Built with Open reimplementations

open-jev-typed-decision-engine

Open reproduction of TypeSafe Jev: a 150M typed decision engine (noul/choice/score in one non-autoregressive pass, calibrated confidence). 0.697 vs Jev's 0.727, 2.5x better calibrated, 4x faster, free. Trains on a Colab T4 in 30 min.

49 ★ on GitHub

What it is

Open Jev — a typed decision engine you can train for free

Getting started

From the README:

pip install -r requirements.txt
python smoke_test.py --all      # validate all 1,600 rows, no GPU, ~2 min
python 01_ceiling.py            # baselines you have to beat, $0
python 02_train.py --epochs 20  # ~25 min on a T4

Where the decision sits

open-jev-typed-decision-engine runs its own weights or its own runtime rather than calling a hosted API, so its decisions do not depend on a vendor being up or on a key being funded. The trade is that the model is now yours to keep current.

Models it references: open-jev-deberta-v3-large.

How active it is

Created 2026-09-19, last pushed 2026-10-06, 49 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.

Find out what your data actually supports

We turn your historical decisions into a frozen test set, then tell you which model, which threshold, and how much of it you can safely automate.