Right now your LP reads like a technical doc rather than a product’s page.
My starting hypothesis is power users and devs, people who want to experiment with local and cloud LLMs, build their own custom agents, and try experiences they wouldn't usually find in consumer AI mobile apps. As the app is now closer to release, I think it has reached a level where it is likely complete enough that there are some viable combinations of its features that can actually solve concrete user problems. I could see the app being used to create agents that serve as small shortcuts tailored to the users' needs, with all the flexibility it enables. A bit like a more iOS-native OpenClaw with opinionated takes on tooling and security. I personally used it to create a food tracker that has a good understanding of my daily routine and also TL;DRs of various sources (including HN) surfaced as suggestions on the home page.
I don't yet know the exact words those users would use to describe their problem, so surfacing that is part of why I'm putting it in front of testers first.