Laya: 11.6k-star open-source engine outputs typed decisions in 33ms, no generation

pandeyparul · x · 2026-09-22

Laya, a trending GitHub project with 11.6k stars, is a multilingual, non-autoregressive System 1 decision engine. It evaluates typed questions (choice/score/noul) over any state — text, email, ticket, or JSON — in a single forward pass: 33ms per question, 7.2ms/question batched on a T4. No text generation means nothing to parse and nothing to hallucinate.

Training uses RLCD — RL against strictly proper scoring rules — with a router that picks the right checkpoint per request:

Install with pip install laya; requires Python 3.10+. Keep an eye on the claimed benchmarks.

Original post →

More from coding & agent

coding & agent channel →