Find a practical pattern

Jev for Home Assistant

AboveColin

Turn Jev answers about household state into Home Assistant sensors and automation responses.

Source

TypeSafe for Vercel AI SDK

Vercel

Use Jev through the AI SDK evaluation API, with Choice, Score, and Boolean questions in one request.

Source

neo4jev

jexp

Explore a Neo4j graph by asking Jev which relationship to follow and whether the goal is reached.

Source

ruby_llm-typesafe

kieranklaassen

A RubyLLM 2 provider that expresses Jev questions through RubyLLM's structured output interface.

Source

TypeSafe AI for n8n

DomMonte

A community n8n node for adding typed Jev questions to automation workflows.

Source

Jevex

jvsteiner

An agent-loop experiment where Jev chooses actions and a LangChain model supplies text.

Source

Pydantic AI + Jev Examples

adtyavrdhn

Small Pydantic AI examples that use Jev at prompt, tool, and application decision points.

Source

DraftPulse

pekth

Inspect typed quality signals while drafting an X post.

Source

Jev Audio Beeper

santos-sanz

Replace flagged Spanish words with beeps using timestamped transcripts.

Source

Triage Guard

shivam2003-dev

Explore Jev workflows for tickets, operational alerts, and deployment risk.

Source

Eve

vercel

Use Jev for automatic model selection and typed evaluations in agents.

Source

Vercel AI CLI

vercel-labs

Send typed evaluation questions from shell scripts through AI Gateway.

Source

Loki

wundercorp

Add a Jev decision companion to the Loki agent.

Source

TypeSafe for Agent Zero

3clyp50

Display typed Jev answers and probability cards inside Agent Zero.

Source

Jev Email Intent Workflow

GiesN

Route example email intents through an async LangGraph workflow.

Source

Safer with Jev

andrelandgraf

Place Jev judgments in an HTTP inspection and forwarding service.

Source

Laravel TypeSafe Jev

Butochnikov

Integrate typed Jev requests into Laravel services and tests.

Source

pg_typesafe

giuliosmall

Ask Choice, Noul, and Score questions from PostgreSQL.

Source

TypeSafe AI Rails

GenieRobot

Add Jev configuration, usage records, and confidence policies to Rails.

Source

TypeSafe Assist

JanOstrowka

Interpret Home Assistant voice commands with batched Jev questions.

Source

Jev4Mellea

SoundBlaster

Prototype Jev semantic checks for a Mellea generation loop.

Source

TypeSafe UI

BunsDev

Browse reusable React components for TypeSafe-style decision interfaces.

Source

Instinct

joevidev

Turn a natural-language request into choices from a fixed UI catalog.

Source

Human Compiler

asfarsadewa

Read writing diagnostics through a playful compiler-style interface.

Source

Jev Paper Judge

JacobLinCool

Evaluate a paper’s presentation, clarity, and completeness.

Source

Jev CSV Workbench

WebGrga

Apply your own typed questions to selected CSV rows.

Source

Clarity Judge

BunsDev

Inspect separate Jev checks for clarity, filler, tone, and actionability.

Source

Jev Data Analysis

narulaskaran

Bring a CSV and inspect Jev classifications in a distribution chart.

Source

Smart Home Assistant Demo

TypeSafe AIOfficial

An official walkthrough of batching home-control questions and using only the relevant answers.

Source

TypeSafe Quick Start

TypeSafe AIOfficial

Start with the playground, make an HTTP request, and translate a first evaluation into Python.

Source

Choice, Score & Noul

TypeSafe AIOfficial

Understand the three question types, the answers they return, and when to use each.

Source

System One Workflow Patterns

TypeSafe AIOfficial

Explore fan-out, confidence-based routing, composite scoring, and intent routing.

Source

System One HTTP API

TypeSafe AIOfficial

The request and response contract for calling Jev directly over HTTP.

Source

Jev 1.13: Known Limitations

TypeSafe AIOfficial

TypeSafe's model-specific notes on failure modes and how to structure questions around them.

Source

TypeSafe Workflow Evals

TypeSafe AIOfficial

TypeSafe's published comparison of structured workflows and single-prompt approaches.

Source

ResolveIQ-by-Jev

Tanish-o9

Source description: ResolveIQ by Jev — An AI-powered customer support triage platform that intelligently classifies support tickets, prioritizes issues, and generates context-aware response suggestions using Jev, LangChain, Groq, and FastAPI.

Source

laravel-jev-moderation

phoenix1331

Source description: Confidence-aware content moderation for Laravel: classify any Eloquent model with Jev and route each item to passed, flagged for human review, or blocked, using per-category thresholds.

