Jev in production › Model and agent routing

Jevstiller

Jevstiller distills a repeated Jev classification call into a local model over time; a demo shows the local model taking over after about 4,000 requests (tomerglick57).

Open on GitHub ↗

4,000measured, as published by the source
Use
Model and agent routing
Industry
AI infrastructure
Form
Open-source tool
Stage
Beta
Listed
2026-09-30
Found via
github
Repository
tomerglick57/Jevstiller
Stars
66
Forks
10
Last push
2026-10-10
Language
Python
License
Apache-2.0
Jevstiller screenshot
docs/media/proxy.gif in the tomerglick57/Jevstiller README, Apache-2.0; shown from GitHub.

The README opens with

Jev, distilled on the fly. Same call. Same answers. Your hardware.

Put Jevstiller in front of a repeated Jev classification call. At first every request still goes to Jev. From Jev's own answers — with their full probability distributions — it trains a small local model on your traffic, checks that the model agrees with Jev within a budget you set, and then answers most requests itself. Uncertain or novel input, and a permanent random audit slice, keep going to Jev.

Badge

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

Listed in Jev in production

Also used for model and agent routing