# NandhaKishorM/laya

> Laya is a non-autoregressive decision engine that answers typed questions (choice, score, noul) over any state (text, email, ticket, JSON) in a single forward pass (~35 ms on GPU) with calibrated probabilities.

- Magnitude: 2.6 out of 10 — Steady
- Stars: 34,914 total · +16 stars measured 2026-11-03, 00:34–06:16 UTC, ≈ 67 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · License: Apache-2.0 · Created: 2026-09-18 · Last push: 2026-11-01
- GitHub: https://github.com/NandhaKishorM/laya · Homepage: https://huggingface.co/convaiinnovations/laya · Page: https://gitnova.dev/en/r/NandhaKishorM/laya

## Useful for

- Route incoming emails to departments with a confidence threshold for automation
- Score churn risk and phishing probability in support using calibrated probabilities
- Run prompts through guardrails to detect jailbreaks and injections

## Why it’s here

- Star-counter measurements on 2026-11-03 (UTC), 00:34–06:16: 34898 → 34914 stars (+16). This is the change over that interval.
- Estimated end-of-day forecast: about +67 stars, using observed gains and the previous day.
- The repository is 46 days old and already has 34,914 stars.
- Top new repositories in the last 4 months: #8.
- About 7 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 3,122
- Issues and pull requests: 1,380
- Watchers: 123
- Average over the last week: 71 per day
- Usual pace: 232 per day
- Stars in the last hour (measured): 2
- Latest release: v0.4.21 (2026-11-01)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-05 … 2026-11-03: 290, 231, 287, 275, 245, 171, 211, 217, 206, 151, 142, 129, 98, 152, 168, 162, 162, 119, 121, 100, 116, 93, 85, 90, 69, 67, 60, 74, 73, 16

## Magnitude by day, last 14 days

10-21 3.3, 10-22 3.3, 10-23 3.1, 10-24 3.0, 10-25 2.8, 10-26 2.9, 10-27 2.7, 10-28 2.8, 10-29 2.8, 10-30 2.6, 10-31 2.5, 11-01 2.4, 11-02 2.8, 11-03 2.6

## Spotted in now

- Top new repositories in the last 4 months: #8

## Similar by description

1. **deepopen-com/deepopen** — 0.0 · Cooling · Language models · Python · Not enough measurements today · unusual star pattern (heuristic)
   Open-source non-autoregressive System 1 decision engine for typed decisions: returns typed answers (choice, score, noul) in a single forward pass across 100+ languages without generating text. Suited for classification, routing and…
   Full card: https://gitnova.dev/en/r/deepopen-com/deepopen.md
2. **jaredpalmer/kev** — 2.1 · Steady · Language models · Python · +9 stars measured 2026-11-03, 00:37–06:17 UTC, ≈ 27 by evening
   kev is a LoRA adapter with a small readout head on top of Qwen2.5-0.5B that answers many typed questions about a document in a single forward pass, returning calibrated probabilities instead of text.
   Full card: https://gitnova.dev/en/r/jaredpalmer/kev.md
3. **mizorewww/laya-mlx** — 0.8 · Steady · Language models · Python · +0 stars measured 2026-11-03, 00:40–06:22 UTC, ≈ 2 by evening
   Native MLX runtime for Laya typed decision models: returns probabilities for choices, scores or truth values without text generation, running locally on Apple Silicon.
   Full card: https://gitnova.dev/en/r/mizorewww/laya-mlx.md
4. **spinfinc/spinf-serve** — 0.8 · Steady · Language models · Python · +0 stars measured 2026-11-03, 00:41–06:21 UTC, ≈ 0 by evening
   A serving engine for bulk classification and decision inference on a single 24 GB GPU: it reads content once and scores many questions about it in the same pass, exposing an OpenAI-compatible API. Built for high-throughput calibrated…
   Full card: https://gitnova.dev/en/r/spinfinc/spinf-serve.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-11-03 06:23 UTC, updated every 30 minutes.