A search engine that values depth over popularity
Hey HN, I'm excited to introduce Graphthem, a search engine designed to explore the deeper layers of knowledge rather than just surface-level popularity. While many AI search engines simply summarize top N results, we've found this approach often misses the many good stuff that is buried deeper in the links and references. Graphthem takes a different approach. we don't just look at the first few pages we find. We also dig into what those pages link to, so you get the whole story. This allows us to deliver answers that capture not just what's immediately visible, but also the foundational…
In plain words
Graphthem is a search engine that prioritizes comprehensive knowledge over surface-level results. Rather than summarizing only top-ranked pages, it explores links and references within those pages to uncover deeper insights and foundational ideas. The tool is designed for users seeking thorough answers that go beyond what initially appears in search results, offering a more complete picture of a topic by examining the interconnected layers of information.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey HN, I'm excited to introduce Graphthem, a search engine designed to explore the deeper layers of knowledge rather than just surface-level popularity. While many AI search engines simply summarize top N results, we've found this approach often misses the many good stuff that is buried deeper in the links and references. Graphthem takes a different approach. we don't just look at the first few pages we find. We also dig into what those pages link to, so you get the whole story. This allows us to deliver answers that capture not just what's immediately visible, but also the foundational ideas and deeper insights that inform those results. Here's a comparison between Perplexity and Graphthem: Query 1: "most watched youtube videos?" Perplexity: https://www.perplexity.ai/search/most-watched-youtube-videos... Graphthem: https://graphthem.com/search?uuid=7f0839a9-85ee-4f81-a5c9-cb... - Query 2: "what is pagerank?" Perplexity: https://www.perplexity.ai/search/what-is-pagerank-ieJ.4iFqTq... Graphthem: https://graphthem.com/search?uuid=c689e9d1-d3d4-4d51-8602-00... --- Some related ideas I've explored before: https://news.ycombinator.com/item?id=35826540 https://news.ycombinator.com/item?id=35510949 I would love to hear your feedback. Please let us know how we can improve.
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 · 18d 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 · 26d ago · cactuscompute.com
