Jev ecosystem projects — page 103

Japanese text linter powered by jev (TypeSafe System One)

Jev Computer Use Agent — cross-platform self-improving computer-use (cua offshoot: linux/windows/macos/android)

JEV 调研报告：TypeSafe System One 决策模型与开源对标（含原始核实记录）

CLI and MCP server for TypeSafe's Jev model, built for scripts, agents, and automation.

A wrapper that gets more value out of TypeSafe's JEV model: transcript compaction, cost-control modes, and a local usage ledger for Claude Code and Codex.

Independent 100-question English benchmark of TypeSafe's Jev decision model (jev-1.13.0)

The Jev System 1 Oracle — Victorian steampunk Magic 8-Ball powered by TypeSafe AI's Jev model

Python examples for using Jev in accounting research, including ESG disclosure classification, forward-looking statement detection, variable construction, confidence-based human review, and validation against human-coded data.

Use Jev typed decisions from any ACP (Agent Client Protocol) client or IDE

把决策模型 Jev 接进亚马逊广告优化的参考实现：规则层出可追溯结论，Jev 出独立第二意见，分歧即信号。输出可落到飞书多维表格。

A runnable decision-first agent evaluation example using Jev and TypeSafe AI.

Jev AI agent skill for typed decisions

Portable Jev skills for intent, completion, routing, Camofox browser loops and shadow context relevance.

Sample: TypeSafe Jev via Vercel AI Gateway

Jev AI Model (Typesafe.ai) security protection and vulnerability scanner tools

Empirical experiments and API research for TypeSafe's Jev System One model trained using RLCD

Can a System One model play arcade games? TypeSafe's Jev plays Tetris, Snake and 2048 — benchmarked against random and heuristic baselines.

Open-source Jev skills for Claude Code, Codex, Cursor, and Grok. TypeSafe System One: choice, noul, score. Proceed, ask, or stop.

Evaluate typed AI decisions on labeled French-language cases.

Measured benchmarks of TypeSafe's Jev decision model vs LLMs: ticket triage, voice-agent decision layer, bulk tagging