kouhxp/gutsy
Local decision model with calibrated probabilities: send a state and yes/no, choice or score questions, get a probability for every option. 0.8B GGUF on CPU, Jev-style API.
About the project
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.
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
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 12 stars today.
- The repository is 0 days old and already has 11 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, 7 h ago.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 11
- Today
- 12
- Forks
- 0
- Issues and pull requests
- 0
- Watchers
- 0
- Language
- Python
- License
- Apache-2.0
- Created
- October 1, 2026
- Last push
- October 1, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Hacker News discussions
- Show HN: Gutsy, a 0.8B Jev-compatible decision model that runs on your CPU8 points, October 1, 2026
Spotted in
- October 1, 2026Spotted on Hacker News
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/kouhxp/gutsy)Similar by description
-
0.4
kshetrajna12/reflex
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.
-
0.6
allebee/jevk5
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.…
-
4.8
firelex/jeff
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.
-
1.9
razorback16/openjev
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.…
-
4.2
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.
-
1.7
nokia-applied-research/AnyJev
Turns any LLM into a decision model with typed questions (choice, yes/no, score) that return real probabilities read from the next-token distribution, without training. L0 removes position and label-prior bias; L1 adds…