Gui.new – The Visual Layer for AI
Hey HN, I built gui.new. You paste one line into ChatGPT or Claude, and from that point on, whenever you ask for something visual (a dashboard, chart, form, report) it renders it as a live shareable link instead of dumping HTML in your chat. The prompt: "Read https://gui.new/docs/llms.txt - use gui.new to render any visual output as a shareable link. Apply this anytime you'd normally show a table, chart, dashboard, or UI mockup." That's the whole setup. Your AI reads the spec, starts using it, and every visual output becomes a clickable URL you can share with anyone.…
What it does
In the maker’s words, at launch
Hey HN, I built gui.new. You paste one line into ChatGPT or Claude, and from that point on, whenever you ask for something visual (a dashboard, chart, form, report) it renders it as a live shareable link instead of dumping HTML in your chat. The prompt: "Read https://gui.new/docs/llms.txt - use gui.new to render any visual output as a shareable link. Apply this anytime you'd normally show a table, chart, dashboard, or UI mockup." That's the whole setup. Your AI reads the spec, starts using it, and every visual output becomes a clickable URL you can share with anyone. Every link gets real-time input sync (form fields, sliders, toggles work across all viewers), state persistence (survives after everyone leaves), and live updates via SSE. Links expire after 24 hours by default. I built it because AI is great at generating UIs but terrible at showing them. You ask for a dashboard and get a code block. gui.new closes that gap. Under the hood, your AI is making a single POST call to create a canvas: ``` POST https://gui.new/api/canvas {"html": "<h1>Hello</h1>"} -> {"url": "https://gui.new/abc123"} ``` You don't need to interact with the API yourself. But if you want to, there are SDKs (`npm install gui-new` / `pip install gui-new`) and the REST API is documented at gui.new/docs. Free, no signup. Try it at https://gui.new Happy to answer questions!
Does the same job
all alternatives →
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
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
