User repository on GitHub
- Forks
- 9
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Cookbooks
DIY Jev
A 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.
- Stars
- 73
- Language
- Python
- Reading time
- 2 min
- Published by
- Community
- Author
- nishtahir
- Last verified
- Oct 2026
Works forJev for Code
Used inJev for Software & DevTools
- Languages
- Python
- Capabilities
- Open source
Highlights
- The whole README: a "DIY Jev" heading and two steps — "1. Download Qwen" and "2. Make Jev."
- GitHub metadata: 72 stars, 9 forks, Python, no license detected, created 2026-09-25, last pushed 2026-10-03.
- Discovered through a jev in:name,description search filtered to repos created after 2026-09-15, so the Jev connection is by name.
- The digest contains no code, commands, screenshots, or hardware notes beyond those two steps.
Watch out
README reviewed 2026-10-17: the groundable content is only the four-line excerpt plus GitHub metadata. No model weights, Qwen version, code, commands, license, or results are available in the digest; treat this entry as a signpost, not an implementation guide.
Questions about this entry
Short answers drawn from the linked project or page.
nishtahir/build-your-own-jev is a small Python repository whose README is titled "DIY Jev" and lists two steps: download Qwen, then make Jev. Beyond that the digest shows only GitHub metadata.
The README's two instructions are to download Qwen and make Jev; it does not include commands, code, or configuration. Anyone following it would be reassembling the approach from Qwen's own documentation.
The README says only "Download Qwen" — no version, size, or source is stated, and the digest contains no linked model card, so the base model choice is unspecified.
No evidence of that appears in the digest: there is no code, endpoint, key, or TypeSafe reference, just the name and the two-step recipe. It is a naming-level connection to Jev as a decision-model concept.
GitHub detected no license for the repository, per the digest metadata, so no usage terms are declared. The repo is public, but without a license you should not assume rights to reuse its contents.
nishtahir; the digest shows 72 stars, 9 forks, Python as the primary language, creation on 2026-09-25, and a last push on 2026-10-03, two weeks before this entry was verified.
Code, commands, a Qwen version, hardware notes, results, and a license are all absent from the digest. The README may grow, but as captured on 2026-10-17 this entry can only point at the repo and its metadata.
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
A hands-on lab that arranges thirty real uses of Jev into ten levels: levels 1–5 call Jev from plain code, and levels 6–10 run inside the pi coding agent, ending with an agent that writes its own Jev questions.
Jev Cookbooks#community#github#typescript
Community
disler/ten-levels-of-jevTypeScript
disler/ten-levels-of-jevTypeScriptA 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-samplesRunnable 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 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.
Jev Cookbooks#community#github#python
Community
jpegbert/JevJupyter Notebook
jpegbert/JevJupyter NotebookFrom 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.