laya

What it is

Multilingual, non-autoregressive System 1 decision engine. Typed decisions over 100+ languages in a single forward pass — 33 ms — trained with reinforcement learning against strictly proper scoring rules (RLCD), with a router that picks the right checkpoint per request.

The homepage listed on the repository, huggingface.co, puts it like this: Text Classification model with 0.4B parameters. Download, explore files and run it on Hugging Face.

Getting started

From the README:

python -m pip install laya

Where the decision sits

laya calls the hosted decision API rather than running its own weights. That keeps the project small and means its behaviour moves whenever the vendor ships a new model version. It also means an API key and a network round trip sit in the path of every decision.

Models it references: Jev, laya-typed-decisions, laya-browser, laya-multilingual, laya-typed-decisions, laya.

How active it is

Created 2026-09-18, last pushed 2026-11-01, 34,859 stars and 3,116 forks when we read it on 2026-11-02. Everything in this category is weeks old at most, so a stale push date means something different here than it would on a mature project. Check the repository before you depend on it.