gutsy

What it is

Local decision models with calibrated probabilities. Send a state (text or JSON) and typed questions (yes/no, choice, score); get a probability for every option back. No text generation, no network calls, no per-call cost. The API follows the Jev-style Decisions format, so existing clients mostly need only a new base…

What the README says it does

• Calibrated. A 0.8 means roughly 80% (validation calibration error 0.022).
• Local and private. Runs on CPU; your data never leaves the machine.
• Deterministic. Same request, same probabilities, on the same machine and build.
• Robust to option order. 96-97% of answers are unchanged when options are shuffled.
• Cheap follow-ups. The state is encoded once; each extra question costs only its own tokens.

From the project’s README.

Getting started

From the README:

git clone https://github.com/kouhxp/gutsy
pip install -e gutsy/gutsy-inference           # needs llama-cpp-python >= 0.3.35
pip install -U huggingface_hub
hf download kouhxp/gutsy --include "gutsy-0.8b-v04*" --local-dir gutsy/gutsy-inference/models

Where the decision sits

gutsy calls the hosted decision API rather than running its own weights. That keeps the project small and means its behaviour moves whenever the vendor ships a new model version. It also means an API key and a network round trip sit in the path of every decision.

Models it references: Jev, laya.

How active it is

Created 2026-10-01, last pushed 2026-10-05, 81 stars and 4 forks when we read it on 2026-11-02. Everything in this category is weeks old at most, so a stale push date means something different here than it would on a mature project. Check the repository before you depend on it.