推荐项目
construct-auto-classifier
作者 godspede
原文简介（英语）：Effect-based safety gate for AI coding agents' shell commands (OpenCode, Antigravity): fast structural rules, then TypeSafe's Jev or a chat model judges what a command does. Certified with Jev at zero dangerous commands allowed.
仓库介绍
仓库作者的原文介绍（英语）：Effect-based safety gate for AI coding agents' shell commands (OpenCode, Antigravity): fast structural rules, then TypeSafe's Jev or a chat model judges what a command does. Certified with Jev at zero dangerous commands allowed.
收录证据
每日检查在原始 README 中找到明确的 Jev / TypeSafe AI 关联，并核对同一提交中存在实现文件。
- **`"jev"` (the default)** asks [TypeSafe's Jev](https://typesafe.ai), a System One model that writes no text and instead answers typed questions with calibrated numbers. The gate sends the command, plus any script it runs, as Jev's `state` and asks twelve questions in one call: - an `allow`/`deny` **choice**, describ
自动核对公开仓库、固定提交的 README 与实现文件；未运行、性能测试或安全审计。
