Annual billing saves ~17%.
Cost watchouts
Execution caps bite on POLLING/SCHEDULED workflows - a single every-5-minute workflow generates ~8,640 executions/mo, blowing the 2,500 Starter cap in ~9 days; Cloud has NO permanent free tier (removed late 2025) and no overage on Starter/Pro (hard pause at the cap); annual lock-in for the 17% discount (no mid-year refund); Cloud limits stored credentials; self-hosting is 'free software' but you own the server + maintenance
Variable cost rationale
Execution-based and far more predictable per-run than step/operation billing (one run = one execution regardless of complexity), but still usage-driven - high-frequency triggers/polling scale executions quickly; self-hosting converts the cost to flat infra you control
Additional watchouts
Polling/scheduled workflows can blow execution caps fast (and Starter/Pro hard-pause with no overage); no permanent free Cloud tier; EUR-native pricing; self-hosting needs server/DevOps awareness (updates, SSL, security); late-2025 self-hosted-Enterprise price increases drew community pushback; fewer native app integrations than Zapier
Overage / add-ons
On Starter/Pro, workflows PAUSE when you hit the monthly execution cap (no overage option - resumes next cycle). On Business, you buy extra execution buckets (e.g., +300,000 executions = €4,000). Enterprise has unlimited executions. Self-hosted Community Edition has no caps.
Sales call required
Mixed (some tiers require a call)
Free / trial
Free trial (no card required)
Lowest paid plan
Starter ~EUR 20/mo AE
Commercial notes
One of the fastest-growing automation platforms - a developer-favored, lower-cost alternative to Zapier/Make (often ~75% cheaper at volume due to per-execution vs per-step billing); fair-code/source-available; strong AI-agent/workflow capabilities; 400+ official integrations (fewer than Zapier's 9,000 but extensible with code + community nodes); large self-hosting ecosystem (Hetzner, Coolify, managed hosts like PikaPods/InstaPods)
Key ambiguities
n8n prices natively in EUR (~$ equivalents vary with FX); pricing was restructured in late 2025 (free Cloud tier removed, self-hosted Enterprise went tiered, execution counting changed to successful-only) and the vendor notes plans/allowances change frequently - confirm current figures; the Business plan is now self-hosted-only
Cancellation / refund
Self-hosted Community Edition is free (no contract); Cloud Starter/Pro are self-serve monthly or annual (annual ~17% cheaper, no mid-year refund); 14-day free trial on all Cloud plans (no credit card for Starter/Pro; card required for Business); Business is self-hosted via license key; Enterprise is custom; a Start-up Plan gives 50% off Business for companies <20 employees
Support SLA / resale
Community support (CE); standard support on Cloud Starter/Pro; dedicated support on Enterprise; Business/Enterprise features (SSO/SAML/LDAP, Git, audit logs, multi-environment) require a license key that pings n8n's license server daily; Cloud is GDPR-compliant (Frankfurt servers); self-host for other regions or full data control
Missing data
Prices are EUR-native (USD equivalents fluctuate); plans/allowances and AI-credit grants change frequently (late-2025 restructure; confirm current figures). Seed 'Starter ~€20/mo annual; OSS Community Edition free self-host; free trial' is accurate and current; Pro is €50/mo, Business €667/mo (self-hosted), Enterprise custom; billing is per-execution.
Related vendors
- Lindy — No-code AI agent builder focused on automating repetitive business…
- Activepieces — Open-source automation platform with a self-hosted Community Edition…
- Adopt AI — No code agent builder that turns existing applications and manual…
- Agent.ai — A marketplace and network of hundreds of prebuilt AI agents plus a…
- AgentX — No code platform to build, evaluate, and deploy multi agent…
- AI Library — No code enterprise AI platform to build and run AI agents across the…
Alternatives to n8n
The closest documented capability profiles to n8n among agent builders tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- FLOWX.AI11.5 / 14Fuller documented coverage on APIs, SDKs & MCP Extensibility
- OutSystems12.0 / 14Fuller documented coverage on Model Flexibility & Routing and APIs, SDKs & MCP Extensibility
- SnapLogic12.0 / 14Fuller documented coverage on Model Flexibility & Routing and APIs, SDKs & MCP Extensibility
- Altilia11.5 / 14Fuller documented coverage on Model Flexibility & Routing and APIs, SDKs & MCP Extensibility
- Flowise11.5 / 14Fuller documented coverage on Memory & State Persistence and APIs, SDKs & MCP Extensibility
- Gumloop11.5 / 14Fuller documented coverage on Model Flexibility & Routing and APIs, SDKs & MCP Extensibilityn8n vs Gumloop →
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded