Standalone TypeSafe Jev code-review CLI: typed decisions over a local git diff.
Applications — page 36
Complete applications where Jev makes a product decision: routing, ranking, classification or approval.
2,602 active projects in this collection. All collections →
Recursive semantic file search using TypeSafe Jev and fzf
Real-time Tetris versus Jev, a TypeSafe decision model — spins, garbage, B2B chains, and decisions prefetched a piece ahead
No project description available.
No project description available.
No project description available.
Turn any word into probability distributions over taste, material, scent, and shape. Powered by Jev.
1
JevCode — Jev (TypeSafe System One) 技术解决方案与最佳实践 · https://www.jevcode.ai
1
Ask typed questions about a text and branch on the answer. A shell front end for TypeSafe's Jev.
Open-source projects that provably call Jev, TypeSafe AI's System One model. Every entry links to the line of code that proves it. Refreshed daily.
No project description available.
TypeSafe AI's first model Jev takes on an entire city's traffic
Every email accounted for. Every expected shipment answered for.
A small detective escape room built with TypeSafe Jev, React, and Express.
1
Long inputs for TypeSafe AI's Jev decision model. An experiment.
A beautifully minimal Magic 8 Ball powered by Jev from TypeSafe. Twenty classic answers, one fast AI judgment.
1
Ask the map anything. Every place answers with a probability. OpenStreetMap + Mapillary + TypeSafe Jev + Cactus Needle.
Node client for decision models such as Typesafe Jev
Optional typed TypeSafe AI Jev decisions for OpenClaw, with SecretRef credentials and strict API validation.
open-Jev LM arm: Qwen2.5-0.5B + LoRA reproducing a hosted decision model's judgment at 92.9% on hand-labelled gold - trained overnight on a 6-vCPU CPU-only host, $0/call. Paper, corpora, harnesses, receipts.
Jev decides what to keep. Compaction never rewrites the transcript.
1
Semantic PR gate: .jev.yml rules as TypeSafe Jev questions. Not a review bot.
1
X 时间线清洁工 · FeedSieve(MIT) 衍生 · 带实测标定的 AI 判定层：误杀 0.7%，还能抓词库认不出的 47%
X（旧Twitter）のタイムラインから誹謗中傷を取り除く Chrome 拡張。判定を TypeSafe の System One モデル Jev で行う。