Built with Open reimplementations
RSI-Jev
Typed-decision models (noul / choice / score) trained by a self-improving loop of AI agents — checkpoints, the code that produced them, and every version that failed.
128 ★ on GitHub
What it is
A recursively self-improving research loop that builds Jev -style System One decision models.
The homepage listed on the repository, shgao.site, puts it like this: Shanghua Gao
Getting started
From the README:
pip install "rsi-jev[fast,vision] @ git+https://github.com/Shanghua-Gao/RSI-Jev"
rsi-jev serve v6.1-vl-4b --effort auto --port 8000Where the decision sits
RSI-Jev 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.
How active it is
Created 2026-09-22, last pushed 2026-10-10, 128 stars and 11 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.