Jev ecosystem projects — page 29

Session Top — htop for AI coding sessions, making usage, quota, and token consumption observable and explainable.

Ask Jev typed questions from the shell: noul, choice, and score answers as numbers, not prose

Unofficial Swift library for the TypeSafe API

AGI JEV Detection — local AI agent monitor: chain-level malicious-agent detection (TypeSafe Jev + Sentinel), escalate-only L1–L5 containment, Neo4j forensics, AngryRobot dashboard. HackSpain 2026.

Workflow for Pi

✨ The easiest decisions you'll ever make.

Selenium 2048 player powered by expectimax search and TypeSafe Jev, with portrait FFmpeg recording.

Rubric-Based Zero-Shot Classification Benchmark: Jev vs Claude Haiku 4.5 vs Claude Sonnet 5 vs OpenJev on rubric-conditioned classification, chained decision execution, and exam grading -- with full price tracking.

A helper which use JEV to play ra2web(WannaFire Version)[王二火大]

利用 jev 刮削音乐元数据,风格,语言

Fast System-1 Decision, Arbitration & Safety Engine for Autonomous AI Agents (Powered by TypeSafe Jev)

Test what your AI should remember. An experimental, source-aware memory admission evaluator powered by Jev, with editable cases and inspectable results.

Jev for Computer Use

Typed System-1 decisions (Laya/Jev) as the judgment layer of a quant research stack, with Claude as System 2. Requirements → design → code → experiments.

Comparing LLM-as-judge vs TypeSafe Jev for agent guardrails: same rules, same agent, measured on cost, latency, calibration and coverage.

A Quick Typesafe's Jev Evaluation on Persian

Keep skill catalogs outside the main LLM context. Jev selects relevant skills through one read-only MCP tool.

A Jev-driven general-purpose agent harness for faster, lower-cost execution, with built-in side-by-side experiments against LLM-only agents.

pi-thinking-router-jev —— pi 的自适应 Thinking Level Router。在任务起点、推理型失败与稳定窗口咨询 jev 决策模型（未配置时本地 规则兜底），动态选择 low/medium/high/xhigh 推理档位：简单改动降档、复杂 debug 升级、失败可升级、稳定可降级。含防抖钳制 、失败安全回退与 JSONL 决策日志，不切换模型、零侵入 agent loop。

https://v.douyin.com/iJtUdfsywHU/

A tiny jev-like model that answers Choice, Score and Noul questions in one forward pass and returns calibrated probabilities. MLX or PyTorch, fully offline, System One compatible.

An unofficial CPP 20 SDK for the TypeSafe API

Local, open-weights decision model for browser agents: a drop-in for System One / Jev requests

Jev MCP server: a decision layer for coding agents, built on TypeSafe Jev (System One model). Ship gates, risk checks, file triage that keeps files out of context, and a safe headless browser, with calibrated confidence. For Claude Code, Codex, Cursor.