Source

jev_router

twilso24

Source description: Standalone TypeSafe Jev-based auto-routing for Agent Zero

Source

langgraph-jev-router

JTankariya

Source description: A native LangGraph conditional edge that replaces slow generative LLMs with TypeSafe AI's deterministic System One model (`Jev`). It enables ultra-fast (sub-500ms), schema-safe routing between specialized agents.

Source

voice_control

igorkasyanchuk

Source description: You say it. Your app does it. Voice and typed commands for Rails.

Source

jevtraces

ishantanu

Source description: The three probability attributes occur only with scored and are in [0, 1]. They are independent judgments, not an overall confidence value. Questions are sent together using TypeSafe's noul primitive through the HTTP API.

Source

jev-acp

formulahendry

Source description: Use Jev typed decisions from any ACP (Agent Client Protocol) client or IDE

Source

judging-with-typesafe

carlsonchik

Source description: Скилл для агентов Letta: суждения по критериям через TypeSafe System One (Jev)

Source

nocap

xi029

Source description: No evidence, no answer. 🧢 System One evidence gate for RAG & AI agents: Jev / Laya / any LLM judges before your LLM speaks. MCP server, Python SDK, CI route tests.

Source

ha-gutcheck

funkadelic

Source description: Home Assistant integration that uses TypeSafe AI's Jev to spot problems and suggest cleanups in your install, and asks before changing anything

Source

hush

emreozyoruk

Source description: Issue triage that stays quiet when it isn't sure. Calibrated labels, spam and duplicate detection — with abstention.

Source

demo-symfony-typesafe

yoanbernabeu

Source description: Démo : trier des demandes de support avec Jev (TypeSafe) et Symfony AI. Messenger, Live Components, Turbo, kit shadcn de UX Toolkit.

Source

n8n-nodes-typesafe-jev

n3ndor

Source description: n8n community node for TypeSafe Jev structured AI decisions

Source

jev-ai-use-cases

atliq

Source description: Hands-on LangChain examples of Jev, TypeSafe AI's decision model: support ticket triage, model routing, reply guardrails, tool selection and finance-inbox fraud checks. An LLM writes; Jev decides.

Source

jevmetrics

ishantanu

Source description: Jev inference for metric assessment and retention in OpenTelemetry.

Source

filament

vibefilter

Source description: Filter Filament tables with a plain-English statement. Each row is scored by TypeSafe Jev.

Source

home-assistant-typesafe-conversation-agent

the-sof

Source description: A Home Assistant voice agent that decides with typed, calibrated judgements instead of an LLM. One ~300 ms call per command, and it asks when it isn't sure.

Source

typesafe-ui

TypeSafeAI

Source description: shadcn-style reusable components and blocks for using TypeSafe AI.

Source

langchain-skill-router

deyna256

Source description: Per-turn skill selection for LangChain and deepagents agents: a fast judge picks the few skills a turn needs, so a catalog of hundreds stays out of the prompt.

Source

n8n-nodes-jev

vibe-with-me-tools

Source description: Helper n8n community node for Jev by TypeSafe. Classify, route, and score text with questions you define, and get a probability for every answer so unsure items can go to review.

Source

n8n-nodes-jev-classification

khmuhtadin

Source description: n8n community node for Jev by TypeSafe AI: classify, score and check text with calibrated probabilities. Parallel requests and multi-item batching.

Source

jev-feels

Qew7

Source description: Semantic decisions as ordinary Ruby #feels?, #decide, #score, Rails validations and pattern matching powered by Jev

Source

discern

doeixd

Source description: Craft Type-Safe Uncertainty-aware semantic pattern matching, control flow, and smart procedures for Effect DecisionModel and Jev

Source

jevql

kylemclaren

Source description: Semantic SQL for Postgres, powered by Jev

Source

jevc

doronp

Source description: Compile agent policy prose into deterministic verdict programs: narrow evidence questions for the model, the verdict computed in code. Install: npm i -g jev-compiler

Source

llama-index-jev

WiktorB2004

Source description: LlamaIndex reranker + router powered by TypeSafe Jev - typed scores/choices, cheaper than LLM-as-judge.

Source

pg-jev

realZachi

Source description: Ask your Postgres tables questions in plain language. A PostgreSQL extension powered by TypeSafe's Jev.

Source

jev-shell-history

mrnugget

Source description: Fish-style zsh history autosuggestions ranked by Jev (TypeSafe)

Source

jevmail

fazlerocks

Source description: Open-source AI email triage for Gmail. Sorts your inbox into Needs reply, Updates, Promos, Sales and Spam with Jev, TypeSafe AI's decision model, via Vercel AI Gateway. Read-only, runs locally, 1,000 emails in about a minute for 3 cents.

Source