agentskit.js
ToolsIntegrations

firecrawl

Firecrawl — scrape a URL or crawl a site, returning clean markdown. The workhorse for RAG ingestion from the open web.

import { firecrawl } from '@agentskit/tools'

const runtime = createRuntime({
  adapter,
  tools: [...firecrawl({ apiKey: process.env.FIRECRAWL_API_KEY! })],
})

Sub-tools

NamePurpose
firecrawlScrapeOne-shot scrape of a single URL
firecrawlCrawlRecursive crawl with include/exclude patterns

Bundled: firecrawl(config).

Config

type FirecrawlConfig = {
  apiKey: string
  baseUrl?: string          // self-hosted Firecrawl
  fetch?: typeof fetch
}

Example — on-demand RAG

const runtime = createRuntime({
  adapter,
  tools: [...firecrawl({ apiKey }), ...rag.tools],
})

await runtime.run('Fetch https://example.com/changelog and answer what shipped this week.')

Comparison

ToolWhen to use
firecrawlStructured markdown + crawl trees, API-backed, paid
readerJina Reader — fast, free, single-URL
fetchUrlZero-dep HTTP GET, no cleanup
browserAgentFull JS-rendered interaction
✎ Edit this page on GitHub·Found a problem? Open an issue →·How to contribute →

On this page