shipwithjev

Catalog / Tools & apps

0263GitHub

HA-Jev

Home Assistant integration exposing typed answers as sensors, automation actions, and an Assist conversation agent.

AboveColin/HA-JevREADME ↗
[](https://github.com/AboveColin/HA-Jev/actions/workflows/tests.yaml)
[](https://github.com/AboveColin/HA-Jev/actions/workflows/hassfest.yaml)
[](https://github.com/AboveColin/HA-Jev/actions/workflows/hacs.yaml)
[](https://github.com/hacs/integration)
[](https://www.home-assistant.io/)
[](https://github.com/AboveColin/HA-Jev/releases)
[](LICENSE)

# Jev for Home Assistant

Ask [TypeSafe Jev](https://typesafe.ai) 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.

**[Full documentation](https://jev.cdevries.dev)**

Not affiliated with TypeSafe. The API client is
[jevclient](https://github.com/AboveColin/jevclient).



## What it does

- [Questions](https://jev.cdevries.dev/questions-ui/) become sensors: a probability,
  one of your options with its distribution, or a number on a scale. Add them in the
  UI, [in YAML](https://jev.cdevries.dev/questions-yaml/), or both.
- Five [actions](https://jev.cdevries.dev/actions/), `jev.noul`, `jev.choice`,
  `jev.score`, `jev.ask` and `jev.box`, answer inside an automation and return a
  response variable.
- An [AI Task](https://jev.cdevries.dev/ai-task/) entity answers
  `ai_task.generate_data` when it is called. A boolean, select or number field
  becomes the matching question.
- Actions and the AI Task can [look at cameras](https://jev.cdevries.dev/images/):
  list camera or image entities, or attach a snapshot, and the picture goes in beside
  the state, scaled to what the API takes. `jev.box` finds where something is in a
  picture.
- A [conversation agent](https://jev.cdevries.dev/conversation/) for Assist routes
  spoken commands through the s

Also filed under Tools & apps

  1. 0616

    Jevstiller: distill Jev calls into a local model

    A self-hosted proxy that trains a local model on Jev's answers. It served 72% of Banking77 locally at 15 ms, with a 2% audit and a bound on disagreement.

    tomerglick57 · Tools & apps · 15 ms local

  2. 0611

    Scruple: code checks for what linters miss

    Semantic-aware linting with System One models: rules you can state in a sentence, checked against your code by Jev.

    @nalexpeae · Tools & apps

  3. 0606

    Algolia-style Postgres search with a Jev reranker

    Typo tolerance, typeahead, barcodes and facet counts in plain Postgres SQL, plus an optional Jev step that asks one question per top-10 result.

    @alex_forman1 · Tools & apps

  4. 0604

    Virtual Closet: outfits from closet videos

    built a virtual closet & outfit generator from raw closet videos. classification + semantic search thanks to jev 🥰. clueless closet dreams finally coming to life

    @maitreemervana · Tools & apps