Built with Open reimplementations
jev-forge
An open training and inference stack for Jev-style decision models. Train models to score dynamic candidate branches from a shared prefix, with support for high-cardinality choice, calibration, and fast batched inference.
164 ★ on GitHub
What it is
An end-to-end toolkit for synthesizing decision data, training calibrated candidate scorers, evaluating them, and serving Jev-compatible inference for interactive web decisions.
The homepage listed on the repository, jay-forge-web.vercel.app, puts it like this: JevForge unifies data synthesis, training, evaluation and Jev-compatible inference for decisions inside web interactions.
Where the decision sits
jev-forge 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, JevForge-0.8B.
How active it is
Created 2026-09-19, last pushed 2026-10-16, 164 stars and 15 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.