Jev-powered skill router & security auditor for any AI agent (Codex, Claude Code, OpenCode, Hermes): ONE cheap decision per request tells the model WHICH skill to load; scans skill libraries for prompt injection & dangerous commands.
Agent routing & tool choice — page 13
Routers and orchestrators that choose between tools, models, agents or workflow branches. Jev returns a typed choice instead of a sentence.
391 active projects match this task, ordered by traction.
Use TypeSafe Jev to select subagent models and reasoning effort in Codex and Claude Code.
Jev as a channel message router | Jev频道消息路由
Confidence-gated creator inbox triage on TypeSafe's Jev (System One) model
Unofficial experiment: classify Chinese short texts with TypeSafe Jev and calibrate a confidence threshold from labeled samples. 用 TypeSafe Jev 给中文短文本分类并做置信度校准。Bring your own API key. Synthetic data only.
Phishing email triage: TypeSafe Jev 1.13 vs GPT-5.6 Luna on 100 labelled emails, accuracy, speed and cost
Real-time last-mile delivery exception triage: Jev (TypeSafe AI System One) evaluates each event, deterministic guardrails decide. FastAPI + Streamlit.
Native Node-RED nodes for versioned Jev decisions, review routing and provenance.
Obsidian plugin: route incoming notes to the right folder using JEV (TypeSafe System One) typed decisions. It never writes your content — it only decides where it belongs.
pi.dev extension to select models using TypeSafe Jev
0
Experimental consent-gated Jev routing and public-passage reranking for Pi
Automatic model routing for Pi using TypeSafe's Jev through Vercel AI Gateway
Pi extension: TypeSafe Jev routes among checked models without becoming a chat model.
Sub-120ms smart LLM gateway & real-time optics dashboard using TypeSafe Jev System One. Defeats cache thrashing on coding agents (Goose, Cursor, VS Code) with Break-Even Cache Affinity and 0.60 Confidence-Gated Safety.
Question classification experiment using TypeSafe AI Jev for QA/RAG routing.
Training demonstration of Jev in a dispatch services command center scenario.
Email triage app built around Spark CLI and TypeSafe Jev. Early development: TanStack Start, React and TypeScript
Hybrid System 1 (TypeSafe Jev decisions) + System 2 (Claude Fable) demo with confidence-gated routing and cost/accuracy benchmarks.
Support ticket triage: TypeSafe Jev judgments plus an explicit policy layer for priority and team routing, with a Next.js triage workbench.
Spring Boot API gateway using TypeSafe AI for confidence-based request routing.
Federated knowledge retrieval engine for AI agents. Routes queries across specialized backends (FTS5, ChromaDB, graph) via a registry-first orchestrator with TypeSafe/Jev AI routing and evidence re-ranking. Read-only by default, security-gated by design.
Confidence-gated action router for TypeSafe Jev — per-action thresholds, human floors, probability + confidence. Liquid gold Pattern 2.
Interactive smart home demo comparing local Laya (MLX) with Jev (TypeSafe API) using shared routing and safety rules.
The judgment API — TypeSafe Jev (System One) on Cloudflare Workers. Classify text into triage/urgency/spam/tone/risk with calibrated confidence, agent-discoverable. Judgment proposals only.