Zero-Server Cost
Static hosting on Cloudflare Pages plus a local LLM means the operational cost of one user scales to the entire planet — no inference servers, no GPU fleets, no usage bills.
Technical deep-dives into how MooduTools runs a full generative AI product with zero server infrastructure, absolute on-device privacy, and an in-browser WebGPU LLM (WebLLM) — turning typed emotions into living HTML/CSS art.
Static hosting on Cloudflare Pages plus a local LLM means the operational cost of one user scales to the entire planet — no inference servers, no GPU fleets, no usage bills.
Mood text is authored, embedded, and answered entirely inside the browser. Zero egress means your emotional data never transits a network, never touches a datacenter.
A lightweight LLM (WebLLM) is loaded over a CDN and runs on your device's GPU. No backend, no sign-up, no Chrome flags — and it works in any WebGPU-capable browser.
In-depth, engineer-authored documentation of the systems behind MooduTools.
How Cloudflare Pages static hosting and an in-browser WebGPU LLM (WebLLM) combine into a production architecture with zero egress, zero server cost, and absolute emotional-data privacy.
Rendering · CSS AnimationInside the rendering engine that parses an on-device LLM's poetic output and emotion parameters into pure HTML5/CSS interactive keyframe animations, sanitized and injected at runtime.
Every document focuses on reproducible engineering: architecture, privacy guarantees, and piping. No ads, no trackers — just the technology.