AI Workflow Automation Platform - n8n

Meet Nod, an open-source personal agent from n8n Labs.
See llms.txt for all machine-readable content.
n8n is the platform for agents and workflows you can follow. Open any step, see what it does, and explain to anyone who runs it.
When a refund request comes in, look up the order. Then ask me in Slack whether to refund it or open a ticket.
Refund requestedRefund requested
Lookup the orderLookup the order
Investigate the claimInvestigate the claim
Parse the verdictParse the verdict
Ask for approval on SlackAsk for approval on Slack
Process refundProcess refund
Open ticketOpen ticket
Confirm to customerConfirm to customer
Record refund in databaseRecord refund in database
Classify reason for refundClassify reason for refund
Route by reasonRoute by reason
Get order itemsGet order items
Email win-back discountEmail win-back discount
Queue a return pickupQueue a return pickup
File QA ticketFile QA ticket
Merge pathsMerge paths
Add to the refunds reportAdd to the refunds report
Publish refund-closed eventPublish refund-closed event
Claude Sonnet 4.6Claude Sonnet 4.6
Read the refund policyRead the refund policy
Check order historyCheck order history
Read past ticketsRead past tickets
Track the deliveryTrack the delivery
Trusted by Fortune 500 companies to build smarter workflows.
New hires get instant access to Slack, Jira, Notion, and more, all in one workflow.
Suspicious indicators are checked against multiple security tools, combined into one report, and summarized by AI, all in one workflow.
When an alert comes in, an AI agent investigates it, then routes it by severity to the right people and tools, all in one workflow.
New messages are answered and qualified by an AI agent, the lead record is kept up to date, and a reply goes out, all in one workflow.
Top 50 Github project with 210.3k stars
Rated 4.7/5 from real users on G2
Join 250k+ developers in our community
Connect n8n to just about any tool you can think of. 500+ native integrations. Any API via HTTP. Any agent or coding assistant via MCP.
Connect any model, see every decision, and add human approval when needed.
Watch agents work live, or open any past run, all inside the same workflow.
Use structured inputs and outputs for AI actions. Add human-in-the-loop approvals and rule-based automation.
Deploy on-prem or with Docker to keep your data in your own environment. Access the source code on GitHub, or use the hosted version.