Back to benchmarks & research
nanojev-arena project preview
Benchmarks & research

nanojev-arena

NanoJev Snake Arena: 1v4 human-vs-AI battleship + 100-agent swarm simulator. Local demo of Jev System-One model (open-source mini replica).

Explore repository

How it uses Jev

模型不生成任何文字——一次前向直接输出所有候选动作的完整概率分布,蛇头上悬浮的概率条就是它"此刻的想法"。本项目是 NanoJev(Jev "System One Model" 的 0.6B 开源复刻)的本地游戏演示。

Languages
HTML 91% · Python 9%
License
MIT
Last activity
Sep 2026
Added
2026-09-21
Stars at snapshot
6
Status
Community listing

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

  • SemIf project preview
    Benchmarks & research

    SemIf

    Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.

    Python 2,775Details
  • jev-eval-agent project preview
    Benchmarks & research

    jev-eval-agent

    Personal-assistant agent built on Vercel's eve with 100 mocked tools, measuring how many steps it takes when Jev picks the tool versus the LLM.

    HTML 99Details
  • typesafe-ai-benchmark project preview
    Benchmarks & research

    typesafe-ai-benchmark

    This is a LLM Gateway that mimics typesafe ai structured output. Like an imposter Jev.

    TypeScript 33Details
  • jev-on-a-laptop project preview
    Benchmarks & research

    jev-on-a-laptop

    Unofficial study: Jev-style parallel typed decisions on stock 1.5B-8B models on an Apple Silicon laptop. Benchmarks, research notes, and a Hugging Face Space demo.

    Python 23Details
  • open-jev (JoshuaSP) project preview
    Benchmarks & research

    open-jev (JoshuaSP)

    Typed JSON inference with DiffusionGemma, with Every and Jev benchmark results

    Python 21Details
  • openvons project preview
    Benchmarks & research

    openvons

    openvons (open-Jev): 有限選択肢に確率で答える判断層 — テキスト / 画像 / 日本語音声コマンド

    Python 12Details