What it does

Simple Jev uses compatible Hugging Face models to classify and score inputs, constructing JSON answers from next-token logits instead of generating a completion.

Evidence 1 ↗

How Jev fits

It explores TypeSafe’s structured-decision interface with open models; it does not reproduce Jev’s architecture or training.

Evidence 1 ↗ · Evidence 2 ↗

Getting started

Send shared context as either state or messages, plus typed questions, to POST /v1/classifier on the configured server.

Evidence 1 ↗

Scope and limits

Its choice and score confidence values are not calibrated correctness probabilities. Matching the response format establishes neither Jev-equivalent quality nor speed.

Evidence 1 ↗ · Evidence 2 ↗

Repository description

Turn any open model into a classifier/jev endpoint

Project facts

Relationship to Jev
Local alternative
Evidence
Documented
Language
Python
License
Apache-2.0
Origin
Original repository
Repository status
Not archived
Created
2026-09-18
Last code update
2026-09-24
GitHub stars
561
Evidence checked
Sep 30, 2026
Metadata checked
Sep 28, 2026
Check status
Up to date

Stars measure the whole repository, including work unrelated to Jev.

Evidence and scope

Documented records the linked documentation or source. JevHunt has not independently run or benchmarked this project.

Evidence commit: c5363e0a2a9d22cb503e8e226daf6d2d5794e415

Discovered through: awesome-jev, typesafe-field-guide.

How we review →

Suggest a correction · Claim this listing · Submit a project