Needle-rs – AI Function calling in the browser, 258 KB WASM
A new AI tool called needle-rs has been developed, allowing function calling directly in the browser using WebAssembly. This tool operates entirely on the user's device without the need for a server or API key. The model features a 26M-parameter transformer and is designed for efficient performance with a runtime of 258 KB.
- ▪Needle-rs is a working AI agent implemented in 258 KB of WebAssembly.
- ▪The model operates without requiring a server or API key, ensuring data privacy.
- ▪It features a 26M-parameter tool-calling transformer with a call latency of approximately 280 ms.
Opening excerpt (first ~120 words) tap to expand
needle-rs AI TOOL CALLING · WASM · NO_STD GitHub 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
Excerpt limited to ~120 words for fair-use compliance. The full article is at Pages.
