Resources · n8n integration

n8n Chat Trigger nodeConfigure Chat Trigger in n8n.

A chat window is only as good as the workflow behind it. The n8n Chat Trigger node runs your workflow every time someone submits a message in an n8n generated webchat. Two head parameters decide who can reach it, one memory port decides what it remembers.

Try the Chat Trigger node on n8nSee the 2 parameters

Verified Trustpilot reviews · AI, automation & growth agency

Why automate

What does the n8n Chat Trigger node actually do?

The Chat Trigger node opens a workflow when a message is submitted in a webchat generated by n8n. It sits at the very start of the canvas, and it needs an agent or a chain root node connected to it, meaning a node that receives the workflow items on its main input and drives the sub nodes plugged into its ports. Without that root node, the chat has nothing to answer with.

Scenario one, an internal helpdesk that answers from your own documents. You turn on Make Chat Publicly Available, keep Mode on hostedChat so n8n serves the page itself, and set Authentication to n8nUserAuth so only people logged into your n8n account can ask anything. Nobody outside the instance sees the conversation.

Scenario two, a support widget on a marketing site. You switch Mode to webhook, build or embed your own interface, and point it at the Chat URL shown in the node. The agent behind it can look up an order in Google Sheets, open a ticket by mail through Gmail, or ping a channel in Slack when a human needs to step in.

Scenario three, an agent your colleagues can reach without opening the editor. Make Available in n8n Chat Hub publishes the agent to n8n Chat Hub so users of the instance can chat with it there, instead of each person hunting for the workflow.

When to prefer something else. If the conversation is not a conversation, meaning a single request with a single answer and no follow-up, a plain webhook and an HTTP Request call are simpler to reason about. The Chat Trigger earns its place when messages come one after another and the thread has to hold together.

The limits are worth knowing before you publish. Every message runs the workflow, so a conversation of 10 messages spends 10 executions of your plan allowance. The node is available from n8n 1.24.0, where it replaced the Manual Chat Trigger node, and the catalog version documented here is version 1. Previous messages are not loaded by default, that is what the Load Previous Session option and the memory port are for. If you want a wider view of the platform before committing, the n8n review covers the rest.

Connect

What do you need to connect before the chat goes live?

  1. 01

    Pick an authentication method

    Inside Make Chat Publicly Available, the Authentication selector offers three choices. none leaves the chat open to anyone holding the URL. basicAuth asks for a username and a password, the same pair for every user. n8nUserAuth requires the visitor to be logged in with an n8n account, which keeps the chat internal.

  2. 02

    Create the Basic Auth credential

    With basicAuth selected, n8n asks for a Credential for Basic Auth holding a username and a password. You create it once from the Credentials menu and reuse it in any other workflow that needs it. Keep in mind that everyone shares that single pair, so it identifies the chat, not the person typing in it.

  3. 03

    Restrict who can run the workflow

    Choosing n8nUserAuth reveals a Require Workflow Execute Permission toggle. Turn it on and a logged in user also needs execute permission on the workflow in the project it belongs to, otherwise the chat refuses them. That pairs well with end-user credentials, where each person runs the workflow with their own connected account.

Connections

What plugs into the Chat Trigger node?

n8n splits AI work between a root node, which receives the workflow items, and sub nodes, which are smaller nodes you drag onto its ports, one type of sub node per port. A sub node never runs on its own.

Ports (what plugs in)

  • Memoryai_memory
01MemoryThe memory port holds the chat history for a session, so the conversation carries over from one message to the next instead of starting from scratch.

The memory port holds the chat history for a session, so the conversation carries over from one message to the next instead of starting from scratch.

Key parameters

  • Optional : the port stays empty on a chat that never reloads a previous session, and it only appears once Load Previous Session is set to From Memory.
  • Simple Memory : the quickest way to start, with Session ID set to Connected Chat Trigger Node.
  • Postgres Chat Memory or Redis Chat Memory : when the history has to survive a restart of the instance.
Use cases
a visitor asks a follow-up two minutes later and the agent still knows which order was being discussed. n8n recommends wiring the same memory sub node to the trigger and to the agent.
Parameters

Which parameters do you actually set?

