needle-rs

AI TOOL CALLING · WASM · NO_STD

A working AI agent in 258 KB of WebAssembly.

Below is a 26M-parameter tool-calling transformer running entirely in this tab — no server, no API key, no data leaving your device. The model is Needle by Cactus Compute; needle-rs is the pure-Rust runtime that makes it deployable here.

258 KB
Runtime
22 MB
Weights
~280 ms
Per call
model not loaded

Weights are streamed from HuggingFace and cached by your browser. One-time download.

Use it in your own project

$ npm install needle-rs
$ cargo add needle-infer
$ pip install needle-rs