Interesting project! The zoom-out revealing a much larger map was really cool after having spent time in the zoomed in view without suspecting there was much more to see around! One thing I'm curious about in these kind of sandbox games is the emerging behaviors we could see and that I feel can bring a lot of life to virtual worlds. Do you already know what platforms you will be targeting?
The emergent behavior is very much our end goal, it’s the reason everything is very systems oriented, and we’re trying to put as much control in the players hands as possible. One of our biggest remaining efforts is adding the depth to the villagers under the hood, and integrating tons of little animations and interactions, but we’re confident on the vision!
Targeting (and wishlist-able now!) Steam first, with development actively happening on Windows, Mac, Linux and the Steam Deck. Closely followed by mobile, where I’ve currently got iOS builds working for a proof of concept, just not proper controls. After that we’d love to target consoles.
I'm working on an iPhone app to run iOS-native agents using both cloud and local models, powered by llama.cpp. It has access basic iOS tools such as calendar, reminders etc. but also more advanced ones like a custom JS environment running on QuickJS that can use various custom modules like an HTTP client, Git etc.
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.
Actually a pretty interesting idea. What problems does it solve? Who is your ICP? What language do they use to describe their problem? Try to answer those questions and put it in your LP.
Right now your LP reads like a technical doc rather than a product’s page.
Thank you! There's this tension between having what feels like a very capable technological foundation and still figuring out the best use cases, and my hope with releasing it as a TestFlight beta is to resolve it.
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.