The Chat Trigger node has 2 parameters. For each one: the node as you configure it in n8n, what the parameter changes, and our field notes.

01

Make Chat Publicly Available

public

What you see in n8n

Notes & use cases

This boolean decides whether the chat is reachable by real users or only through the manual chat interface. Turning it on reveals the parameters that describe the public chat.

Key parameters

  • Mode : hostedChat serves the chat on a page hosted by n8n, webhook expects a widget embedded in another page or a call to the webhook URL.
  • Initial Message(s) : the lines shown when the chat opens, one message per line.
  • Authentication : none, basicAuth or n8nUserAuth, the way access to the chat is restricted.
  • Options : the collection where extra fields are added through Add Field.
Use cases
an onboarding assistant published on a hosted page, with two opening lines that tell the visitor what it can answer.
02

Make Available in n8n Chat Hub

availableInChat

What you see in n8n

Notes & use cases

Separate from public publishing, this boolean exposes the agent inside n8n Chat Hub, where users of the n8n instance can chat with it directly.

Key parameters

  • Make Available in n8n Chat Hub : turned on, the agent shows up in Chat Hub for the people who already work in the instance, no external URL involved.
Use cases
an ops team that keeps asking the same question about a supplier file gets an agent in Chat Hub rather than a workflow nobody remembers how to open.
Need help

Need help automating Chat Trigger with n8n?

A person reads every message.

FAQ

Chat Trigger questions, answered

01Is the n8n Chat Trigger node included in n8n, on Cloud and self-hosted?
Yes. The node ships in the n8n AI package, so there is nothing to install and nothing extra to pay on the n8n side, whether the instance runs on n8n Cloud or on your own server through Docker or npm. A workflow behaves the same way in both cases. One thing does consume your plan, though, and it is not the node itself: every message sent to the chat runs the workflow, so a conversation of 10 messages uses 10 executions of your allowance. If an AI model sits behind the chat, the model provider bills its own API calls under its own terms, and n8n adds nothing to that.
02What do you need for the Chat Trigger node to work?
Two things. First, an agent or a chain root node connected to the trigger, because the Chat Trigger opens the workflow but does not answer anything by itself. Second, an authentication choice if the chat is public. With none, anyone holding the URL can chat. With Basic Auth, you create a Credential for Basic Auth with a username and a password shared by all users. With n8n User Auth, only people logged in to an n8n account get through, and the Require Workflow Execute Permission toggle can narrow that further to users allowed to execute the workflow in its project. A credential is created once and reused everywhere.
03What are the limits of the Chat Trigger node?
The node runs the workflow on every single message, which is worth budgeting for on a busy chat. It does not load previous messages on its own either: without Load Previous Session set to From Memory and a memory sub node attached, each message arrives without context. That misconfiguration often shows up as a workflow could not be started error. Initial Message(s) only applies to the hosted interface, so an embedded chat has to display its own opening text. Finally, the documented version here is version 1, and an older workflow can still show an earlier version with fewer options.
04What should you connect at minimum, and which sub node to start with?
At minimum, an agent or chain root node on the main output, because the Chat Trigger alone has nothing to reply with. For memory, Simple Memory is the sub node to start with: attach it to the Memory connector of the trigger, attach the same node to the Memory connector of the agent, and set its Session ID to Connected Chat Trigger Node. That single source of truth avoids the mismatch that breaks session loading. Separate memory nodes make sense when you set Session ID to Define below and need a different expression (a computed value such as {{ $json.field }}) on each node.
05n8n or Make for a chat workflow like this?
It depends on where you want the conversation to live. Make is hosted by Make, with no self-hosting option, and billed per operation, so a chatty assistant multiplies the cost in a way that is easy to underestimate. n8n runs on n8n Cloud or on your own infrastructure, which matters when the chat handles customer data you would rather keep in house. On the visual side, both build flows on a canvas, and the real difference is the AI model of n8n: root nodes with ports and sub nodes you drag in. Try both on one small chat before you decide.
Hack'celeration Lab

Get our weekly integration tips.

No spam. Unsubscribe anytime.

Same platform

Other docs you might need on this stack.

Browse all integrations