dan is a Python library and server that turns any open-weight causal LM into a System One model with a Jev-compatible API, reading label-token probabilities in a single prefill. It includes calibration and LoRA training tools.
该仓库明确实现 Jev-compatible System One 模型推理服务，提供 Jev API 兼容的 /v1/systemone 端点，并支持 TypeSafe SDK 连接，与 TypeSafe AI 的 Jev / System One 模型直接相关。
TypeSafeAITypeSafeAI/jev-harnessOfficialTypeSafeAI community repository implementing a Jev-based proposal-review workflow: an LLM proposes, Jev answers four narrow questions, code decides and leaves receipts; includes offline tests, routing experiments and a Next.js demo.
ekzhangekzhang/openjev-sglangJev-compatible API endpoint based on open models (prefill-only), implementing TypeSafe Jev/System One evaluation endpoints with Qwen3.6-35B-A3B on SGLang.
keltokhykeltokhy/jgrepjgrep is a CLI semantic grep that calls TypeSafe's Jev/System One decision model to judge lines or diff hunks by description, returning probabilities instead of generated text.
