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.

41
/ 100
Emerging

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.

No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 12 / 25

How are scores calculated?

Stars

280

Forks

19

Language

Python

License

MIT

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.