Web data · Integration

AI agents for Firecrawl

Clean page extraction for research-grade scraping. AGNT connects to Firecrawl so agents can read what happens there, reason about it, and act — with a receipt for every run.

Install Research Analyst → Get AGNT free

Research Analyst is a ready-made agent that works in Firecrawl — free, and it runs on your machine.

Firecrawl and AGNT, in brief

What it does	Lets an AGNT agent read from and act in Firecrawl.
Connects with	An API key held in the local vault
AGNT node	firecrawl-api
Runs when	A scheduled crawl runs
Typical build time	Two minutes
Where data goes	Nowhere by default — AGNT runs on your machine and credentials never leave it.

What you can automate

Reacts when…

a scheduled crawl runs

Agents can…

scrape pages to clean text
crawl site sections
extract structured fields

Teams use it for

competitor pages diffed weekly
research corpora built from the web
listings extracted into sheets

Build it: the Firecrawl workflow

Most Firecrawl builds begin the same way. A run starts when a scheduled crawl runs. The agent reads what arrived, judges it against criteria you wrote in plain language, and acts only where that judgment says it should — typically to scrape pages to clean text. That is what makes competitor pages diffed weekly something you can hand over rather than merely schedule.

The shape is deliberately small. A trigger watching Firecrawl, an agent that judges what arrived, and one action taken only when that judgment warrants it. Everything below is the actual definition, not an illustration of one.

The whole flow runs locally against your own Firecrawl account. Deciding to take no action counts as an outcome and is recorded like any other.

Firecrawl — read, decide, actpaste into a new workflow

{
  "id": "88766061-92e7-4fc7-a77b-43863b62d08e",
  "name": "Firecrawl — read, decide, act",
  "nodes": [
    {
      "id": "754fa7fb-893a-484c-a1c7-c5f7c7fe12c4",
      "text": "Run on a schedule",
      "x": 512,
      "y": 144,
      "isEditing": false,
      "type": "trigger-timer",
      "icon": "clock",
      "category": "trigger",
      "isSelected": false,
      "parameters": {
        "interval": "15",
        "unit": "minutes"
      },
      "description": "Checks Firecrawl every fifteen minutes.",
      "error": null,
      "isActive": false,
      "output": null,
      "outputs": {}
    },
    {
      "id": "e77439bd-94f3-4bdb-a887-28cc454e6222",
      "text": "Read it and decide",
      "x": 512,
      "y": 336,
      "isEditing": false,
      "type": "agnt-agent",
      "icon": "agnt",
      "category": "action",
      "isSelected": false,
      "parameters": {
        "instructions": "Read the Firecrawl item and decide whether it warrants action. Explain your reasoning."
      },
      "description": "Judges the Firecrawl item against criteria you wrote in plain language.",
      "error": null,
      "isActive": false,
      "output": null,
      "outputs": {}
    },
    {
      "id": "48b12ff3-d312-42d6-a4f9-839133fab214",
      "text": "Act in Firecrawl",
      "x": 512,
      "y": 528,
      "isEditing": false,
      "type": "firecrawl-api",
      "icon": "connect",
      "category": "action",
      "isSelected": false,
      "parameters": {},
      "description": "Scrape web content using Firecrawl API",
      "error": null,
      "isActive": false,
      "output": null,
      "outputs": {}
    }
  ],
  "edges": [
    {
      "id": "915c4abb-3c40-4d45-aa45-9dec0d39983a",
      "start": {
        "id": "754fa7fb-893a-484c-a1c7-c5f7c7fe12c4",
        "type": "output"
      },
      "end": {
        "id": "e77439bd-94f3-4bdb-a887-28cc454e6222",
        "type": "input"
      },
      "startX": 800,
      "startY": 168,
      "endX": 512,
      "endY": 360
    },
    {
      "id": "23c7c814-8208-4d50-a349-669eee620b30",
      "start": {
        "id": "e77439bd-94f3-4bdb-a887-28cc454e6222",
        "type": "output"
      },
      "end": {
        "id": "48b12ff3-d312-42d6-a4f9-839133fab214",
        "type": "input"
      },
      "startX": 800,
      "startY": 360,
      "endX": 512,
      "endY": 552
    }
  ],
  "zoomLevel": 1,
  "canvasOffsetX": 0,
  "canvasOffsetY": 0,
  "isTinyNodeMode": false
}

Install Research Analyst — it runs on Firecrawl

Research Analyst is a working agent that uses Firecrawl. Installing it drops the whole workflow onto your canvas — connected, editable, and yours to change.

Install Research Analyst → Don’t have AGNT? Get it free

Runs on your own machine · See what it does

Clean text is what makes web data usable

Raw HTML is mostly navigation, scripts and boilerplate. Extraction that returns clean readable text is what makes a page useful as model input, and it is the difference between research that works and a context window full of menus.

Monitoring and research at scale

Scheduled crawls of pages you care about — competitor pricing, changelogs, documentation — build the history that makes change detection meaningful rather than a snapshot of today.

Inside the Firecrawl API node

Scrape web content using Firecrawl API

Full Firecrawl API parameter reference

Parameter	Type	What it does
`url`required	string	The URL to scrape
`format`required	string	The desired output format Markdown · HTML

Every parameter above is read from the shipped firecrawl-api node, so it cannot drift from the product.

Connect Firecrawl in two minutes

Download AGNT Community Core — free, local-first, no account needed to run.
Connect by pasting an API key into AGNT’s vault — stored encrypted on your machine, never uploaded.
Drop the Firecrawl node into a workflow or hand it to an agent — the first run produces a receipt you can read line by line.