01 · nextLive
/stream — Streaming response demo
Token-by-token text streaming UI — the chrome we drop in front of OpenAI / Anthropic / local model calls.
Open demo
/ sandbox
Tiny AI tools that run in your tab.
Nothing here calls our servers. Every demo loads its model and runs inference entirely in your browser — close the tab, it's gone. Open the source: it's the pattern we use in client work.
filter
// demos5 of 5
- 02 · nextLive
/browser-llm — In-browser LLM (WebGPU)
Pick from Llama, Qwen, Gemma, Phi, SmolLM and more. Weights download once and cache to your browser; inference runs on WebGPU. Zero servers, zero API keys.
Open demo - 03 · nextLive
/embeddings — Vector embeddings (MiniLM)
Index 5 public-domain novels (Austen, Shelley, Doyle, Carroll, Sun Tzu), then search them by meaning. Runs MiniLM-L6-v2 in your tab via Transformers.js.
Open demo - 04 · nextLive
/tokenizer — Tokenizer playground
Paste text → see exactly how 6 different models (GPT-4o, GPT-4, Claude, Llama 3, Mistral, GPT-2) carve it into tokens. Color-coded chips, live char/token ratio.
Open demo - 05 · nextLive
/vision — Webcam vision
Real-time object detection on your camera feed via YOLOs-tiny. Bounding boxes drawn on a canvas overlay; the video stream never leaves your tab.
Open demo
$ Want to drop in your own SPA? Build it, copy the dist into public/sandbox/<slug>/, and add an entry in src/data/sandbox.ts.