Jev in production › Model and agent routing

Gatekeeper

Answers which handler owns a request as a typed Choice with confidence bands using Jev, after simple requests are routed directly by rules, inside a Claude Code hook (Gatekeeper).

Open on GitHub ↗

The source publishes no measured number.
Use
Model and agent routing
Industry
Developer tools
Form
Open-source tool
Stage
In production
Plugs into
Claude Code
Listed
2026-09-25
Found via
github
Repository
AgriciDaniel/gatekeeper
Stars
20
Forks
3
Last push
2026-09-23
Language
Python
License
MIT

The README opens with

Gatekeeper decides which AI agent or skill should handle a request, before your AI picks one. Commands you type go straight through; the plain requests, where the AI would otherwise guess, get checked by your rules and judged by Jev. Each decision costs a fraction of a cent and takes about half a second.

The engine and rulebooks are tool-neutral. Today it installs as a Claude Code hook.

A gate is a YAML rulebook. Code decides what code can decide (slash commands, keywords, field checks). Jev, TypeSafe's System One model, answers the one semantic question left ("which of these handlers owns this request?") as a typed Choice with a probability for every option. Confidence bands then turn that answer into a verdict:

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for model and agent routing