jev4k - Kotlin DSL for TypeSafe Jev
A Kotlin DSL and client for TypeSafe's Jev model, enabling typed questions and answers.
OPEN SOURCE · CURATED REPOSITORIES
Curated Jev SDKs, tools, demos, integrations, benchmarks, and research projects. Repository metrics come from GitHub; titles, summaries, and categories are editorial.
Sponsors
These products pay for the directory. Want yours up here?
Ranked by GitHub Stars
Ranked by recent Star growth and update activity
A Kotlin DSL and client for TypeSafe's Jev model, enabling typed questions and answers.
An OpenAPI semantic compatibility checker that uses TypeSafe JEV System One to evaluate behavioral risks in changed contract prose, with CLI, GitHub Action, deterministic checks, and benchmarks.
A high-throughput native DuckDB extension for TypeSafe/Jev, enabling batched and streaming classification, scoring, and semantic predicate evaluation from SQL.
WordPress connector for the TypeSafe Jev API, providing typed answers with confidence scores, plus REST routes, caching, and tests.
A reference implementation that lets TypeSafe's Jev (System One) model drive a browser via Claude Code and Codex skills. It observes page controls, asks Jev multiple-choice questions, validates and executes the picks, and includes a runnable demo and trace explainer.
One card in the feed, every sixteen, on every page of it. $50 a week, cancel any week.
Jev.Net is a community .NET client for the TypeSafe AI System One / Jev API. It is a faithful port of the official Python SDK with one dependency, sample apps, offline tests, and Native AOT support.
A Claude Code plugin and TypeScript library that uses TypeSafe's JEV model for model routing and recoverable context filtering. It includes a local comparison UI, CLI launcher, and offline tests, and is not affiliated with TypeSafe or Anthropic.
Claude Code plugin that uses TypeSafe's Jev model to set per-step reasoning effort, keeping routine steps cheap and boosting effort after failures.
Use Jev model to augment CSV files with inferred classification, scoring, or probability scores via YAML-defined questions and the TypeSafe API.
Jev grades gated tool calls for oh-my-pi; calls Jev allows run without a prompt, others are held with Jev's reasoning. Includes measurements on real traffic and a 140-row labelled safety corpus.
An agent skill for discovering TypeSafe Jev opportunities, designing typed questions, and running helper scripts for local scans and evaluations.
Integrates TypeSafe's Jev (System One classifier) into Claude Code, Codex, Pi, and OpenCode as typed tools for classify, check, score, rank, and ask, with one-command setup and a CLI.