Amelia's Agent - Dream It, AI Builds It.
Build apps with any AI model. See what every turn costs.
What it does
Most AI builders lock you to one model and burn credits you can't see. Amelia's Agent prices every turn before it runs — real sites on our examples page cost $0.007–$0.01 to build — and a spend cap is on by default, so no overdraft. Pick from 300+ models. Every project is a real git repo you own from turn one, not a walled garden. Publish in one click with SSL, or self-host with your own keys and pay us nothing. Free to start, come join the ai building revolution!
Describe it and watch it get built — or bring the site or repo you already have. 300+ AI models, a git repo you own, one-click publishing, and the exact cost on every answer.
Then preview it, put it online in one click, and keep every file — the work is yours. Already have a site or a repo? Bring it — she edits that too . Hey — I’m Amelia. Tell me what you want to build and I’ll start on it right now. Built from one prompt each, priced at what our own account was charged. All 53 builds → What the money is for — and what happens to everything you built if you ever stop paying it. Zip it, clone it, or push it to your own GitHub. Any time, plan or no plan. Three sites online on your own domain, on every plan. No extra charge. Your project runs on a machine in the cloud, not on your laptop. Nothing to install, and it works…from ameliasagent.com
Does the same job
all alternatives →
PlaygroundJul 2026 · playground.fabraix.com · ▲198Earn $100K+ in weekly rewards for hacking AI agents.
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, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
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