Jev ecosystem projects — page 47

Evaluate JEV robot control in MetaWorld and RoboTwin: discrete actions, hierarchical control, privilege-level ablations, and replay analysis.

Unofficial Jev-powered Zig terminal agent with deterministic policy gates and encrypted audit trails.

an Information-Geometric Analysis Toolkit for any System-one (Jev, Jevlike) agent systems

System 1 vs System 2 AI models, measured: a chain test comparing one-pass Jev with Qwen 3.8 thinking on and off

Jev / TypeSafe AI 驱动的 X 信息筛选：按你的规则发现值得读的帖子。开源判断规则库 + 免费 Chrome 扩展。Filter X with your own criteria.

Agent make dozens of silent judgments a turn: is this done, is this correct, do I have enough to decide, which way now. Made inside your own text stream, those judgments are uncalibrated and biased toward finishing, you tend to certify your own work. judge hands one such judgment to Jev.

A bounded Jev System-1 browser tool for Pi, OpenCode V2, Amp, and MCP, powered by agent-browser

The Jev projects actually worth your time — picked, compared, kept current.

用 JEV（TypeSafe System One 判断模型）自动完成 B 站「硬核会员试炼」的单文件 Python 脚本：手机只扫码登录一次，100 题在电脑上自动答完，零第三方依赖。

Agent skill for writing programs with Laya and laya-cli — local typed decisions (Choice/Score/Noul), port of building-with-jev-skill to Laya

Classification of human/agent messages using Jev in Claude-Code/OpenCode

Experimental native Codex Desktop and CLI model routing with Jev and a configurable allowlist

Portable JevRouter setup for cost-aware Codex subagent model selection, with English and Russian instructions

Crush 好感监控器的 Windows / macOS 安装包（第三方打包，源码与版权属原作者 FerryCorleone/crush-monitor）

40-agent, ~10,163-dimension security analysis swarm (static + live ops) with a scored 46-chain exploit planner and Jev (TypeSafe System One) decisioning. Built and verified; source available on request.

Typed, probabilistic decisions (Choice / Score / Noul) for System One tasks, powered by TypeSafe Jev, with OpenAI and Anthropic as alternative engines

EvidenceLens is an open-source research build for testing what we believe may be JEV's ideal use: bounded semantic evidence review and human-review triage.

Serveur MCP pour piloter Firefox avec Claude : Jev (TypeSafe) choisit les clics, Claude planifie. Benchmark inclus.

FormPilot: AI form-filling Chrome extension

用 TypeSafe Jev 给 Gmail 自动分类：写回标签、钓鱼检测、退订分析、Chrome 侧边栏面板

Fuses two System-1 decision models (Laya + Jev) into one auditable verdict — confidence-weighted fusion, disagreement escalation to a local adjudicator, append-only JSON decision logs.

Label and prioritise Gmail with a language model. Reads mail through himalaya, classifies each thread with Jev (TypeSafe) over OpenRouter, and applies Gmail labels and colours. Dry run by default, idempotent, no state file.

Local retrieval without embeddings. Every answer comes back as the original passage with its coordinates (path:start-end), so a person or an agent can open the exact lines. No Embedding, Zero Cost, Fully Local.