{"repo":"vakra-dev/reader","free":true,"listed":false,"github":"https://github.com/vakra-dev/reader","clone":"git clone https://github.com/vakra-dev/reader.git","description":"Open source web infrastructure for AI. Scrape, crawl, and automate the web, clean markdown, browser sessions, ready for your agents.","language":"TypeScript","stars":557,"topics":["ai","ai-agents","anti-bot","crawler","data-extraction","headless-browser","html-to-markdown","llm","markdown","nodejs"],"license":"Apache-2.0","category":"ai-agents","readme_excerpt":"Reader Open source web infrastructure for AI. Access the web without the complexity. Docs · Examples · Discord The Problem Building agents that need web access is frustrating. You piece together Puppeteer, add stealth plugins, fight Cloudflare, manage proxies and it still breaks in production. Because production grade web scraping isn't about rendering a page and converting HTML to markdown. It's about everything underneath: Layer What it actually takes ------------------------ ------------------------------------------------------------------- Browser architecture Managing browser instances at scale, not one-off scripts Anti-bot bypass Cloudflare, Turnstile, JS challenges, they all block naive scrapers TLS fingerprinting Real browsers have fingerprints. Puppeteer doesn't. Sites know. Proxy infrastructure Standard vs premium, rotation strategies, sticky sessions Resource management Browser pooling, memory limits, graceful recycling Reliability Rate limiting, retries, timeouts, caching, graceful degradation I built Reader , a production-grade web scraping engine on top of Playwright, with stealth and anti-detection built in from the ground up. The Solution Three primitives. That's it. All the hard stuff (browser pooling, anti-bot bypass, proxy rotation, retries) happens under the hood. You get clean markdown. Your agents get the web. And when you need full browser control, browser() gives you a stealthed Chrome that Playwright or Puppeteer can drive. [!TIP] If Reader is useful","default_branch":null,"files":null,"tree":[],"storefront":"/r/vakra-dev","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/vakra-dev/reader/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}