Jev (TypeSafe AI System One) agent harness guide + video manual — from the LangChain 'Building a Harness with Jev' post. Learn Jev Noul/Choice/Score questions, Model Router, and AutoMode guardrails with LangChain.
Agent tooling — page 36
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 →
Jev-supervised madmax conductor for Claude Code: tiny slices, parallel subagent workers in worktrees, TypeSafe Jev makes routing/review/QA/supervision decisions.
Question-design and confidence-calibration toolkit for TypeSafe's Jev (System One) API — a Claude Code plugin skill.
A Codex plugin that turns noisy input into small, typed, calibrated decisions using TypeSafe Jev.
Demos with Jev, TypeSafe's System One model, one folder per demo. Code behind the videos on The Agentic Enterprise.
Per-turn model AND reasoning-effort routing for Hermes Agent on Ollama:Cloud, decided by TypeSafe Jev (a System One decision model, not an LLM). Rewrites the outgoing provider request itself via llm_request middleware. Ollama:Cloud only.
A Claude Code skill: an authoritative reference for TypeSafe AI's Jev, the "System One" model. You send it a state plus typed questions (Choice / Score / Noul) and it returns typed answers with calibrated probabilities. It doesn't generate text. The skill covers the API contract, primitives, confidence calibration and its quirks, where Jev is weak
Can a System One model (TypeSafe Jev, open-source Kev) replace an LLM-as-judge in agent guardrail callbacks?
Opt-in bounded Jev decisions for Pi through pi-mcp-adapter. Community MIT package with measured overhead and explicit privacy boundaries.
Jev decides; Claude, Grok, or any LLM only writes. TypeSafe Jev integration for routing, compaction, and cheaper agent turns.
⚡ Autonomous Multi-Model Routing Engine powered by TypeSafe Jev System One (<250ms, 97.4% cost savings), LangGraph State Machine, Dual-Tier In-Path Security Firewall, and real-time Mistral Large & Google Gemini execution.
Routes each Claude Code turn's model and reasoning effort with TypeSafe Jev, and keeps small-window models away from large sessions.
AI TUI harness using Vercel Eve and typesafe-ai/jev for dynamic model routing
Quick agent-ready Jev tool for decision making on the fly
Prompt injection protection & tool-call guardrails for LangChain / LangGraph AI agents. Screens tool outputs, gates risky tool calls (allow / human review / block), powered by TypeSafe Jev.
Interactive showcase of TypeSafe's Jev System One model (choice / score / noul) via OpenRouter — zero-dependency Node app
Score every page on your site against your own brand/AEO rules, combining free regex checks with Jev (TypeSafe AI) semantic judgment calls. Point it at your own site with your own brand rules and OpenRouter key.
Independent measurement of a Jev (TypeSafe System One) skill router on a real Hermes agent roster: 81 labelled turns, router scorecard, and an inconclusive agent-level appendix.
Agent-neutral Jev skills for Claude Code and Codex, from 207 Studio.
0
TypeScript fuzzy sorting with Jev: non-mutating arrays, shared context, and batched parallel comparisons
No project description available.
Measure an agent or a prompt with a panel of typed questions, judged by Jev
0
Plugin for Claude Code and Codex: TypeSafe's fast classifier Jev screens spec drift, failed CI runs and code-rule violations in seconds; your agent investigates only what it flags. Specs in English, Latin-alphabet languages, Chinese, Japanese and Korean.
0
Open-source MCP server that lets AI coding agents offload yes/no, multiple-choice and scoring questions to TypeSafe's Jev. Jev reads your files, your agent gets back tiny, confidence-scored answers, fewer tokens, faster runs. Works with a TypeSafe or OpenRouter key.