NanoJev

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

End-to-end Jev-style structured-decision stack for auditable data construction, Qwen3.5-0.8B training, fixed Mind2Web and OOD evaluation, preliminary RLCD, local serving, and interactive replay.

Independent Jev-style replica with head training: a frozen Qwen3-1.7B backbone plus a small trained decision head returns calibrated Choice/Boolean/Score distributions in one forward pass, with committed datasets and a same-backbone generation benchmark.

Typed semantic decisions for Unix pipelines and CI, powered by TypeSafe AI Jev.

完全本地的 NanoJev 网格决策游戏实验场，支持中文 Pygame、多关卡与 GTX 1660S 训练

Dynamic, confidence-aware Agent Skill routing with TypeSafe Jev and Tink

Open replica of TypeSafe's Jev: typed calibrated decisions in one forward pass, on Gemma 4 E2B / Gemma 3 270M (Modal)

Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating)

Three composable judgment pipelines on TypeSafe's Jev: support-ticket triage, observability alert triage, and a deploy-risk gate.