Skip to content
JevDirectory.org
CommunityRepos & SDKs13 starsVerified 2026-09-22

jevframe

A Python library that adds .jev accessors to pandas and Polars: ask a natural-language question per row and get labels, scores, and full probability distributions back.

Open github.comktaletsk/jevframe
Category
Repos & SDKs
Published by
Community
Author
ktaletsk
Added
2026-09-22
Tagscommunitypythondatapandaspolarsclassification

Highlights

  • df.jev.noul, choice, score, and evaluate run per-row questions and return ordinary Series and DataFrames.
  • Choice and Score results carry complete probability distributions as p__ columns, and evaluate prefixes fields by question name.
  • Row order and pandas indexes, including duplicates and MultiIndexes, are preserved, and the input is never mutated.
  • Row concurrency is bounded, and responses can be cached in memory and reused across calls.
  • score returns the expected zero-based level rather than a probability, and no result is thresholded or renormalized.

Quickstart

python
import pandas as pd
import jevframe.pandas

df["dissatisfied"] = await df.jev.noul(
    "Is this customer dissatisfied?",
    state=["title", "review"],
)

topics = await df.jev.choice(
    "What is the main issue?",
    choices=["billing", "bug", "other"],
    state="review",
)

Watch out

MIT-licensed. v0 covers eager pandas and Polars only, not LazyFrame expressions; every uncached row sends its selected context to TypeSafe and needs a key.

More like this

Laya
14.3kGitHub stars
Open multilingual System 1 decision models with published checkpoints for choice, score and noul questions, plus a router that dispatches each request to the right checkpoint in one forward pass.
Repos & SDKs#community#python#open-models
Communitylaya
Simple Jev Project
475GitHub stars
A local server and Python package that runs open models with Hugging Face Transformers or PyTorch and returns Choice, Score, and Noul answers read from next-token logits instead of generated JSON.
Repos & SDKs#community#python#open-models
Communitysimple-jev
Von
425GitHub stars
An open, non-autoregressive System One model with published weights and a TypeSafe-compatible /v1/systemone API; the 395M-parameter OptionMarker checkpoint scores discrete and ordinal questions locally.
Repos & SDKs#community#python#open-models
Communityvon
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

A really smart switch statement

Nathan Flurry 🔩
Nathan Flurry 🔩
Rivet
@NathanFlurry
·

hype-free explanation of jev: jev does not replace gpt / claude jev is just a *really* smart switch statement like if 2016 ml classifiers got 2026 levels of intelligence it's a new* type of tool that will make a lot of workloads insanely fast, cheap, and accurate * = and by Show more

Diogo Almeida
Diogo Almeida
TypeSafe AI
@CompleteSkeptic

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

Watch on X
Reply
Read 230 replies

When a designer gets Jev

Full Jev video tutorial

The case against Jev-scored compaction

Theo - t3.gg
Theo - t3.gg
@theo
·

This is a terrible compaction strategy that fundamentally doesn't understand how compaction and context management work. Seems like a lot of people are confused so let's break this down. 1. Compaction isn't a filter The role of compaction is to clean up history to keep the Show more

tamara
tamara
@tamarajtran

found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant

Watch on X
Reply
Read 182 replies

Classifying rows in DuckDB

A playable 16-judgment demo