⬢github Python · 25.7K ★ +69 since we first saw it · pushed 3 h ago · Apache-2.0
NandhaKishorM/laya
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
Laya is a Python library that makes fast, single-forward-pass decisions over text — yes/no answers, scores, or choices from typed options — in 100+ languages. Instead of generating tokens like an LLM, it uses non-autoregressive checkpoints (ModernBERT-based) trained with RL, plus a router that automatically picks the right model per request, running in tens of milliseconds.
Why now: It's trending as a newly released, heavily starred project, amplified by a dev.to article where the author says a frontier lab validated his earlier non-autoregressive decision-model idea.
Who it is for: Developers building classification, moderation, routing, or scoring pipelines who need cheap, calibrated text decisions without LLM generation.
calibrationclassificationdecision-modelhuggingfacejevmodernbertmultilingualnlppythonpytorch
Stars over our 15 snapshots: 25.6K to 25.7K, since 1 h ago.
Where people talked about it
- ⬢github new repos, most starred 8 min ago
API: https://socialmediatrends-api.osmike.com/v1/repos/NandhaKishorM/laya