User repository on GitHub
Grill-me with Jev optional each turn
- Forks
- 1
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
CommunityJev Demos & Experiments
Jev Me
Small skill that grills a plan as a design-tree interview, using Jev ad hoc for typed judgments during the session.
- Stars
- 14
- License
- MIT
- Published by
- Community
- Author
- jon-devlapaz
- Last verified
- Oct 2026
About this project
Grill a plan as a design-tree interview. Jev is ad hoc for typed judgments. Type /jev-me. Export TYPESAFEAPIKEY for Jev.
Quoted from the project's README. Read the full README.
Works forJev for Classification
Used inJev for Software & DevTools
- Languages
- Python
Highlights
- Design-tree interview flow for grilling a plan with ad hoc typed judgments.
- Installs through a single skills add command, then runs via a slash command.
- Uses an exported Jev API key for its judgments.
- MIT-licensed skill with a deliberately tiny documented surface.
Watch out
The repository README is only a few lines: it names the install command, the slash command, and the API key, with no detail on prompts, models, or options. Copy reviewed against the repository README on 2026-10-04, not from running it.
Questions about this entry
Short answers drawn from the linked project or page.
The README describes it only as a design-tree interview over a plan with ad hoc typed judgments, so expect an interrogation of the plan's structure rather than a generator, scorer, or autonomous reviewer.
No. The documented flow exports TYPESAFE_API_KEY for Jev, so plan on supplying a key before the typed judgments can run.
A plain assistant call returns prose you must parse yourself, while this skill routes plan questions through Jev's typed judgments inside the interview loop.
Run the single skills install command, invoke the slash command, and keep the key in the environment; there are no documented flags or setup branches beyond that.
Jev is called ad hoc for typed judgments during the session rather than pre-baked, so the interview asks for judgments as questions come up instead of relying on a fixed script.
MIT, and the skill is deliberately tiny: its README documents only the install command, the slash command and the API key, with no detail on prompts, models or options.
It is a Python skill installed through the skills CLI and run through the /jev-me slash command; the repository exposes no other documented options or setup branches.
More Jev resources like this
46GitHub stars
Open 150M encoder that reproduces the typed noul, choice, and score interface in one forward pass, trainable on a free GPU and runnable locally for nothing.
Jev Demos & Experiments#community#jevbest#catalog-import
941GitHub stars
Library that adds schema-guaranteed typed outputs to existing autoregressive LLMs without changing weights, served through SGLang or a hosted API.
Jev Demos & Experiments#community#jevbest#catalog-import
Community
TypeLLM/TypeLLMPython
TypeLLM/TypeLLMPython55GitHub stars
Toolkit that makes a model behind an OpenAI-compatible endpoint or running in-process answer typed choice, score, and yes/no questions from next-token probabilities in Jev API shape.
Jev Demos & Experiments#community#jevbest#catalog-import
Community
fidecastro/jevifyPython
fidecastro/jevifyPython164GitHub stars
End-to-end toolkit that synthesizes decision data, trains and calibrates candidate scorers, evaluates fixed splits, and serves Jev-compatible inference for interactive web decisions.
Jev Demos & Experiments#community#jevbest#catalog-import
Community
zwliJay/jev-forgePython
zwliJay/jev-forgePython70GitHub stars
Self-hosted proxy that records typed decisions, distils them into small heads on a frozen encoder, and answers locally when confident.
Jev Demos & Experiments#community#jevbest#catalog-import
Community
bladedevoff/stuntdPython
bladedevoff/stuntdPython42GitHub stars
Open harness that renders allowed JSON answers on a diffusion canvas, denoises for a fixed step budget, then picks the top allowed tokens from final logits with no training.
Jev Demos & Experiments#community#jevbest#catalog-import
Community
JoshuaSP/open-jevPython
JoshuaSP/open-jevPythonFrom the Jev guides
Original write-ups on what this entry is for.
A game tick is a state plus a legal action list. How Clash Royale, Minecraft, and the earlier Mario, Pokémon, StarCraft, and drone loops ask Jev one step at a time.
Jev Demos & Experiments#gaming#agents#control
Read article
From the Jev community
Posts from builders shipping with Jev right now.