# StartLuxLabs/StartLux-Decision-v1

> A family of decision models: given a state and questions with options, it returns a probability for each option in one forward pass without generating text.

- Magnitude: 2.3 out of 10 — Peaking
- Stars: 365 total · +23 stars measured 2026-10-10, 00:35–20:34 UTC, ≈ 27 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: Apache-2.0 · Created: 2026-09-29 · Last push: 2026-10-10
- GitHub: https://github.com/StartLuxLabs/StartLux-Decision-v1 · Page: https://gitnova.dev/en/r/StartLuxLabs/StartLux-Decision-v1

## Useful for

- Pick the next action in browser automation using control probabilities
- Measure model confidence in a chess move choice without search
- Make decisions in a game bot (StarCraft II, Doom) via typed requests

## Why it’s here

- Star-counter measurements on 2026-10-10 (UTC), 00:35–20:34: 342 → 365 stars (+23). This is the change over that interval.
- Estimated end-of-day forecast: about +27 stars, using observed gains and the previous day.
- The repository is 11 days old and already has 365 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.

## 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: 31
- Issues and pull requests: 5
- Watchers: 3
- Average over the last week: 32 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 0

## Stars per day, last 12 days (oldest → newest, today is partial)

2026-09-29 … 2026-10-10: 9, 5, 6, 63, 75, 36, 21, 18, 45, 39, 36, 23

## Magnitude by day, last 8 days

10-03 4.5, 10-04 4.8, 10-05 4.0, 10-06 3.0, 10-07 2.4, 10-08 3.6, 10-09 3.5, 10-10 2.5

## Similar by description

1. **kouhxp/gutsy** — 2.1 · Steady · Language models · HTML · +2 stars measured 2026-10-10, 00:34–20:35 UTC, ≈ 3 by evening
   Local decision model with calibrated probabilities: send a state and yes/no, choice or score questions, get a probability for every option. Runs on CPU via GGUF, Jev-style API.
   Full card: https://gitnova.dev/en/r/kouhxp/gutsy.md
2. **OmniJev/OneJev** — 0.9 · Steady · AI agents · Python · +4 stars measured 2026-10-10, 00:40–20:38 UTC, ≈ 5 by evening
   A multimodal System One decision model that returns calibrated probabilities for typed questions about screenshots, photos, video and text in a single forward pass. Available in 0.8B, 4B, 9B and 27B.
   Full card: https://gitnova.dev/en/r/OmniJev/OneJev.md
3. **mode-io/vllm-jev** — 2.2 · Steady · Language models · Python · +20 stars measured 2026-10-10, 00:35–20:34 UTC, ≈ 23 by evening
   A vLLM-based server for Jev decision models: given a question and candidate answers, it returns a label and probability for each candidate. Runs on Linux with NVIDIA GPUs and on Apple Silicon via MLX/MPS.
   Full card: https://gitnova.dev/en/r/mode-io/vllm-jev.md
4. **Mapika/decider** — 1.3 · Cooling · Language models · Python · +8 stars measured 2026-10-10, 00:39–20:37 UTC, ≈ 9 by evening
   A language model that does not generate text: from a single forward pass it returns calibrated probabilities for typed questions (Choice, Score, Noul) about a given state. An open reproduction of the "System One" model class built on…
   Full card: https://gitnova.dev/en/r/Mapika/decider.md
5. **NandhaKishorM/laya** — 3.2 · Cooling · AI agents · Python · +169 stars measured 2026-10-10, 00:33–20:32 UTC, ≈ 197 by evening
   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.
   Full card: https://gitnova.dev/en/r/NandhaKishorM/laya.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 2026-10-10 20:41 UTC, updated every 30 minutes.