# kouhxp/gutsy

> 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.

- Magnitude: 2.5 out of 10 — Early signal
- Stars: 12 total · +0 stars today, ≈ 12 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: Apache-2.0 · Created: 2026-10-01 · Last push: 2026-10-01
- GitHub: https://github.com/kouhxp/gutsy · Page: https://gitnova.dev/en/r/kouhxp/gutsy

## Useful for

- Classify support tickets into categories without sending data to the cloud
- Gate risky agent actions on a probability threshold measured on your own labeled data
- Run content moderation locally on CPU with calibrated probabilities

## Why it’s here

- 0 stars so far today, about 12 expected by the end of the day.
- The spike has held for 2 days in a row — not a one-off blip.
- The repository is 1 day old and already has 12 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Hacker News: “Show HN: Gutsy, a 0.8B Jev-compatible decision model that runs on your CPU” — 8 points, 8 h ago.

## 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: 0
- Issues and pull requests: 0
- Watchers: 0
- Average over the last week: 12 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 1

## Stars per day, last 6 days (oldest → newest, today is partial)

2026-09-27 … 2026-10-02: 0, 0, 0, 0, 12, 0

## Magnitude by day, last 2 days

10-01 2.6, 10-02 2.5

## Hacker News

- Show HN: Gutsy, a 0.8B Jev-compatible decision model that runs on your CPU — 8 points, 2 comments: https://news.ycombinator.com/item?id=49923223

## Spotted in now

- Spotted on Hacker News

## Similar by description

1. **kshetrajna12/reflex** — 0.1 · Steady · Language models · Python · +0 stars today, ≈ 0 by evening
   An open decision model: given a state (text, JSON, or image) and typed questions, it returns calibrated probabilities over fixed answer options. Runs on top of Qwen3.5 and answers with numbers instead of free text.
   Full card: https://gitnova.dev/en/r/kshetrajna12/reflex.md
2. **allebee/jevk5** — 0.4 · Steady · Language models · Python · +0 stars today, ≈ 1 by evening
   An open-weight alternative to TypeSafe Jev: given a state (ticket, log, policy, diff) and a yes/no, choice, or score question, it returns a probability for every option in one forward pass with zero generated tokens. Qwen3.5-4B weights…
   Full card: https://gitnova.dev/en/r/allebee/jevk5.md
3. **firelex/jeff** — 4.4 · Cooling · Language models · Python · +0 stars today, ≈ 51 by evening
   Small fine-tuned Qwen3.5 and Gemma 4 models for zero-shot classification: given a situation description and a list of options, they return a calibrated probability for each option in a single forward pass.
   Full card: https://gitnova.dev/en/r/firelex/jeff.md
4. **razorback16/openjev** — 2.0 · Cooling · Language models · Python · +0 stars today, ≈ 19 by evening
   An open-source "System One" decision server on DiffusionGemma: send a state and typed questions (yes/no, choice, score) and get probabilities plus confidence in tens of milliseconds, with no text generated. Wire-compatible with TypeSafe's…
   Full card: https://gitnova.dev/en/r/razorback16/openjev.md
5. **NandhaKishorM/laya** — 4.1 · Cooling · AI agents · Python · +0 stars today, ≈ 458 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 2026-10-02 00:11 UTC, updated every 30 minutes.