I’m building Waycore, an open-source project exploring what a flexible, offline-first field computer should look like for outdoor, survival, and off-grid scenarios.
The core goals are adaptability and resilience:
modular hardware (external sensor/tool modules)
extensible OS with support for external apps (guidelines in progress)
no required internet connection — maps, models, and knowledge work offline
optional LTE/Wi-Fi when available and explicitly enabled
A major focus is on-device agentic AI, not just chat or image recognition. The AI is intended to:
read live sensor data (GPS, compass, environment)
reason over offline knowledge
use apps and core APIs
assist with navigation, safety checks, logging, and communication
Main project repo (OS & architecture): https://github.com/dmitry-grechko/waycore
There’s also a separate repo curating freely downloadable survival & outdoor PDFs for offline use: https://github.com/dmitry-grechko/waycore-knowledge
I’m looking for feedback and contributors around:
UI/UX for rugged touch devices
hardware modularity & interfaces
offline/edge agent architectures
small models that work well without internet
high-quality public-domain or permissive survival knowledge sources
Happy to answer questions or hear critique.
think of it as a modular field computer inspired by Flipper Zero, but aimed at outdoors/survival/trades folks instead of security people.
Right now I'm deep in the software/OS layer - getting the core system working (Qt/QML UI, Docker services, on-device AI with Phi-3, offline maps, Meshtastic integration). Once I validate everything with field tests, I'll finalize the hardware design. It's built on Raspberry Pi 5 + ESP32-S3 doing the heavy lifting for LoRa mesh comms and always-on sensors.
The big idea is making something that's flexible like Flipper Zero but for different use cases - you could run apps for hunting, survival navigation, plant identification, whatever fits your lifestyle. The app ecosystem is key - I want developers to easily build specialized tools that work in their workflow.
Communication-first design too - Meshtastic for long-range mesh when networks are down, with graceful degradation from LTE → WiFi → LoRa → GPS beacon. The whole thing is designed to work offline-first - max functionality with zero internet dependency.
Still super early (hence the software focus first), but the goal is a rugged platform that people can actually build on and customize for their specific needs. Not trying to replace phones, just be the reliable tool that works when phones don't.
E-ink or transflective LCD or maybe the modified LED used by the Daylight Computer folks.
Agree that AI needs to go as not reliable enough for life-death situations.
Yeah I don't want LLMs near anything life or death, where a hallucination can kill, thank you very much.
So, I certainly see the inherited risk and problems, but mostly think about it as a means of information extraction
Please reconsider using a full text search index instead.
Wonder if that would run in a current version of Windows...
https://daylightcomputer.com/
The hardware component will be open sourced in a separate repo, once the prototype is tested in the field to validate the configuration. I hope to make it public in January.
Feel free to email us (hn@ycombinator.com) to discuss further.