Submit a project
construct-auto-classifier
By godspede
Source description: 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.
Repository description
The repository describes its purpose as: 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.
Source evidence
The daily check found an explicit Jev / TypeSafe AI connection in the original README and implementation files at the same commit.
- **`"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
Automatically source-checked: public repository, pinned README, and implementation files. Not run, benchmarked or security-audited.
