A2T integrates TypeSafe AI's Jev (System One) as an independent judge to cross-check its deterministic graders; methodology and results are in docs/jev.md. The repo benchmarks, simulates, and scores agent trustworthiness via evidence-based credit scores.
仓库 README 明确包含 'Judge cross-check — powered by Jev (TypeSafe)'，并提供 docs/jev.md 说明方法、结果和复现步骤；topics 也包含 jev、typesafe。因此真实集成并研究了 TypeSafe Jev / System One。
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.
