User repository on GitHub
All projects for learning Jev and other Decision (System-1) Models, a model that makes decisions instead of writing text.
- Forks
- 3
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Demos & Experiments
Jev Crash Course (AIAnytime)
Eleven small runnable projects for learning Jev and other System One decision models, each lesson pairing a one-command web demo with a whiteboard and README, from the three question types through jobs sorting and contract review to Jev inside a SQL query. Every demo makes live API calls.
- Stars
- 17
- Language
- Python
- Reading time
- 2 min
- Published by
- Community
- Author
- AIAnytime
- Last verified
- Oct 2026
- Platforms
- BrowserPlaywright
- Capabilities
- Open sourceRequires API key
Highlights
- Eleven lesson folders, each a web demo on its own port from 8001 to 8011, with a whiteboard explaining the idea and a README.
- Covers the three question types, where to use Jev, text analysis, calibration versus an LLM, contract review, Jev-in-SQL and prompt injection.
- Project 06 reviews a thousand rows inside a single SQL query; project 08 writes browser test assertions in English with Playwright.
- Setup is a venv plus pip install -r requirements.txt, then a .env with JEV_API_KEY (required) and OPENAI_API_KEY (only for projects 01, 04 and 09).
- Project 11 compares the hosted model against an open one you run yourself, and the README links a YouTube playlist walkthrough.
Quickstart
bash
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txtWatch out
README reviewed 2026-10-17; the digest truncates just after the Playwright chromium install line, so the closing setup steps and the per-project documents were not captured. The GitHub license shows as NOASSERTION, so reuse terms are unclear, and every demo calls the live Jev API (and OpenAI in three lessons), so running the course costs money.
Questions about this entry
Short answers drawn from the linked project or page.
Eleven runnable lesson projects from AIAnytime for learning Jev and other System One decision models, each folder holding a web demo on its own port, a whiteboard and a README. Nothing is simulated or recorded.
The three question types next to a language model, where to use Jev, six-questions-at-once text analysis, calibration head-to-heads, writing measurement, Jev-in-SQL, contract review, English-assertion browser tests, prompt injection and a game.
Python with a virtual environment, pip install -r requirements.txt, and a .env at the repo root with JEV_API_KEY (required) and OPENAI_API_KEY; the OpenAI key is only used by projects 01, 04 and 09 for their comparison lane.
One port per project, 8001 for 01-what-is-jev through 8011 for 11-jev-vs-laya, so several lessons can run side by side without conflicts.
Yes: project 08 needs python -m playwright install chromium, and the README says two projects need an extra step, though the digest captured only that one. Project 11 also compares against an open model you run yourself, so expect extra setup there.
The README states no pricing; every demo makes live API calls, so the Jev key is metered and projects 01, 04 and 09 also call OpenAI, meaning the normal API charges apply as you work through the lessons.
GitHub reports the license as NOASSERTION, so check reuse terms before copying the code; the README embeds a YouTube playlist walkthrough, whose list contents the digest did not capture.
Other listings of this project
Forks and copies of this project in the directory. This entry is the canonical one.
Eleven-level Jev course from hello-world to a ticket-triage capstone, pairing short lessons with runnable scripts against the live API and using LiteLLM so the writing half works with any provider.
Jev Benchmarks & Evaluations#community#github
Community
nadeemcite/jev-crash-coursePython
nadeemcite/jev-crash-coursePythonEleven-level Jev crash course from zero with runnable examples, LiteLLM write-half, and a ticket-triage capstone with tests and evals.
Jev Benchmarks & Evaluations#community#github
Community
nadyth/jev-crash-coursePython
nadyth/jev-crash-coursePythonMore Jev resources like this
A Python dispatcher skeleton for TypeSafe System One (Jev) that turns typed signatures into batched questions, plus a Playwright browser harness that measures the dispatcher against ground truth.
Jev Demos & Experiments#community#github#python
Community
monkey1sai/jev-systemone-labPython
monkey1sai/jev-systemone-labPythonA Streamlit lab that places a bounded System One decision inside a coding-agent workflow: Laya classifies CI failures, LangGraph applies a fallback policy, and an OpenAI agent inspects a fixture repo and proposes a fix.
Jev Demos & Experiments#community#github#python
Community
natenberenstein/systemonePython
natenberenstein/systemonePythonA small Python app that asks whether a headline is Onion-style satire or real news. Jev runs through TypeSafe's API with your own key and is compared side by side with AnyJev L0 and raw Qwen3-8B running locally, with an option to swap the answer order.
Jev Demos & Experiments#community#github#python
Community
andrisgauracs/onion-or-notPython
andrisgauracs/onion-or-notPythonThe Cua computer-use platform documents a jev-use recipe where TypeSafe Jev picks bounded action IDs and Cua Driver executes clicks and fills in the browser.
Jev Demos & Experiments#community#browser#computer-use
Community
trycua/cuaRust
trycua/cuaRustAn open-source browser 3D character split between two models: GPT-Live-1 talks with you over WebRTC while Jev reads the live transcript and picks Annie's face, gestures and body language in about 120 ms, with code gates on every answer.
Jev Demos & Experiments#community#github#python
Community
rehan-remade/open-anniePython
rehan-remade/open-anniePythonA Chinese-language e-commerce customer-service demo on FastAPI, LangGraph and React: adaptive retrieval routing with hybrid BM25-plus-vector search, and intent classification switchable between TypeSafe Jev's structured choice interface and DeepSeek.
Jev Demos & Experiments#community#github#python
Community
gbh1234/Adaptive-ragPython
gbh1234/Adaptive-ragPythonFrom 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.