Yo, I also got the email:

""" Hi Matt,

I found your GitHub and thought you might like what we're building. We're developing an open source SDK that runs LLMs directly on-device.

We're getting about 45 tokens per second on iPhones, with support for Swift, Kotlin, React Native and Flutter. There's also a fully offline voice pipeline built in, so everything runs locally. We recently got into Y Combinator and are focused on expanding support to more edge devices and continuously improving performance.

If you're curious, here's the repo: github.com/RunanywhereAI/runanywhere-sdks

Feel free to reply to this email with any feedback or ideas you'd like to explore with on-device AI, or if you'd be interested in contributing. I'd love to hear your thoughts.

Best, Aditya """

Just to share the entire email, I think it's pretty well written, I went ahead and talked to the team, they were very curious and took my feedback regarding their flutter sdks very seriously, and they seem to be great people. Also, just an fyi, I tried their sdks, it's great! and I've been loving their apps as well.

I think their team is great, and I asked them for adding the rag implementation, they did it in less than week and it's pretty impressive. I think it's worth checking it out, It's easier to demean someone in public like that but might be worth checking.