Applications for Jev — page 66
1810 repositories with documented relationships and source evidence.
Linter for source-code comments: grades accuracy and usefulness with TypeSafe Jev and deletes the useless ones
Seems: Python, plus judgment. A superset of Python where a condition can be plain English, answered by TypeSafe Jev as yes, no or unsure. Playground, examples and the language guide.
竹影 · 原创竹林忍者游戏,支持网页、触屏、Python 桌面和 TypeSafe Jev AI 测试。
Guideline-driven code review bot for Ruby: code finds what to inspect, TypeSafe Jev judges it, explicit rules decide what to report
Visualize a character's journey through a story using TypeSafe System One
A tiny, zero-dependency TypeScript library for Jev by TypeSafe. Checks, classification and scoring, with a live playground.
Tiny demo of TypeSafe System One / Jev: unstructured state in → typed probabilistic decisions out (noul, choice, score). Mock by default; live API optional.
Telegram Goups auditor with TypeSafe models.
Clean up Gmail and YouTube with AI, safely: Jev judges each email or channel, plain code sets the limits, you approve. pipx install tidy-ai
A self-organizing Downloads folder. Jev (TypeSafe AI) files each download into the folder you described in plain English; unsure files stay put; every move is logged and undoable.
triaje-ambulancias
Typed questions to a model, verdict in code, thresholds from your labels
TypeSafe AI is a San Francisco AI lab building System One models — a class of model trained to return typed, calibrated decisions for software instead of generated text. Its flagship and first System One model, Jev, is served by a single HTTP endpoint: POST /v1/systemone takes a `state` (a string, JSON object, or array) plus a map of typed…
Ruby client for the TypeSafe AI(Jev) System One API
Typed decisions from TypeSafe AI's Jev model inside TYPO3: a decision editor and playground in the backend, powermail_cond operators, and submission routing
Measure meaning by perturbing text and watching a calibrated probability move. Ablation attribution over TypeSafe's Jev, reported against a measured noise floor.