m92vyas/llm-reader
Turn Webpage to LLM friendly input text. Similar to Firecrawl and Jina Reader API. Makes RAG, AI web scraping, image & webpage links extraction easy.
Leverages Playwright for async/concurrent web scraping with automatic browser management, then normalizes and cleans HTML into context-optimized text by removing noise, extracting structured data (tables, links, images), and preserving semantic relationships for LLM consumption. Designed as a modular preprocessing layer that decouples page fetching from text transformation, allowing users to substitute their own scraping infrastructure (proxies, paid APIs) while reusing the free LLM-optimization pipeline for reduced token costs and improved extraction accuracy.
280 stars.
Stars
280
Forks
19
Language
Python
License
MIT
Category
Last pushed
Feb 14, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/m92vyas/llm-reader"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
any4ai/AnyCrawl
AnyCrawl 🚀: A Node.js/TypeScript crawler that turns websites into LLM-ready data and extracts...
ScrapeGraphAI/Scrapegraph-ai
Python scraper based on AI
adbar/trafilatura
Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping,...
kreuzberg-dev/html-to-markdown
High performance and CommonMark compliant HTML to Markdown converter. Maintained by the...
lightfeed/extractor
Using LLMs and AI browser automation to robustly extract web data