Snitchmd – Cloudflare-protected URLs into clean Markdown via Docker
Beats Firecrawl on token count for Cloudflare sites when you need local execution.

HTML-to-Markdown for LLMs when JinaAI and Firecrawl already exist.
AI engineers building RAG pipelines and web scrapers
Jina AI Reader · Firecrawl · Html2Markdown
Beats Firecrawl on token count for Cloudflare sites when you need local execution.
Turns messy X threads into clean Markdown for LLMs better than generic scrapers.
Smartly checks for native markdown files before falling back to HTML scraping.
Nice, focused product: site-specific extraction rules (CSS selectors/metadata overrides), edge-first delivery (<500ms p99) and SDKs for Node/Python make it quick to drop into an LLM pipeline and claim 40–60% token savings. That said, HTML→Markdown is a crowded niche (Pandoc, Jina, Firecrawl and dozens of scrapers already exist), so Klovr needs clearer differentiation — e.g. demonstrable extraction accuracy, enterprise-grade rule sharing, or unique model-aware trimming — to move beyond 'handy utility'.
Strips 90% of tokens from web pages for agents—no API key, no server, MIT open source.
Multi-tab + token counter saves context-window hunting; but web-to-Markdown is solved.