compress.new
Compress markdown for LLMs. Cut token usage drastically.
What it does
Web-to-markdown isn't new. But when you're feeding thousands of pages to LLMs daily, sloppy conversion bleeds tokens - and money. compress.new extracts only what matters. Try it and use it - it's free. Getting started is simple: just prepend `https://compress.new/` to any public URL you want to convert. You can control extraction and compression behavior using feature flags via query parameters (for example, enabling compression or targeting specific content). No setup, no SDK (yet!)
Does a similar job
all alternatives →
- IMI made a tool to clean and convert any webpage to Markdown2024 · markdowndown.vercel.app · ▲441
My partner usually writes substack posts which I then mirror to our website’s blog section. To automate this, I made a simple tool to scrape the post and clean it so that I can drop it to our blog easily. This might be useful to others as well. Oh and ofcourse you can instruct GPT to make any final edits :D
Geekflare Scraping API v2Apr 2026 · geekflare.com · ▲84RAG-ready web scraping that cuts your LLM token costs
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
