A home that understands

Turn the state of your home into typed decisions, sensors, and smarter automations.

A home that understands project preview

Ask your house a question, get a number back. Home Assistant integration for TypeSafe Jev: typed answers as sensors, four actions for automations, and a conversation agent for Assist.

How it uses Jev

Ask TypeSafe Jev questions about your house and get numbers back. Jev is a decision model, not a chat model. It answers a typed question with a probability, a choice or a score, and this integration turns each answer into an entity you can automate on.

Highlights

  • Questions become sensors: a probability,
  • Five actions, jev.noul , jev.choice ,
  • An AI Task entity answers
  • Actions and the AI Task can look at cameras:
  • A conversation agent for Assist routes
  • A house check opens a Repairs card for

Getting started

Requires Home Assistant 2026.9 or newer and an API key from typesafe.ai.

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README · the project website.

Keep exploring

Similar to A home that understands

Browse all
typesafe-assist project preview
Integrations
Home Assistant Assist conversation agent powered by TypeSafe's Jev (System One) model
a0-typesafe-ai project preview
Integrations
TypeSafe AI Jev judgments for Agent Zero, with typed tools and probability cards.
pg-jev project preview
Integrations
Ask your Postgres tables questions in plain language. A PostgreSQL extension powered by TypeSafe's Jev.
TypeSafe.Jev project preview
SDKs & clients
Typed AI decisions for .NET: ask Jev (TypeSafe AI System One) yes/no, choice and score questions and get a C# enum with calibrated probabilities back.
wechat-jev-assistant project preview
Windows 微信对话分析助手:本地读取、脱敏、TypeSafe Jev 判断与加密历史
jevgrep project preview
Agent tooling
grep by meaning: pipe in any text, ask a yes/no question in plain English, get only the matching lines. Works behind tail -f, about $0.004 per 1,000 lines, powered by TypeSafe's Jev.
typesafe-local project preview
Benchmarks & research
Inspired by TypeSafe Ai, Ask a local LLM typed questions, get calibrated probabilities instead of text. Structured output without generation or parsing. MLX / Apple Silicon.
SemIf project preview
Jev alternatives & open source
Semantic ifs from open models, on a 3090 at home. Independent; not affiliated with Jev or TypeSafe.
jev-cli (shaharia-lab) project preview
Benchmarks & research
Command-line tool for TypeSafe AI's Jev model. Ask yes/no, multiple-choice and rubric questions about any text and get calibrated probabilities back. Answers become exit codes for shells and CI, JSON for scripts, and MCP tools for AI agents.