User repository on GitHub
if you're experimenting with jev it will be easier from here
- Forks
- 0
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.
CommunityJev Demos & Experiments
Jev Studio
Python kit pairing a Jev CLI for verify, screen, classify, extract, match, route, ask, find, rerank, compact, and batch with an MCP server exposing the Jev ruleset over stdio.
- Stars
- 16
- Language
- Python
- License
- MIT
- Published by
- Community
- Author
- utk2103
- Last verified
- Oct 2026
About this project
One-stop kit for playing with TypeSafe's Jev: MCP tools for Choice/Noul/Score, ready-made prompt libraries, and slash commands for every cookbook. jev — the CLI for TypeSafe's Jev decisions (verify, screen, classify, extract, match, route, ask, find, rerank, compact, batch). jev-studio — the MCP server that serves the Jev ruleset over stdio.
Quoted from the project's README. Read the full README.
Works forJev for Classification
Used inJev for Software & DevTools
- Languages
- Python
Highlights
- Eleven CLI verbs from verify and screen to find, rerank, compact, and batch over JSONL with bounded workers.
- Typed extraction with builtin email, phone, URL, amount, date, percent, and number plus custom regex wants.
- Machine-friendly outputs, field plucking, fail-on gates with exit 2, and @file, stdin, and dry-run inputs.
- MCP server with mode-aware prompts and read-only instruction tool plus model, auth, and config commands.
Watch out
Judgments are probabilistic and provider-dependent, so gate critical paths with --fail-on and exit codes rather than prose. Extraction proposes with regex before Jev picks, and config precedence is file, then env, then flags. 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.
Use verify for claim-against-evidence checks, screen for injection and boilerplate triage with pass, review, block, or skip, classify for labels, and find or rerank for retrieval. Each command has distinct outputs and fail-on conditions.
Yes. Every command speaks JSON, Markdown, JSONL, CSV, TSV, or tables, supports --pluck for one field, and exits 2 on matched --fail-on conditions, which fits CI gates and scripts.
It is a Python port of a TypeScript CLI rebuilt on the standard library with the same command surface and question shapes. Auth accepts stored keys, env vars, or OpenRouter and Cloudflare credentials.
Point an MCP host at the jev-studio command over stdio. It serves a jev prompt in lite, full, or ultra modes plus a read-only instructions tool for hosts that pull context via tools.
`pip install jev-studio` installs two commands, the jev CLI and the jev-studio MCP server. Authenticate with any one of `jev auth login` to store the key in the OS keychain, TYPESAFE_API_KEY, OPENROUTER_API_KEY, or CLOUDFLARE_API_TOKEN plus CLOUDFLARE_ACCOUNT_ID, first found wins, then run `jev auth status` to inspect what is live.
Code 0 means the command completed with no --fail-on condition matched, 1 means a usage, configuration, input or transport error, and 2 means a judgment condition matched, such as a contradicted claim or a blocked injection. The 2 code is what makes it usable as a CI gate.
Builtins cover email, phone, url, amount, date, percent and number, and custom patterns use the form `name=/regex/:description`. Regex proposes candidates, Jev picks among them, and code normalizes the result, so extraction stays typed rather than free-form.
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.