ToolsIntegrations

reader

Jina Reader — turn any URL into clean markdown. Free, fast, no API key required for casual use.

import { reader } from '@agentskit/tools'

const runtime = createRuntime({
  adapter,
  tools: [...reader()],
})

#Sub-tools

Name	Purpose
`readerFetch`	Fetch + clean a single URL via r.jina.ai

Bundled: reader(config).

#Config

type ReaderConfig = {
  apiKey?: string          // for higher rate limits
  baseUrl?: string         // default https://r.jina.ai
  fetch?: typeof fetch
}

#Example

await runtime.run('Read https://news.ycombinator.com/item?id=40000000 and list the three most upvoted arguments.')

#When to reach for reader vs alternatives

reader — zero-config, text-only, free tier.
firecrawl — paid, structured markdown + crawl trees.
fetchUrl — lowest-level; keeps HTML; zero-dep.
browserAgent — when you need to click / fill / wait.

Integrations overview · firecrawl.

Explore nearby

✎ Edit this page on GitHub·Found a problem? Open an issue →·How to contribute →

firecrawl

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

documentParsers

PDF, DOCX, XLSX parsers — BYO parser functions keep core dependency-free.

On this page

Sub-tools Config Example When to reach for reader vs alternatives Related