Run Laya in the browser
Laya is small enough to run in a browser tab with no server and no API key. The input never leaves the page. The trade-off is a download of several hundred megabytes on the first visit and much slower inference than a native runtime.
361 projects
laya-workbench
uu889
Installs and serves local Laya with a bilingual web workbench and remote decision API options
laya-onnx
inferenceprince
Exports Laya to ONNX for inference with ONNX Runtime on CPUs, GPUs, and browsers
laya-typed-decisions-onnx
ti3x-m
Exports the Laya typed-decisions checkpoint to ONNX for CPU and browser inference
open-jev-laya-multilingual-onnx
killkli
A browser-ready ONNX export of Laya multilingual for typed decisions
laya-web-q8
nvkudva
Runs an 8-bit ONNX conversion of Laya locally in web browsers
laya-onnx-q8
nvkudva
Runs an 8-bit ONNX export of Laya in the browser for local text classification and decisions
laya-sdk
ryuzcorp
Provides a TypeScript SDK for running cached Laya decision models locally in browsers and Node
laya-portable
MatteoGauthier
Exports Laya to ONNX and provides JavaScript runtimes for Node.js and browser inference
laya-needle
50bbx
Finds semantically relevant webpage passages with a locally running Laya model
laya-asteroids-local
Klerith
Runs the Laya decision model locally to play Asteroids in a browser
systemone-lab
baldellimtt
Demonstrates typed System One decisions with local Laya, a playground, routing examples, and evaluation tests
laya-typed-decisions-web-q8
alfred361
Provides a quantized web build of Laya typed-decision models
layaForWeb
VishalMysore
Provides quantized ONNX checkpoints and a demo for running Laya in browsers
cut-laya-onnx
harshpreet931
An 8-bit ONNX conversion runs Laya text classification in browser-based editors
layaForWebTrained
VishalMysore
Provides a quantized ONNX version of Laya typed decisions for browser inference
laya-plays-google-snake
BoogieKn
Provides an imitation-trained Laya checkpoint that scores moves in the Google Snake game
laya-web-q8
go-vertika
Provides an 8-bit ONNX quantization of Laya for in-browser decision inference
laya-browser-agent
knpatil
Fine-tunes a ModernBERT-based Laya model for autonomous browser control
laya-typed-decisions-onnx
ningsuhen
Converts Laya typed decisions to fp16 ONNX for browser inference with WebGPU
decision-model-playground
tedliou
A local web playground comparing Laya and Jev for recommending articles
laya-mlx-ddz
smile-magic
A browser-based 斗地主 game lets two local AI seats play using Laya on Apple Silicon
laya-jev-arena
dante01yoon
Compares local Laya and hosted Jev models in games and measurement tools
laya-invaders
inhabitants
Uses Laya to choose targets in a Space Invaders game and compares it with a rule baseline
system-one-playground
minkhant1996
Provides a local web playground for Laya and other System One decision models
Libraries
kevala is a zero-dependency Rust engine compiled to WebAssembly, with WebGPU kernels. It works from any page:
<script type="module">
import { Kevala } from "https://cdn.jsdelivr.net/npm/kevala@latest/js/src/index.js";
const kevala = await Kevala.load({ model: "laya", onProgress: console.log });
</script>
or pnpm add kevala. According to its README, the Laya int8 pack is 479 MB and is kept in browser storage after the first visit.
@r4ai/laya-web runs ONNX Runtime Web with WebGPU and a WebAssembly SIMD fallback, and is designed to run in a Web Worker:
npm install @r4ai/laya-web onnxruntime-web
Demos you can open
- layaForWeb: the English checkpoint as quantized ONNX (default build about 440 MB), with a live demo.
- open-jev-laya: multilingual Laya on Transformers.js (fp16 ONNX about 647 MB) with Gomoku, Big Two and a 3D maze.
- layaAsRagJudge: checks RAG claims against retrieved evidence entirely in the tab.
Speed and support
The layaForWeb README reports that a three-question call on the default WASM backend took about 2 to 5 seconds on a 2-core machine. In that project, WebGPU works only with the int4 build, because ONNX Runtime's WebGPU MatMulNBits kernel supports 2- and 4-bit weights. open-jev-laya tries WebGPU and falls back to WebAssembly.
Caveats
Quantized browser builds do not match PyTorch exactly. layaForWeb reports 97.9% top-answer agreement for all three of its quantized builds, with the largest probability gaps in int4. For a real-time loop, laya-pong keeps the model native. Its README gives the reason: the checkpoint wants about 2.4 GB resident in f32, and wasm32 has a 4 GB address space and no Metal.
More ways to use Laya