← Agent Data Hub · Search endpoints · /llms.txt

HTML-to-Clean-Plaintext Sanitizer for LLM Context Saving

Strips scripts, styles, and HTML tags from raw HTML snippets to reduce LLM token consumption by up to 80%.

Call it (no API key)

GET https://api.agentdatahub.de/api/v1/call/text-html-stripper-clean?html=%3Chtml%3E%3Chead%3E%3Cstyle%3Ebody%7Bcolor%3Ared%7D%3C%2Fstyle%3E%3C%2Fhead%3E%3Cbody%3E%3Ch1%3EQuarterly%20Report%3C%2Fh1%3E%3Cp%3ERevenue%20grew%20%3Cb%3E24%25%3C%2Fb%3E%20YoY.%3C%2Fp%3E%3C%2Fbody%3E%3C%2Fhtml%3E&compact=1

Full metadata: without compact=1 · Markdown: format=llm · Only some fields: add &fields=a,b.c · MCP: tool call_api with {"apiId":"text-html-stripper-clean"}

Parameters

html Raw HTML snippet (default: <html><head><style>body{color:red}</style></head><body><h1>Quarterly Report</h1><p>Revenue grew <b>24%</b> YoY.</p></body></html>)

Example response (live, compact)

{
  "apiId": "text-html-stripper-clean",
  "data_freshness": "live",
  "data": {
    "raw_char_length": 129,
    "clean_char_length": 38,
    "token_savings_pct": 70.5,
    "clean_text": "Quarterly Report Revenue grew 24% YoY."
  },
  "source": "100% Platform Deterministic Compute / Reference Engine",
  "license": "100% Platform Local Compute"
}

Source & license

Source	100% Platform Deterministic Compute / Reference Engine
License	100% Platform Local Compute
Source URL	local://html-stripper
Terms	https://creativecommons.org/publicdomain/zero/1.0/
Category	Knowledge, Research & News › 5. Scientific Reference, Periodic Table & Text/RAG Utilities