Docs
CommunityJev Tools & CLIs
jevclient (PyPI)
The PyPI page for jevclient 1.3.1, an independent async Python client for TypeSafe Jev: typed Noul, Choice, Score and Box questions batch into one request, with image assets, billing tables and error classes documented in the README.
- Format
- Docs
- Reading time
- 3 min
- Published by
- Community
- Author
- AboveColin
- Last verified
- Oct 2026
Highlights
- Version 1.3.1; requires Python 3.12 or newer and aiohttp; installs with pip install jevclient.
- Four question types: Noul (probability of yes), Choice, Score and Box (image location); a Noul carries no confidence.
- Batching is nearly free in time: 3 questions answered in 712 ms and 400 in 1,336 ms, measured from the Netherlands on 2026-09-17.
- Image part of a request costs 2 x ceil(width/28) x ceil(height/28) tokens; sides must be 280 to 1568 px or the API returns 400.
- Box needs Jev 1.14; images work on 1.13 too, and an asset no string refers to is refused locally before a request is spent.
Quickstart
bash
pip install jevclientWatch out
Page text fetched 2026-10-17; the PyPI project page itself served a client challenge, so this entry rests on the metadata and README recovered in the supplemental fetch (version 1.3.1, requires_python >=3.12, author and licence undeclared). Latency and image-token figures are the README's own measurements on the dates it names. The README says the client is independent and not affiliated with TypeSafe, and links GitHub Sponsors for abovecolin.
Questions about this entry
Short answers drawn from the linked project or page.
An async Python client for TypeSafe Jev, the System One decision model, published on PyPI as version 1.3.1. Jev answers typed questions about a state and returns values, so there is no text to parse; the README states the client is independent and not affiliated with TypeSafe.
pip install jevclient. It requires Python 3.12 and aiohttp, and it can use your own aiohttp.ClientSession if you have one, in which case closing it stays your responsibility. Base URL and model are configurable on the client.
Four: Noul for yes/no questions returning the probability of yes; Choice for one of your options with probabilities and confidence; Score against ordered levels with a weighted score; and Box for where something is in an image. A Choice takes 2 to 255 options and a Score 2 to 10 levels, checked locally.
Pass images in assets keyed by a reference string and write the reference where the image belongs, in the state, an instruction or a criterion. The client sends a danger-zone header only when a request has an image or Box, and Box requires Jev 1.14 or jev-preview; on 1.13.0 the API answers 400.
Every question in a call is evaluated in isolation against the same state and answered in parallel: measured latency was 712 ms for 3 questions and 1,336 ms for 400, with warm connections at 250-580 ms. Question text is billed as input tokens, about 38 for a short question, and output is billed at zero.
Through typed exceptions: JevAuthError (401), JevValidationError (400, 413, 422), JevRateLimitError (429, carrying retry_after), JevOverloadedError (529) and JevConnectionError, all deriving from JevError. There is no internal retry loop, so the caller sets the policy, and errors from an HTTP answer carry their status.
Yes: base_url points the client away from https://api.typesafe.ai and model names which model to ask, with /v1/systemone appended to the base URL so a path prefix is kept. An empty api_key sends no Authorization header for endpoints that need no credential.
More Jev resources like this
An independent open-source pipeline that gives Jev vision: it detects and tracks objects in images, video, and RGB-D camera feeds, then asks Jev a typed question about each relevant object and prints the chosen answer with its confidence.
Jev Tools & CLIs#community#github#python
Community
CharlesFeng0314/JEV_seesPython
CharlesFeng0314/JEV_seesPythonA desktop AI assistant with a Jev / System One inline plugin for classification, routing, verification, and scoring without chat-style output.
Jev Tools & CLIs#community#python#desktop
Community
szczyglis-dev/py-gptPython
szczyglis-dev/py-gptPythonA local workbench that pairs OpenCV vision with Laya or Jev decision models: images are segmented and measured, hard rules settle the numbers, and the model gives the verdict — with one-click installers and an "open-source JEV" training path served at /v1/systemone.
Jev Tools & CLIs#community#github#python
Community
uu889/laya-opencvPython
uu889/laya-opencvPythonA 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/vibecheckPythonToolkit, knowledge base and local dashboard for building with Jev via OpenRouter Alpha Decisions or the TypeSafe Direct API: a zero-dependency SQLite request log, a localhost REST server and Python CLI demos.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
rileycarney/jevtoolsHTML
rileycarney/jevtoolsHTMLA 2.4 GHz WiFi site-survey instrument built on a ZimaBoard 2 and an Alfa USB adapter: Python and Scapy turn captured 802.11 frames into structured RF telemetry, and Jev reads each measurement window through OpenRouter to return coverage, congestion and optimization decisions.
Jev Tools & CLIs#community#github#wifi
Community
ronibandini/jevwifianalyzer-Python
ronibandini/jevwifianalyzer-PythonFrom 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.