by TianyuCodings · Agent Tool · ★ 2.6k
NanoJev — A nano replica of Jev English | 简体中文 A 0.6B parallel decision model. States and questions in, complete probability distributions out—with zero output-token decoding. Model · Dataset Open the live side-by-side demo → Three models, one game Download the maze video (MP4) · 27 seconds · 1440 × 1120 · 30 fps Play Snake · Explore the 50×50 maze · Recorded sources and replay checks The standalone ChatGPT Sites demo presents Jev, NanoJev, and Untuned Qwen in three light panels. Playback advances by the same environment step across panels; completed runs freeze at their actual final state.
| Stars | 2,559 |
| Forks | 263 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 59.902743168504/100 |
| Open Issues | 9 |
| Last Updated | 2026-10-16 |
| Created | 2026-09-17 |
| Platforms | python |
| Est. Tokens | ~16k |
These tools work well together with NanoJev for enhanced workflows:
Explore other popular agent tool tools:
NanoJev is A nano replica of Jev: parallel decisions, dynamic candidates, and an end-to-end training pipeline.. It is categorized as a Agent Tool with 2.6k GitHub stars.
NanoJev is primarily written in Python.
You can find installation instructions and usage details in the NanoJev GitHub repository at github.com/TianyuCodings/NanoJev. The project has 2.6k stars and 263 forks, indicating an active community.
NanoJev is released under the MIT license, making it free to use and modify according to the license terms.