Jev in production › Model and agent routing

Quicksilver

Claude Code skill routes bulk judgment calls to Jev, cutting Claude tokens 86% and running up to 20x faster across a 12-task benchmark (Quicksilver).

Open on GitHub ↗

86%measured against a baseline, as published by the source
Use
Model and agent routing
Industry
Developer tools
Form
Open-source tool
Stage
Announced
Plugs into
Claude Code
Listed
2026-09-26
Found via
github
Repository
UditAkhourii/quicksilver
Stars
120
Forks
6
Last push
2026-09-25
Language
JavaScript
License
MIT

The README opens with

A big share of every Claude Code session is spent reading things only to decide whether they matter. Which of these 187 files handle auth? Which of these 3,000 log lines are real failures? Which of these 200 tickets are refund requests? Claude reads it all, pays for it all, and the context fills up with noise.

Quicksilver is a Claude Code skill that hands those calls to Jev, TypeSafe's System One model. Jev returns typed verdicts (yes/no, a label, a score) in about a second, for $0.042 per million tokens. Claude gets back a shortlist and spends its tokens on the thinking only it can do.

Badge

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

Listed in Jev in production

Also used for model and agent routing