User repository on GitHub
Async Python client for TypeSafe Jev. Typed questions in, probabilities and choices out, no prose to parse.
- Forks
- 1
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.Homepage
Jev directory
CommunityJev Repos & SDKs
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.
- Stars
- 2
- Language
- Python
- License
- MIT
- Reading time
- 3 min
- Published by
- Community
- Author
- AboveColin
- Last verified
- Sep 2026
About this project
Async Python client for TypeSafe Jev, the System One decision model. Jev answers typed questions about a state and returns values, so there is no text to parse. A Noul carries no confidence, because the probability is the whole answer. Every question in a call is evaluated in isolation against the same state, and the API answers them in parallel. Measured from the Netherlands on 2026-09-17:
Quoted from the project's README. Read the full README.
Works forJev for Scoring
Used inJev for Software & DevTools
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.
Questions about this entry
Short answers drawn from the linked project or page.
It adds typed Noul, Choice and Score wrappers, local validation and typed errors. A Choice accepts 2 to 255 options and a Score 2 to 10 levels, both checked before a request so a mistake costs nothing. Errors map to JevAuthError, JevValidationError, JevRateLimitError with retry_after, JevOverloadedError and JevConnectionError.
Time, no; tokens, yes. Questions in one call are evaluated in isolation against the same state and answered in parallel: 3 questions took 712ms, 100 took 714ms, and 400 took 1,336ms with 15,417 input tokens. Question text is billed as input at roughly 38 tokens for a short question, while output is billed at zero.
No, there is no internal retry loop, so JevRateLimitError carrying retry_after reaches you and the caller decides the policy. If you pass your own aiohttp.ClientSession the client uses it and leaves closing to you, otherwise the async context manager owns the session.
Yes. base_url swaps the host and the client appends /v1/systemone to it, so a path in the base URL is kept as a prefix, and model names what to ask. An empty api_key sends no Authorization header, which suits an endpoint that asks for no credential. Requires Python 3.12 and aiohttp.
Python 3.12 and aiohttp. You can pass your own aiohttp.ClientSession and the client will use it and leave closing it to you; otherwise the async context manager owns the session.
A Noul returns noul, the yes probability with no separate confidence; a Choice returns choice, probabilities and confidence; a Score returns score, legend, probabilities and confidence.
The README's cold first calls run 690 to 1,336 ms, but over 16 calls from the same location a warm connection answered in 250 to 580 ms, so connection reuse matters more than question count.
More Jev resources like this
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.
Jev Repos & SDKs#community#python#open-models
Community
featherless-ai/simple-jevPython
featherless-ai/simple-jevPythonOpen 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.
Jev Repos & SDKs#community#python#open-models
Community
NandhaKishorM/layaPython
NandhaKishorM/layaPythonAn Apache-licensed System One decision server that reads Choice, Score, and Noul probabilities from DiffusionGemma 26B-A4B through vLLM on NVIDIA or MLX on Apple silicon, so TypeSafe SDKs work unchanged.
Jev Repos & SDKs#community#python#open-models
Community
razorback16/openjevPython
razorback16/openjevPythonA DSPy fork whose @typesafeify decorator routes decision-shaped signature fields to Jev, so bool, Literal, and scored outputs come back typed while freeform fields still use the LM.
Jev Repos & SDKs#community#python#sdk
A Python library that turns Jev-style decision models into ordinary function calls: check returns a bool, classify picks one option, label picks every option that applies, and score rates on a scale, with probabilities behind every answer.
Jev Repos & SDKs#community#github#python
Community
jlowin/vibecheckPython
jlowin/vibecheckPythonA reproduction of Jev that turns any Qwen checkpoint into a decision model serving the same /v1/systemone schema (Choice, Score, Noul), with no training and no generated answer text.
Jev Repos & SDKs#community#python#open-models
Community
zhengxuyu/litjevPython
zhengxuyu/litjevPythonFrom the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.