GitHub · by Shanghua Gao

RSI-Jev

Decision models trained by a self-improving loop of AI agents.

Shanghua Gao's RSI-Jev is a recursively self-improving research loop that builds Jev-style System One models. AI agents propose the hypotheses, register their predictions before they spend GPU time, run the experiments and retire their own champions. The repository reports 8 releases in 13 days and 496 experiments, each one written up, failures included.

Shanghua-Gao/RSI-Jev on GitHub

Stars: 83
Forks: 5
Language: HTML
Last push: Oct 7, 2026

Repository created Sep 22, 2026. Counts read from the GitHub API on Oct 8, 2026, and they move daily — quote them with the date.

Open the source

CUA-S1-FORMS

Parameters: 706k
Form fill: one 50 ms pass

Vincent Wang-Maścianica

@vinnylarouge

I reverse-engineered a jev-like architecture given its type. You can find the repo here to train your own jevlikes: github.com/vinnylarouge/j…

GitHubOpen source

jevlike

Eric Zhang

@ekzhang1

Inspired by @typesafeai , here is a Jev-compatible public API to play with It runs a comparable open model (Qwen3.6-35B-A3B), and just uses SGLang radix cache to preserve the prefill reuse / really fast parallel systemone generation - 64 tasks in <1s. github.com/ekzhang/openje…