It started with a family member telling me they were frustrated with existing websites. What I noticed is that in many cases they feel cluttered and not smooth to use, almost like a 1-to-1 translation of the underlying database queries, where they have you choose filters and sorting options upfront then browse the paginated results.
I wanted to avoid all of that by creating a different experience; I built an interactive full-screen wall UI with infinite browsing so that most of the screen space is dedicated to the core content. I worked on the name sampling algorithm to try to make it as enjoyable to browse as I could, and the only filter displayed by default is the one to select genders.
More advanced queries are available through the search field which supports natural language queries, running on a local multilingual interpretation engine with a cloud LLM fallback. The database engine is custom built with Rust, compiled to WASM for higher performance when running on CloudFlare Workers. I don’t use an external DB service for names today.
What I’m pretty proud of is to know a lot of technical work is hidden behind that UI, and how it has been shaped by the experience I wanted instead of the other way around.
Hi HN! I recently published AbracadaNames, a website that shows an interactive wall of first names, with a name selection designed to be pleasant, infinite scrolling, and ways to search for names by country, origin etc. A close relative of mine was unhappy with the names websites they had visited, and after taking a look myself I felt like trying a different approach from what I saw. I wanted...
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.
It's a project I have been working on for quite a long time and I released it on TestFlight about a week ago. It was really nice to work on something end-to-end, from creating a wrapper around llama.cpp with support for prompt caching/forking and automatic model loading and unloading based on device memory constraints, to the custom agentic harness the app runs on. I have also spent quite a lot of time on agent execution modes that I hope can enable to more easily reason about agent security regarding prompt injection attacks.
What I'm really hoping for now is to get actual feedback, to know if users end up having real use cases where the app is truly useful / interesting for them, to understand what should most urgently be improved etc.