Jev in production › Agent tool and action selection

Home Assistant TypeSafe Conversation Agent

Home Assistant voice agent asks Jev typed yes/no questions per command to resolve intent instead of using an LLM, resolving commands in about 300ms (the-sof).

Open on GitHub ↗

300msmeasured, as published by the source
Use
Agent tool and action selection
Industry
General-purpose
Form
Open-source tool
Stage
In production
Plugs into
Home Assistant
Listed
2026-09-30
Found via
discord
Repository
the-sof/home-assistant-typesafe-conversation-agent
Stars
9
Forks
2
Last push
2026-10-22
Language
Python
License
MIT

The README opens with

A Home Assistant conversation agent that decides with a System One decision model instead of an LLM: TypeSafe's hosted model, or one running on your own hardware through Ollama, so nothing has to leave your home. Device commands and questions about the home are resolved from its typed answers in code; a language model, if you add one, only writes text.

- Local or hosted, your choice: run a decision model such as nimble or tev1 on your own machine with Ollama, free and fully local, or use TypeSafe's hosted API. See Running locally and What gets sent. - Fast: a command or a question about the home takes about 250 ms on TypeSafe's API, where an LLM turn takes 2–8 s. - Predictable: every decision is a typed, calibrated answer checked in ordinary...

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for agent tool and action selection