Open-source tool that uses TypeSafe AI's Jev (System One) model to score new arXiv papers against plain-English interests, producing a daily paper radar, RSS feed, and cost logs.
该仓库 README 多处明确提到 TypeSafe AI 的 Jev / System One 模型，实际调用其 API 对 arXiv 论文进行逐篇相关性概率评估，并提供 demo、calibrate 校准、GitHub Actions 自动运行、RSS 与成本追踪，属于真实集成而非空壳。
kylemclarenkylemclaren/jevqljevql is a CLI/SDK that adds Jev semantic predicates, choices, and scores to ordinary Postgres SQL. It calls TypeSafe AI's System One model via the Jev API and supports Go, TypeScript, Python, MCP, and HTTP.
frostneyfrostney/clean-code-reviewUses TypeSafe's Jev evaluation model through eve and the AI Gateway to judge every file in a pull request against Clean Code, then Luna writes the review. Includes a live Next.js web app, CLI scripts, and an MCP server.
vinibrslvinibrsl/gutGut is an Elixir library that maps subjective input to a fixed value and supports configuring the TypeSafe Jev evaluation model.
