jevwire

Repository description

The repository describes its purpose as: Jev decision layer for agents: MCP server, embeddable DecisionModel library, and an escalate-only Claude Code plugin (TypeSafe AI's Jev)

Source evidence

The daily check found an explicit Jev / TypeSafe AI connection in the original README and implementation files at the same commit.

**Jev** is TypeSafe AI's [System One](https://docs.typesafe.ai/concepts/system-one) model: a fast, calibrated classifier. You give it a state and a map of typed questions — yes/no, pick-one, rate-on-a-rubric — and it answers every one in parallel with a probability over the answer space *you* defined. It never generate

Automatically source-checked: public repository, pinned README, and implementation files. Not run, benchmarked or security-audited.

How automated checks and editorial selection work