Skip to content
JevDirectory.org
CommunityRepos & SDKs2 starsVerified 2026-09-22

jevclient

An async Python client for Jev with typed Noul, Choice, and Score helpers: questions batch into one request, and callers get probabilities, choices, and weighted scores instead of text to parse.

Open github.comAboveColin/jevclient
Category
Repos & SDKs
Published by
Community
Author
AboveColin
Added
2026-09-22
Tagscommunitypythonsdkclassification

Highlights

  • One call evaluates every question in isolation against the same state and answers in parallel; 400 questions took 1,336 ms with 15,417 input tokens.
  • Batching is nearly free in time: latency stayed near 700 ms from 3 to 100 questions, while question text is billed as input and output is billed at zero.
  • A Choice accepts 2 to 255 options and a Score 2 to 10 levels, both checked locally so a mistake costs no request.
  • Typed errors cover 401, 422, 429 with retry_after, 529, and connection failures, and the client has no internal retry loop.
  • Requires Python 3.12 and aiohttp, and is an independent client not affiliated with TypeSafe.

Quickstart

python
import asyncio
from jevclient import JevClient, Noul, Choice, Score
async def main():
    async with JevClient("YOUR_API_KEY") as jev:
        answers = await jev.ask(
            "The front door has been unlocked for 40 minutes.",
            {"warn": Noul("Should someone be warned?"),
             "area": Choice("Which area?", {"security": "Locks", "climate": "Heating"}),
             "urgency": Score("How urgent?", ["Ignore", "Today", "Right now"])},
        )
    print(answers["warn"].noul, answers["urgency"].score)
asyncio.run(main())

Watch out

MIT-licensed and not affiliated with TypeSafe. Needs Python 3.12 and aiohttp; batching keeps latency flat, but question text is billed as input tokens while output is free.

More like this

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
Jev email intent workflow
7GitHub stars
An async LangGraph workflow that sends a mocked email to Jev, receives a typed Choice between invoice and general, and routes it to a demo handler, with confidence and both label probabilities printed for inspection.
Repos & SDKs#community#python#agents
Communitytypesafe-jev-workflow
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
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

Security decisions that fit Jev

Kostas
Kostas
@Kostastsale
·

This made me rethink where AI actually fits into security engineering. For purely engineering work, forget about ChatGPT or Claude. TypeSafe AI just released Jev, and I think it’s going to change how we build AI into security workflows. Instead of asking an LLM to “investigate Show more

TypeSafe AI
TypeSafe AI
@typesafeai

we are officially out of stealth! join the frontier and get access to Jev on our website (link on profile)

Reply
Read 14 replies

A million judged questions

Inferring Jev's internals from 1,000 calls

iwashi / Yoshimasa Iwase
iwashi / Yoshimasa Iwase
@iwashi86
·

Jevの内部アーキテクチャを推測している技術記事(Jev’s Architecture Unmasked)からメモ。 ・本記事はJevのAPIを約1万回の呼び出して、内部構造を推測したもの ・従来の言語モデルを用いた分類やルーティングでは、トークンを1文字ずつ逐次生成するために膨大な無駄な計算コストが発生していた。 Show more

Reply
Read 2 replies

The open System One roundup

小墨同学
小墨同学
@xiaomovps
·

Jev 发布没几天，开源社区已经开始疯狂复刻了🔥 最值得推荐的五个模型： 1、Laya 421M：原生决策模型，支持 Mac 2、Decider-2B：最像 Jev，基于 Qwen3.5 3、NanoJev 0.6B：专门的 Decision Head 4、Reflex：Qwen3.5 + Direct Logits 5、System-One 4B：专门做概率校准 Show more

小墨同学
小墨同学
@xiaomovps

Jev 刚发布没几天，开源社区就出现了同款🔥 Decider-2B模型，是基于 Qwen3.5-2B 做了特殊调整 它和 Jev 模型是一样的 只做选择 评分和判断 不是文本类的 LLM 模型 但两者还是有几个明显区别： 1、模型 Jev：闭源 System One Model Decider：Qwen3.5-2B，约 1.9B 参数，Apache 2.0 开源 2、价格

Image
Reply
Read 6 replies

The launch post

Trading bot, one decision per block