Resources · n8n integration

BrowserAct n8n integrationAutomate BrowserAct with n8n.

A BrowserAct bot can run from inside an n8n workflow, on your schedule and with your data. The BrowserAct n8n integration exposes one operation, Run a Bot, built on six required fields, and there is no trigger node: another node in n8n always starts the run.

Community node This node is not shipped with n8n: it is a community package (n8n-nodes-browseract) you install from Settings › Community nodes on a self-hosted instance. npm

Verified Trustpilot reviews · AI, automation & growth agency

Why automate

What does the BrowserAct n8n integration actually do?

The BrowserAct n8n integration gives a workflow one job: start a BrowserAct bot and wait for its result. The node covers a single resource, Bot, and a single operation, Run a Bot. Nothing listens on the BrowserAct side, so the run always begins with another node in n8n. Everything the bot returns lands as regular items that the next node can read.

Start with the shape of the node, because it decides how the rest of the workflow looks. One operation, one resource, no trigger. That means a BrowserAct step is never the first node on the canvas. A Schedule Trigger firing at a fixed interval, an n8n Webhook (a URL that another service calls), or the trigger of a different tool opens the workflow, and BrowserAct sits one step later.

First scenario, a recurring pull. The Schedule Trigger fires, the node runs a bot picked from the Template Marketplace, and the items come back into the workflow. Send them to Google Sheets and the sheet keeps a dated history without anyone touching it.

Second scenario, a run on demand. A Webhook node receives a call from an internal tool, the bot identifier arrives in the request body, and the node reads it with an expression such as {{ $json.botId }}. The result goes back to the caller through Respond to Webhook, so the person who clicked the button sees the answer in the same request.

Third scenario, a run that has to be watched. A bot with a long timeout can occupy a workflow for a while, so the branch that follows it matters. Route a clean result to Slack for the team channel, and route an empty or unusable one to Stop and Error so the execution fails visibly instead of passing bad data downstream.

When to reach for HTTP Request instead: the node stops at Run a Bot. Anything else the BrowserAct API offers has no button here, and the HTTP Request node calls any endpoint of that API while reusing the same credential through predefined authentication. That is the normal way to cover what a single operation cannot.

Two limits worth knowing before you build. The package is a community node, which rules out a stock n8n Cloud instance unless the node is one of the verified ones. And since no BrowserAct event can start a workflow, real reactivity depends on how often your Schedule Trigger runs or on a webhook fired by something else. The n8n review goes further into where that model fits.

Connect

How do you connect BrowserAct to n8n?

  1. 01

    Install the community node

    The node does not ship with n8n. On a self-hosted instance, open Settings, then Community nodes, and install the npm package n8n-nodes-browseract, currently version 1.4.0. Once it is installed, BrowserAct appears in the node panel like any other app. On n8n Cloud the same screen only accepts verified community nodes, so plan for self-hosting (Docker or npm) if this one is not among them.

  2. 02

    Create the credential once

    A credential in n8n is a stored set of access details. Open the Credentials menu, create the BrowserAct one there, save it, and every workflow on the instance can use it. The node then offers it in its own dropdown, so there is no key to paste again on the second workflow, or the tenth. Keeping it in one place also means a rotation is a single edit rather than a hunt through the canvas.

  3. 03

    Point the node at a bot

    Drop the BrowserAct node after your trigger and open it. Pick the operation Run a Bot, tell Search Bots From where to look, then choose the bot itself, map its inputs, set Proxy Region and leave Timeout alone unless the bot is slow. Run the node once from the editor: the output panel shows exactly what the next node will receive, which beats guessing at the field names.

Actions

What can the BrowserAct node do?

The BrowserAct node exposes 1 operations across 1 resources. For each one: the node as you configure it in n8n, the required fields, and our field notes.

Resources × operations matrix
ResourceRun a Bot
Bot✓

Bot

1 operation
01

Run a bot

workflow.runWorkflow

What you see in n8n

Notes & use cases

Starts one BrowserAct bot from the workflow and returns what the run produced, as items the next node reads.

Key parameters

  • Search Bots From: TEMPLATE for the Template Marketplace, WORKFLOW for your own published bots.
  • Bot: the marketplace bot, picked from the list or set by expression.
  • Bot: your own published bot, only if it has a published version.
  • Bot Inputs: maps incoming fields onto what the bot expects.
  • Proxy Region: the region the run goes through.
  • Timeout: run length in seconds, 3600 by default.
Use cases
a weekly competitive pull where the schedule sets the pace and the bot does the collecting.
Need help

Need help automating BrowserAct with n8n?

A person reads every message.

FAQ

BrowserAct and n8n, the usual questions

01Is the BrowserAct node free in n8n?
Nothing is charged by n8n for the node itself. It is a community node, meaning it is not bundled with n8n: it lives as the npm package n8n-nodes-browseract, version 1.4.0, installed from Settings then Community nodes. On a self-hosted instance, whether you run it through Docker or npm, that install costs nothing. On n8n Cloud the rule is narrower, since only verified community nodes are accepted there. What BrowserAct itself costs on its own side is a separate question and this page does not cover it. Budget the hosting, not the node.
02What credentials does the BrowserAct node need?
You create one BrowserAct credential in n8n and reuse it everywhere. Go to the Credentials menu, add the BrowserAct entry, save it, and the node picks it up in its dropdown on every workflow of that instance. The node has no authentication selector of its own, so there is a single path rather than a choice between several. The exact fields that credential asks for are not documented in the source used for this page, so check the form in n8n once the community package is installed. The same credential also serves an HTTP Request node through predefined authentication.
03What are the limits of the BrowserAct n8n integration?
The node covers one resource, Bot, and one operation, Run a Bot. Nothing else from the BrowserAct API has a dedicated button in n8n. When you need a call the node does not make, the HTTP Request node reaches any endpoint of that API and reuses the same credential through predefined authentication, which keeps the workflow on a single set of access details. The other limit is the install itself: a community node is not available on a stock n8n Cloud instance unless it is verified. On the run, Timeout is expressed in seconds and defaults to 3600.
04Can a BrowserAct event start an n8n workflow?
No. There is no BrowserAct trigger node, so nothing on that side can wake a workflow up. The workflow starts elsewhere and calls BrowserAct afterwards. Three options cover almost everything: a Schedule Trigger that fires at a fixed interval, an n8n Webhook, meaning a URL that another service calls when something happens on its end, or the trigger of a different tool already in your stack. Pick the Schedule Trigger for recurring collection, the Webhook when an outside system decides the moment, and set the interval according to how fresh the data has to be.
05n8n or Make for BrowserAct?
It depends on where you want the workflow to run. n8n can be self-hosted through Docker or npm, or used on n8n Cloud, the hosted offer from n8n, and a workflow behaves the same way in both. Make is hosted only, with no self-hosting option, and it bills per operation. For BrowserAct the difference is sharper than usual, because the node is a community package: installing it needs an instance you control, which points to self-hosted n8n. Beyond that, compare on data control, the cost model and which visual logic your team reads more easily.