Jev in production › SDKs and workflow integrations

vibecheck

Wraps Jev decision calls as plain Python functions (check, classify, label, score) returning calibrated probabilities with no prompt templating (vibecheck).

Open on GitHub ↗

The source publishes no measured number.
Use
SDKs and workflow integrations
Industry
Developer tools
Form
Open-source tool
Stage
In production
Listed
2026-09-25
Found via
github
Repository
jlowin/vibecheck
Stars
42
Forks
3
Last push
2026-09-24
Language
Python
License
none stated

The README opens with

vibecheck lets you drop decision models right into your Python code.

Decision models such as Jev are a new kind of AI model built for judgment calls. They answer typed questions (yes or no, pick one, rate on a scale) in a fraction of a second, for a fraction of a cent, with a probability attached to every answer.

vibecheck puts all of that one function call away. Each call returns a plain Python value, with no prompts to template, no text to parse, and no agents to configure:

Badge

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

Listed in Jev in production

Also used for sdks and workflow integrations