An AI interface to a point-of-sale (POS) system: https://github.com/paulmooreparks/PosKernel

I'm actually in the middle of a complete redesign of the AI layer, but there is a POC video linked from the GitHub README that demonstrates the interaction I'm going for using an earlier version. The POS is a very bare-bones system where the "kernel," as it were, is implemented in Rust. There's an MCP atop that to allow the AI and UI layers to drive the POS. Stores may be implemented as extensions that plug into the POS kernel, and that's where language, currency, item databases, and such are defined. The AI cashier knows what items are for sale, how to modify items (in a restaurant context), how to translate from other languages, how to interpret what the customer actually wants, and seamlessly lead the customer through a transaction.

The current code is quite ugly and full of a lot of unfortunate hacks, but it was a good education. The new design puts the AI much more in charge, without as much code-level orchestration. I'm applying a lot of my knowledge from the retail POS and self-service checkout domains to this, as well as learning a lot about applying AI to a "legacy" software domain.