Website to Clean Markdown, Vector RAG Chunks & llms.txt
Pricing
$0.50 / 1,000 converted webpage to clean markdown + vector rag chunks + llms.txt entries
Website to Clean Markdown, Vector RAG Chunks & llms.txt
Convert any webpage or documentation site into clean structured Markdown, section-aware overlapping RAG text chunks with estimated token counts, H1-H3 outlines, quality scores, and ready-to-use llms.txt index entries for Claude, GPT, LangChain, and LlamaIndex.
Pricing
$0.50 / 1,000 converted webpage to clean markdown + vector rag chunks + llms.txt entries
Rating
0.0
(0)
Developer
Ömürsel Ocakcı
Maintained by CommunityActor stats
0
Bookmarked
1
Total users
0
Monthly active users
5 hours ago
Last modified
Categories
Share
🎁 RUN FOR FREE WITH YOUR $5.00 APIFY MONTHLY CREDIT: Every Apify account automatically receives $5.00 in free platform usage every month — enough to extract 3,300 to 10,000 verified records every single month for $0.00 out of pocket! Click the green Start button above to test immediately.
⚡ Why Choose lucacelli/ai-ready-website-to-markdown-rag-crawler Over Firecrawl / Jina Reader API ($19–$99/mo)?
- Ultra-Low Pay-Per-Result Pricing: Just $0.50 per 1,000 pages (
$0.0005/page) with $0 monthly subscription and $0 hidden add-on charges. - 100% Automation & AI-Agent Ready: Native synchronous REST API endpoint (
/run-sync-get-dataset-items) for n8n, Make.com, Clay.com, LangChain, and Claude Desktop / Cursor MCP. - Structured JSON, CSV & Excel Output: Clean, normalized fields ready for immediate CRM or database ingestion.
| Metric | This Actor (lucacelli/ai-ready-website-to-markdown-rag-crawler) | Firecrawl / Jina Reader API ($19–$99/mo) |
|---|---|---|
| Effective Price per 1,000 pages | $0.50 / 1,000 pages | $49–$299/month mandatory subscription |
| Free Monthly Allowance | Up to 10,000 items/mo free (via $5 Apify credit) | Trial / Credit Card Wall |
| n8n / Make / Clay / Claude MCP | Native 1-Click Support | Expensive Enterprise API add-on |
🔗 3x Power Combo: Chain With Our Other Cloud Actors for Full-Funnel Automation
Multiply your ROI by chaining lucacelli/ai-ready-website-to-markdown-rag-crawler with our companion Cloud Actors in n8n, Make.com, or Clay:
- Step 1 — Discover Local Businesses & Websites: Google Maps Scraper: Places, Emails, Contacts & Reviews Pro ($1.50/1k)
- Step 2 — Enrich Domains, Verified Emails, DNS MX/DMARC & 38+ Tech Signatures: B2B Domain Contact, Email, DNS & Tech Stack Enricher ($0.80/1k)
- Step 3 — Audit 45-Point Technical SEO, JSON-LD Schema & Broken Links: Technical SEO, Broken Link, Schema.org & Security Auditor ($0.80/1k)
👉 Download Ready-to-Import 3x Chained n8n Workflow JSON →
🤖 Use as a 5-in-1 AI Agent Tool in Claude Desktop, Cursor & Windsurf (MCP)
Paste this into your claude_desktop_config.json or Cursor MCP settings to give your AI assistant simultaneous access to Website to Clean Markdown, Vector RAG Chunks & llms.txt plus our top B2B intelligence Actors:
{"mcpServers": {"lucacelli-b2b-cloud-suite": {"command": "npx","args": ["-y","@apify/actors-mcp-server","--actors","lucacelli/ai-ready-website-to-markdown-rag-crawler,lucacelli/google-maps-scraper-places-emails-contacts-reviews,lucacelli/b2b-domain-contact-tech-enricher,lucacelli/shopify-store-product-contact-spy,lucacelli/seo-technical-audit-broken-link-schema-analyzer"],"env": {"APIFY_TOKEN": "YOUR_APIFY_TOKEN_HERE"}}}}
🚀 Synchronous REST API, Python & Node.js Quickstart
1. Synchronous HTTP POST (n8n / Make.com / Clay / cURL)
curl -X POST "https://api.apify.com/v2/acts/lucacelli~ai-ready-website-to-markdown-rag-crawler/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN" \-H "Content-Type: application/json" \-d '{"startUrls": ["https://docs.apify.com","https://modelcontextprotocol.io"],"chunkSizeTokens": 500}'
2. Python (apify-client)
from apify_client import ApifyClientclient = ApifyClient("YOUR_APIFY_TOKEN")run = client.actor("lucacelli/ai-ready-website-to-markdown-rag-crawler").call(run_input={"startUrls": ["https://docs.apify.com","https://modelcontextprotocol.io"],"chunkSizeTokens": 500})for item in client.dataset(run["defaultDatasetId"]).iterate_items():print(item)