1
Jev (TypeSafe System One) operating a web page through its DOM — no WebMCP required
Agent tooling — page 21
Frameworks, routers and utilities that use Jev to choose tools or branches inside a larger agent system.
1,206 active projects in this collection. All collections →
TypeScript MCP server that finds TikTok and YouTube micro-KOLs, tags their niche, scores campaign fit with Jev, and drafts outreach emails. Results are cached locally in SQLite.
Agent Skill that finds where TypeSafe Jev decision models would pay off in a codebase. Works in Claude Code, Codex, Cursor and other Agent Skills hosts.
Talk to your Mac and it acts before you finish the sentence. Jev (TypeSafe) + ElevenLabs + on-device Whisper.
When Jev meets LLM — Transparent proxy that makes AI coding agents 3× faster and 80% cheaper. Cut response times from 2.4s to 890ms with Line J architecture.
Stop AI agents from executing MCP tools unchecked — policy, approval, JEV decisions, and one-use execution permits.
a work in progress, built from the typesafe-ai-skill for building and analyzing jev opportunities
Fast, calibrated System One decision platform powered by TypeSafe Jev via OpenRouter. Sub-second logprob scoring, transfer curves, zero hallucinations.
1
A zot extension that wires Jev (TypeSafe System One) into the agent loop.
A small multi-agent harness built around the pattern from LangChain's post: use a fast, non-generative "System One" classifier (TypeSafe AI's Jev) for structured in-loop decisions -- routing and risky-tool-call gating -- and reserve a real chat LLM for the genuinely open-ended reasoning.
One-command setup that makes Claude Code use fewer tokens: rtk shell compression, stash search index, web-search, codebase-memory, fast-jev-compaction, ponytail, plus Jev skill suggestions and model routing.
1
An open-source AI skill that turns Gmail and Outlook promotions into a weekly savings calendar, with JEV-powered filtering and deduplication. 一个开源 AI Skill，将 Gmail 和 Outlook 中的促销邮件整理成每周省钱日历，借助 JEV 智能筛选、去重，让优惠一目了然。
1
DSH Plugin（DeepSeek Harness 插件）：每轮对话调用 typesafe.ai systemone(jev) 判定用户情绪/意图，结果注入模型上下文；API Key 与全部参数在 GUI 设置页配置
Nearly half the agent cost, with accuracy intact. Just enough tools is a DeepSeek Harness plugin that uses Jev to reveal tools and skills progressively. The main model starts with a clean planning step. Jev then selects which capabilities to add as the task unfolds.
DeepSeek Harness WSL plugin: TypeSafe Jev / OpenRouter System One (jev_ask / check / rank)
1
Go harness for Jev/Kev decision models: TypeSafe, Vercel AI Gateway, and in-process Kev via llama.cpp
Local MCP server for TypeSafe Jev typed decisions, with Codex integration
No project description available.
Vets an LLM agent's tool calls through TypeSafe AI's Jev before they run — allow, block, or hold, failing safe on uncertainty.
A Codex skill that asks TypeSafe Jev through OpenRouter which model and reasoning effort to use
基于 TypeSafe Jev 的学术论文智能初筛系统与 Agent Skill，支持批量 PDF/URL 自动提取与硬门槛决策分流
Claude Code plugin that routes skill selection and post-turn code judgment through TypeSafe Jev on OpenRouter
A JEV-gated semantic communication layer for parallel coding agents.
A lightweight, auditable Jev testbench built through Agentic Engineering, with frozen evidence, a preregistered null result, and a bilingual technical blog. 基于 Agentic Engineering 的轻量、可审计 Jev 实验台，包含冻结证据、预注册负结果、双语技术博客与认知负债反思。