Jev in production › Agent tool and action selection
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).
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...
For the project's own README, linking back here: