Basically, I hooked up an ESP32 camera to a vision model so I can prompt it to watch stuff and send webhooks. Thinking analog gauges, legacy equipment, sourdough starters (still no API), and stuff like that.
Been dogfooding the prototype on my desk, and now I have an air quality API that reads the display on a cheap monitor.
Also added direct camera access via MCP so Claude could help me debug the hardware, which has been pretty fun.
It looks like this is sending video signal off into the cloud? Are you sure people will be OK with this? Can I integrate it with local inference and lock it down?
Why can't this just run on a spare cellphone? Why the dedicated hardware?
I'd be curious to see some technical details on how you're routing b/w the user's prompt to the continuous monitoring. Are you purpose-building a tiny CV model for each prompt? Or are you running a big model continuously.