@r4ai/laya-web: client-side Laya-MLX inference with WebGPU and Wasm fallback

RaiSep 20

Browser runtime for Laya decisions on ONNX Runtime Web. WebGPU with SIMD Wasm fallback, Web Worker friendly, CPU embedding slicing to get past storage-buffer limits.

Open on GitHub

Preview of @r4ai/laya-web: client-side Laya-MLX inference with WebGPU and Wasm fallback

Launch: Laya
Use case: Agents
Format: Repo
Source: github.com

Rai

1st-year MS in Computer Science

See all

codejunkie99

@codejunkie99 · Sep 22

tswawa

@tswawa · Sep 23

ipenywis

@ipenywis · Sep 21

A port of the jev-ultrafast browser agent that decides with local laya-mlx instead of the hosted Jev API, covering DOM snapshot, executor and safety checks. Runs free on Apple Silicon.

wdobry

@wdobry · Sep 20

Open on GitHub

@r4ai/laya-web: client-side Laya-MLX inference with WebGPU and Wasm fallback

More built with Laya