User repository on GitHub
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Cookbooks
Jev decision-model share pack (Chinese)
A Chinese-language share pack on Jev and decision models: two long-form documents, eleven runnable Python examples, a live-demo notebook and a slide deck, covering the three primitives, batch calls, a confidence gate with LLM fallback and Chinese evaluation.
- Stars
- 0
- Language
- Jupyter Notebook
- Reading time
- 2 min
- Published by
- Community
- Author
- jpegbert
- Last verified
- Oct 2026
- Languages
- Python
- Capabilities
- Open sourceRuns locally
Highlights
- Contains two document versions covering the model, the open-source ecosystem and internal adoption, plus code/ with 11 Python files and requirements.txt.
- Examples cover the three primitives, batch parallel questions, a confidence gate with LLM downgrade, dish matching and a Chinese evaluation.
- systemone_client.py is a general /v1/systemone client with real HTTP calls and an offline mock, so the examples run without a key.
- Real-model options: SYSTEMONE_BASE_URL for a local Laya server, or TYPESAFE_API_KEY for TypeSafe's hosted Jev cloud.
- Includes notebooks/JEV_live_demo.ipynb and a presentation deck, Jev: 10 usage scenarios, referenced by the documents.
Quickstart
bash
cd code
pip install -r requirements.txt
python 01_basic_primitives.pyWatch out
README reviewed 2026-10-17 from the round-eleven capture, which is truncated in the code index: the repository declares no licence, the evaluation results and notebook outputs are not in the digest, and all documents are written in Chinese.
Questions about this entry
Short answers drawn from the linked project or page.
A Chinese-language share pack about Jev and decision models, aimed at internal team sharing: long-form documents, a slide deck, eleven runnable Python examples and a live-demo notebook.
The three primitives, batch parallel questions on one state, a confidence gate with LLM downgrade, dish matching, a Chinese four-dimension evaluation and a general /v1/systemone client.
Yes. The client falls back to an offline mock so the data structures run through, and the README says the no-key path works; the live demo notebook reuses the same code.
Two documented options: set SYSTEMONE_BASE_URL to a local Laya server, or set TYPESAFE_API_KEY to use TypeSafe's hosted Jev cloud.
A pattern where a low-confidence decision is downgraded to an LLM call, listed in the code index as 03_confidence_gate.py. The digest does not include its measured behavior.
Chinese. The documents, the presentation and the notebook are written in Chinese, and the README's quick-start comments use Chinese labels for the example scripts.
No licence is declared, the digest truncates the code index, and evaluation results are not captured. The repository has 0 stars and was last pushed on the same day it was created, 2026-10-11.
More Jev resources like this
Six 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
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.
Jev Cookbooks#community#github#python
Community
ignitewala/system-onePython
ignitewala/system-onePythonA small, fast decision model — a system one model — for agentic workflows from Strands Labs: it picks between options or rates on a scale faster than an LLM and returns a calibrated confidence with every decision.
Jev Models & Reimplementations#community#github#python
Community
strands-labs/strands-deciderPython
strands-labs/strands-deciderPythonA minimal repository whose entire README is a two-step recipe for building your own Jev: download Qwen, then make Jev. It is a signpost for readers who want to assemble a System One-style decision model from an open base model.
Jev Cookbooks#community#github#python
Community
nishtahir/build-your-own-jevPython
nishtahir/build-your-own-jevPythonOne Python interface for evaluating what LLM apps and agents say and do. Its CascadeEvaluator asks a decision model first — Jev, OpenAI's Decisions API, or any model served at /v1/systemone — keeps confident answers, and sends only the rest to an LLM judge.
Jev Benchmarks & Evaluations#community#github#python
Community
grounded-ai/grounded_aiPython
grounded-ai/grounded_aiPythonA proof-of-concept HTTP service for constrained decisions with a local MLX model: send text or JSON plus typed choice, score, or noul questions and it returns probabilities over the answers you declared — no generated text, no parsed model JSON.
Jev Tools & CLIs#community#github#python
Community
snellingio/system-onePython
snellingio/system-onePythonFrom 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.