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:
- laya: ModernBERT-large, 421M params, 512 context, English
- laya-multilingual: mmBERT-base, 322M params, 1024 context, 100+ languages, 2x faster
- laya-typed-decisions: for typed-decision workflows
Install with pip install laya; requires Python 3.10+. Keep an eye on the claimed benchmarks.
More from coding & agent
- Copilot + Luna agent auto-fills GitHub issue from video transcript for just 16.6 cents — lee_stott · 2026-09-22
- Resist the slop tornado: read reasoning traces and steer your agent — deobfuscations · 2026-09-22
- Local Qwen 27B agent logs into Amazon and buys paper autonomously in one run — fuzhongkai · 2026-09-22
- Steve Yegge floats 'Agentic TPMs' as the fastest path for coding agents into enterprises — Steve_Yegge · 2026-09-22
- Prof. Tom Yeh releases printable hand-calc agentic AI cost math problems — ProfTomYeh · 2026-09-22
- apibase unifies 327 tools from 92 providers behind one pay-per-call MCP endpoint — modelcontextprotocol · 2026-09-22