A FIELD GUIDE TO JEV / VOL. 01

SMALL
DECISIONS.
BIG
POSSIBILITIES.

The best of Jev. Real projects, practical guides and ideas from across the internet.

1,195resources16languagesFind something
worth building.
IN THE SPOTLIGHT SOURCE: X
Gregor Zunic@gregpr07

Browser Use + Jev

Gregor Zunic's flight-search demo with a dynamic DOM action space.

Browser Use + Jev Explore this project

01 / A small decision engine. A whole new way to build.

114 resources / The collection

Reset filters

AI-assisted summaries and translations. Check original sources for context and performance claims.

adhyaay-karnwalGitHub

jev-chat

A chatbot from typed Jev decisions: hierarchical speculative decoding over System One probabilities.

Research & dataEnglish
SamuelSaccoGitHub

jev-exploration

Jev (TypeSafe) exploratory thread: claim audit, live demos, and runnable code.

Research & dataEnglish
keskuGitHub

jev-freeform

An observable raw-character chat experiment powered entirely by TypeSafe Jev Choice.

Research & dataEnglish
Abhishek RaiGitHub

open-spark-jev

A research project on GitHub uses Jev with Qwen3 models on an NVIDIA DGX Spark system.

Research & dataEnglish
AbdelStarkGitHub

jev-benchmarks

Probability-aware evaluation for typed decision models: calibration, selective risk, latency, and reproducible benchmarks.

Research & dataEnglish
olanotoluGitHub

jevbetter

A stronger one-pass scorer over a variable list of text options: hashed n-gram encoder, rival-aware attention, gated head, temperature scaling, benchmarked against jevlike.

Research & dataEnglish
myokoymGitHub

misereru-slide-jev

Ongoing Japanese research deck on Jev and System One models, maintained as Markdown slides.

Research & dataEnglish
wfzyxGitHub

von

The open-source System One decision model. Sub-15ms, non-autoregressive, local drop-in alternative to TypeSafe Jev.

Research & dataEnglish
shibadogcapGitHub

kyotsu-ai-bench

AI benchmark on Japan's 2026 Common Test: Jev vs luna-none vs luna-low (static dashboard).

Research & dataEnglish
bitnovusGitHub

jev-spam-eval

Zero-shot spam filtering with TypeSafe Jev Noul questions, compared with TF-IDF baselines.

Research & dataEnglish
MapikaGitHub

decider

One-pass typed decisions with calibrated probabilities (System One style model), fine-tuned from Qwen3.5-2B.

Research & dataEnglish
mithalouniGitHub

system-one-open

Open replica of TypeSafe's Jev: typed calibrated decisions in one forward pass, on Gemma 4 E2B / Gemma 3 270M (Modal).

Research & dataEnglish
zhihzGitHub

openjev (zhihz)

Local bilingual probability decisions from context, questions, and candidate answers. Independent research preview inspired by TypeSafe Jev.

Research & dataEnglish
genai-craftGitHub

openvons

Openvons (open-Jev): 有限選択肢に確率で答える判断層 — テキスト / 画像 / 日本語音声コマンド.

Research & dataEnglish
vercel-labsGitHub

ai-cli

Vercel Labs terminal CLI that can run Jev as the evaluation model for its evaluate command.

Research & dataEnglish
zhengxuyuGitHub

LitJev

A reproduction of Jev that turns any Qwen model into a fast decision model, serving the same /v1/systemone schema (Choice, Score, Noul) with no training and no generated answer text.

Research & dataEnglish
0xnairbGitHub

research_desk

TypeSafe Jev demonstration for new analyzation — experimenting with Jev for fast analysis of news and tickers.

Research & dataEnglish
AkashPriyadarshiiGitHub

jev-curate

High-throughput synthetic & pretraining dataset sifter powered by TypeSafe AI Jev (api.typesafe.ai). Stream, filter, and score Parquet & JSONL datasets at 1,500+ rows/sec using System One typed decisions (Choice, Score, Noul).

Research & dataEnglish

Privacy, on your terms.

Essential functionality works without analytics. Optional Google Analytics runs only with consent. We respect Do Not Track and Global Privacy Control. External X and YouTube embeds load only when you ask.