User repository on GitHub
System-one model evaluation and example
- Forks
- 0
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Cookbooks
system-one (ignitewala)
Runnable Python examples for Jev, TypeSafe's first System One model: the README explains the three typed question primitives — Choice, Score and Noul — gives a venv install for Python 3.10+ and is explicit that the model cannot chat or generate text.
- Stars
- 0
- Language
- Python
- License
- MIT
- Reading time
- 2 min
- Published by
- Community
- Author
- ignitewala
- Last verified
- Oct 2026
This is one of several Jev listings for the same project. The canonical entry is System One — iamaamir.
Used inJev for Software & DevTools
- Languages
- Python
- Capabilities
- Open sourceRequires API key
Highlights
- Runnable examples: send a state plus typed questions and Jev evaluates every question in parallel in one pass, returning typed answers with probabilities.
- The three primitives: Choice (pick one of my options), Score (place this on an ordered scale) and Noul (how true is this statement, 0 to 1).
- States the model's whole menu plainly: it decides, scores and routes; it cannot chat, generate text, write code or run an agent loop.
- Install is Python 3.10+ in a venv with requirements.txt: langchain, langchain-typesafe, langchain-openai, openai, python-dotenv and scikit-learn.
- A Keys section says to copy a template and fill it in; MIT licensed.
Quickstart
bash
git clone https://github.com/ignitewala/system-one.git
cd system-one
python3 -m venv .venv
source .venv/bin/activate
pip install --upgrade pip
pip install -r requirements.txtWatch out
README reviewed 2026-10-17 from the round-eleven capture, which is truncated inside the Keys section: the endpoint templates, the evaluation methodology behind scikit-learn and any results are not in the digest.
Questions about this entry
Short answers drawn from the linked project or page.
A Python repository of runnable examples and evaluation material for Jev, the first System One model from TypeSafe AI. The README walks through what the model is and how to call it.
You give it a state — a string or JSON — and a set of typed questions. It evaluates every question in parallel in one pass and returns typed answers with probabilities, so there is no string to parse or JSON to validate.
Choice asks it to pick one of your options and returns the chosen option plus a probability for each; Score places a value on your ordered scale; Noul returns how true a statement is as a float from 0 to 1.
The README is explicit: it cannot chat, generate text, write code or run an agent loop. It decides, scores and routes, and that is the whole menu.
Clone the repository, create a Python 3.10+ venv, activate it, upgrade pip and run pip install -r requirements.txt, which pulls langchain, langchain-typesafe, langchain-openai, openai, python-dotenv and scikit-learn.
The README shows a template env file to copy and fill in before running against Jev. The captured excerpt truncates there, so which variables the template expects is not in the digest.
Evaluation results. The repository description mentions evaluation and lists scikit-learn, but the digest stops before showing the methodology or any numbers; the repo has 0 stars.
More Jev resources like this
A community curriculum of Jupyter notebook recipes that teach typed decisions with Jev, TypeSafe's System One model. Each recipe takes one bounded Choice, Noul or Score decision over text or image state, spanning first classification through closed-loop control.
Jev Cookbooks#community#github#python
Runnable samples for Jev, TypeSafe AI's System One model: each sample sends state plus questions that carry their own answer options and then branches on the typed value returned, including a README checker and an AGENTS.md readiness scorer.
Jev Cookbooks#community#github#samples
Community
aarora79/jev-samples
aarora79/jev-samplesAn 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 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/vibecheckPythonSix small Python files that build one coding agent step by step on DSPy's RLM sandbox, with Jev answering closed questions — command safety, tool choice, history relevance, delegation — and plain Python owning the thresholds.
Jev Cookbooks#community#github#python
Two Jev demos over SprintPulse QA data: one scores release risk with a 10-level rubric evaluated against a reference score, the other diagnoses the main risk cause with a 9-label choice question, both sending the same per-ticket signals to Jev's System One API.
Jev Demos & Experiments#community#github#python
Community
avi350751/jev-qa-analyzerPython
avi350751/jev-qa-analyzerPythonFrom 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.