Open-source web scraping
for LLMs

Two primitives. Clean markdown. Ready for your agents.

npm install @vakra-dev/reader

Two primitives. That's it.

scrape() for URLs, crawl() for websites. Everything else happens under the hood.

import { ReaderClient } from "@vakra-dev/reader";

const reader = new ReaderClient();

// Scrape URLs → clean markdown
const result = await reader.scrape({
  urls: ["https://example.com"],
});

console.log(result.data[0].markdown);

await reader.close();

Everything you need for web scraping

Reader handles the hard parts so you can focus on building your AI applications.

Production-Grade

Built on Ulixee Hero with TLS fingerprinting and stealth browsing

Clean Output

Markdown and HTML with automatic main content extraction

Browser Pool

Auto-recycling, health monitoring, and queue management

Website Crawling

BFS link discovery with depth and page limits

Proxy Support

Datacenter and residential proxies with rotation strategies

CLI Included

Use from command line or programmatically in your code

Open-source web scrapingfor LLMs