So one the most pressing issues with the HomeBrain has been false positives, not that this is an issue solely with the HomeBrain, as both the Google and Alexa devices frequently get erroneously triggered and start yappingg about nothing nobody asked for. The issue was pressing because the HomeBrain was bad enough that it bothering my wife, so it moved to the top of the “fix” list. To understand the solution, first let’s look at the current system at a high level:

So, I’m trying to put together something I call a “Home Brain”, a conversational system I can interact with that not only allows me to control IoT devices in my home, but also contains personal knowledge I can access, and also more general knowledge (think wikipedia), and yet all this functionality should run locally, with no cloud services required. I initially started down this path with Home Assistant, adding all of our IoT devices into Home Assistant running on an RPi, which worked fine, but when I took the next step of buying a couple Home Assistant Voice Preview Edition devices I found the performance of the RPi was painfully slow.