⬢github Python · 2.3K ★ +4 since we first saw it · pushed 5 d ago · MIT
TianyuCodings/NanoJev
A nano replica of Jev: parallel decisions, dynamic candidates, and an end-to-end training pipeline.
NanoJev is a small open-source Python replica of Jev, a 0.6B 'parallel decision' model. Instead of decoding tokens, it takes game states and questions and directly outputs probability distributions over 2–255 candidate choices. The repo includes an end-to-end training pipeline, datasets, and a single checkpoint that plays ViZDoom, Maze, and Snake.
Why now: A recent update (Sept 20, 2026) showed one checkpoint beating the original Jev on ViZDoom benchmarks, with side-by-side browser replays comparing NanoJev, Jev, and untuned Qwen — driving attention on trending repos.
Who it is for: ML researchers and hobbyists interested in token-free decision models, RL-style game-playing agents, and training such systems from scratch.
Stars over our 15 snapshots: 2.3K to 2.3K, since 1 h ago.
Where people talked about it
- ⬢github new repos, most starred 3 min ago
API: https://socialmediatrends-api.osmike.com/v1/repos/TianyuCodings/NanoJev