Jev for Home Assistant
Turn Jev answers about household state into Home Assistant sensors and automation responses.
Connect Jev decisions to existing tools, frameworks and workflows. These integrations show how typed answers become actions, validations or application data.
Public projects, checked against their original sources.
Turn Jev answers about household state into Home Assistant sensors and automation responses.
Use Jev through the AI SDK evaluation API, with Choice, Score, and Boolean questions in one request.
Explore a Neo4j graph by asking Jev which relationship to follow and whether the goal is reached.
A RubyLLM 2 provider that expresses Jev questions through RubyLLM's structured output interface.
A community n8n node for adding typed Jev questions to automation workflows.
Use Jev for automatic model selection and typed evaluations in agents.
Send typed evaluation questions from shell scripts through AI Gateway.
Add a Jev decision companion to the Loki agent.
Display typed Jev answers and probability cards inside Agent Zero.
Route example email intents through an async LangGraph workflow.
Place Jev judgments in an HTTP inspection and forwarding service.
Integrate typed Jev requests into Laravel services and tests.
Ask Choice, Noul, and Score questions from PostgreSQL.
Add Jev configuration, usage records, and confidence policies to Rails.
Interpret Home Assistant voice commands with batched Jev questions.
Prototype Jev semantic checks for a Mellea generation loop.
Browse reusable React components for TypeSafe-style decision interfaces.
Try another keyword or clear your filters.
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 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 description: Standalone TypeSafe Jev-based auto-routing for Agent Zero
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 description: You say it. Your app does it. Voice and typed commands for Rails.
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 description: Use Jev typed decisions from any ACP (Agent Client Protocol) client or IDE
Source description: Скилл для агентов Letta: суждения по критериям через TypeSafe System One (Jev)
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 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 description: Issue triage that stays quiet when it isn't sure. Calibrated labels, spam and duplicate detection — with abstention.
Source description: Démo : trier des demandes de support avec Jev (TypeSafe) et Symfony AI. Messenger, Live Components, Turbo, kit shadcn de UX Toolkit.
Source description: n8n community node for TypeSafe Jev structured AI decisions
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 description: Jev inference for metric assessment and retention in OpenTelemetry.
Source description: Filter Filament tables with a plain-English statement. Each row is scored by TypeSafe Jev.
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 description: shadcn-style reusable components and blocks for using TypeSafe AI.
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 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 description: n8n community node for Jev by TypeSafe AI: classify, score and check text with calibrated probabilities. Parallel requests and multi-item batching.
Source description: Semantic decisions as ordinary Ruby #feels?, #decide, #score, Rails validations and pattern matching powered by Jev
Source description: Craft Type-Safe Uncertainty-aware semantic pattern matching, control flow, and smart procedures for Effect DecisionModel and Jev
Source description: Semantic SQL for Postgres, powered by Jev
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 description: LlamaIndex reranker + router powered by TypeSafe Jev - typed scores/choices, cheaper than LLM-as-judge.
Source description: Ask your Postgres tables questions in plain language. A PostgreSQL extension powered by TypeSafe's Jev.
Source description: Fish-style zsh history autosuggestions ranked by Jev (TypeSafe)
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.