Judge agent steps — ok / retry / escalate / stop via TypeSafe Jev
Jev ecosystem projects — page 96
5191 repositories with documented relationships and source evidence.
Hermes Home Vision - installation Hermes Agent multi-profils (3 profils isoles) sur Windows 11 : runtime, documentation, scripts de bootstrap et de restauration. Version courante : 1.3 (branche main, tag v1.3) ; versions precedentes 1.2 (v1.2-ameliorations) et 1.1 (v1.1-original).
HireSignal — resume first-pass fit+interview via TypeSafe Jev
Typesafe/Jev public X demo
Challenge Atari with Jev: structured decisions, value questions, and replayable experiments
Reproducible benchmark for TypeSafe AI's Jev on agent tool-call risk classification: accuracy, latency, and whether the confidence score is worth routing on.
Local browser automation UI that uses TypeSafe Jev to choose bounded page actions and a text model only for field values.
Jev-powered browser MCP for LLM agents — ~300ms decisions, no LLM tokens in the loop. Benchmark vs Playwright MCP included.
1
No project description available.
Jev Gamecast: replay-first React app that asks Jev typed questions about live sports data.
1
同じ発言を jev と LLM の両方に判定させ、感情の変動値のズレと応答速度を1画面で見比べるデモ（affectus + Vercel AI Gateway）
No project description available.
Typed, auditable Jev decisions for Python agents, with an optional shared runtime, offline previews, and calibration.
MoonBit client for Jev plus a Jev-vs-Jev gomoku match, with timing logs.
1
TypeSafe Jev MCP decision layer for coding agents and CI
1
Jev MCP Hub is a small Go gateway that exposes TypeSafe's Jev model through the Model Context Protocol.
1
Busca em arvore (MCTS/PUCT) com avaliacao tipada do TypeSafe Jev e portao humano obrigatorio. A arvore supoe, a sonda mede: marco so e concedido por codigo de saida verde.
Benchmarks Jev against other evaluation models in games with explicit states, legal actions, and measurable outcomes.
发明 RLHF 的人，这次做了个不会说话的模型：Jev 独立研究报告。52 页 PDF + 50 条中文实测复现包 + 143 条可回溯数据表
CV diagnostics and job alignment with TypeSafe Jev, React and FastAPI
A small second eval for shadcn-ui/lint that uses TypeSafe's Jev to judge the linter's own output.
TypeSafe's Jev model plays Snake live in the browser, with a headless eval and a self-improvement loop
1
Job Risk Analyzer: CLI and REST API that uses Jev to score an occupation's exposure to AI-driven layoffs and its resilience.
A visual TypeSafe demo where Jev chooses verified Tetris placements.