jev-kit

Everything you need to run TypeSafe's Jev with Claude Code:
guard your agent's tool calls, right-size its sub-agents, and wire Jev into search, browsing, review and more.

Quickstart · What is in the kit · How it works · Measured results · Safety · FAQ

What is Jev, and why a kit

Jev is a TypeSafe System One model. It does not return text. It returns a typed decision -- yes or no, a choice, a score -- with a probability attached, in roughly 0.3 s, for a fraction of a cent. That is fast enough and cheap enough to sit inside an agent's loop as a judge rather than beside it as another chat.

A kit, because the judge is the easy part. The work is the places it pays off: which tool call to question, which sub-agent rung a task needs, what to redact before sending, and how to fail open when no answer arrives. This repository is that