url_to_llm_compact | URL to LLM-ready Markdown

USE_WHEN: RAG-ready Markdown from public URL, minimize tokens. One input → markdown + scored sections. tool_id: url_to_llm_compact. PPE url_to_llm_compact_result $0.002. MCP twin.

Pricing

from $2.00 / 1,000 url_to_llm_compact | successful results

Rating

0.0

(0)

Developer

Paweł Józefowski

Actor stats

Bookmarked

Total users

Monthly active users

3 days ago

Last modified

url_to_llm_compact

USE_WHEN: you need RAG-ready compact Markdown from a public URL and must minimize LLM tokens.

Call

{
  "url": "https://example.com/pricing",
  "maxChars": 8000,
  "selector": "#main",
  "minSectionImportance": 3
}

Returns

{ markdown, sections[{heading, text, importance}], stats{compressionRatio, estimatedTokens}, title, error?, agentHints[] }

Cost

$0.002 per result (PPE url_to_llm_compact_result). MCP x402 twin: same price.

MCP twin

url_to_llm_compact on scryptex-agent-tools — https://scryptexlabs.com/mcp.json

Markdown API

vivid_astronaut/markdown

Fabio Suizu

Site to Markdown — any site to clean, LLM-ready markdown

topsail/site-to-markdown

Scrape any website to clean, LLM-ready markdown — a compliant Firecrawl alternative for RAG ingestion, robots.txt always on.

Connor Teskey

Web to Markdown for LLMs

george.the.developer/web-to-markdown-llm

Convert any URL to clean LLM-ready markdown. 60-70% fewer tokens than raw HTML. Built for AI agents and RAG pipelines.

George Kioko

Website to Markdown Crawler for LLM & RAG

logiover/website-text-markdown-crawler

Crawl any website to clean Markdown and plain text for LLM training and RAG. HTML to Markdown, no API or login. Export website text to CSV or JSON.

Logiover

Markdown Anything — URL to Markdown

s-r/markdown-anything

Convert any URL to clean markdown using a 3-provider fallback chain. Batch input, high concurrency.

URL to Markdown for LLMs (polite, robots-respecting)

weltverbenzer/url-to-markdown-for-llms

Turn any URL into clean, LLM-ready Markdown for AI agents and RAG pipelines. Enforces robots.txt, extracts main content (Readability) and converts to Markdown. Returns title, byline and markdown.