There's a company which sells something like this, as "Prepper Disk".[1]
In the 1950s, US Civil Defense had a set of microfilms on how to rebuild society. These were packaged with a sunlight reader and stored in larger fallout shelters. Someone should find one of those.
So this thing is based on Kiwix, which is based on the ZIM file format.
In the meanwhile, wikipedia ships wikidata, which uses RDF dumps (and probably 8x less compressed than it should be).
https://www.wikidata.org/wiki/Wikidata:Database_download
There is room for a third option leveraging commercial columnar database research.
And for those who are only vaguely familiar, this ZIM file format is not the same as the https://zim-wiki.org one.
I am actually only vaguely familiar and I was wondering about that every time I saw the format referenced but never bothered to check, your comment is informative!
Normally I cringe at doomsday preppers but given how many dictators out there love the idea to cut their country off Internet whenever anything starts going not in their favor, I imagine a lot of people may find this useful.
I wouldn’t want to lose access to knowledge how to fix a sink or which medication is better, just because the local kingface currently feels that free exchange of opinions about him threatens his kingship.
I like the idea of an LLM that acts as a public knowledge base. But that doomsday framing on the site is pretty annoying.
I think there’s a difference between doomsday framing and preparedness.
Offline access and local models aren’t about assuming collapse—they’re about treating knowledge as infrastructure instead of something implicitly guaranteed.
That feels more like resilience than pessimism.
If current frontier online LLMs are made inaccessible due to a local or global cataclysmic event running models locally will be the least of your concerns.
This isn’t prepping for anything it’s cosplaying as a vault dweller.
P.S. Having TED talks as part of the “educational” curriculum of this project is probably the biggest circle jerk imaginable.
This is not just a random idea.
AlexNet -> Tansformers -> ChatGPT -> Claude Code -> Small LMs serving KBs
Large LLMs could have a role in efficiently producing such KBs.
Doomsday may not be the end of the world, but simply living in a country where you're being unjustifiably bombed by a foreign government lead by a delusional sociopath, and so access to information sources becomes limited.
You’ll be hanged from a construction crane if they’ll catch you with this project in Iran… :)
What Gulf state do you live in? UAE?
Closing on 40 acres in Panama for an eco-resort.
I was planning to build my own offline repository, but will check out this repo.
In a world where this is useful, you aren't going to be spending your precious battery on running an LLM...
Solar cells work no matter what, I agree that maybe less processing is more useful but LLM is uniqely useful as well
This is not true for me. I would want an LLM after the apocalypse. I'd become like the Wizard of Oz, the all-knowing oracle.
No need for a battery, you just need someone to hit the pedals on that dynamo.
For anyone wanting the video explanation from the creator, watch: https://youtu.be/P_wt-2P-WBk
I'm a fan of "civilization in a box" kinds of projects. However the ZIM file format leaves a lot to be desired in 2026. I've been exploring a refreshed, alternative approach: https://github.com/stazelabs/oza
I do think having an LLM as an optional "sidecar" is a useful approach. If you can run a meaningful Ollama instance alongside your content, great!
ZIM or not, I think the “LLM as optional sidecar” part is the right idea.
The durable asset is the knowledge base itself. A local model can be useful on top, but it should stay a layer, not become the dependency.
what a coincidence, i am just downloading 110gb wikipedia dump on kiwix right now
Anyone thought about using a Steam Deck with this? Or explored the concept of a "Nomad Deck"?
It might be an interesting idea given that the Steam Deck has reasonable amount of RAM/GPU. The main issue for a knowledge base might be the lack of a physical keyboard though.
It has built in microphones though.
Not sure how good of an idea a Steam Deck would be for this. If you can't access Wikipedia, I imagine a replacement for its unprotected glass screen would be harder to come by if you drop it.
True, but I always give my devices a protective glass and put them in rugged armor. Broken screens never been a problem for me..
Missing a chance to note (or configure for?) installation on a Raspberry Pi --- that'd make an affordable option to leave powered down, but ready to go in an EMI-shield/Faraday Cage.
They specifically state that they’re aiming for a “fatter” model that expects higher-end hardware, and other projects like Internet in a box already target rpi-style devices.
I like this idea! I don't need the LLM bits, and want it to run on an old Android tablet I have lying around. Can anyone recommend similar software where I can get wikipedia / street maps / useful tutorial videos nicely packaged for offline use?
A friend made this years ago. I never used it but the idea is awesome.
>Knowledge That Never Goes Offline
>What is Project N.O.M.A.D.? Node for Offline Media, Archives, and Data
That's the first header, and the first sentence of the first paragraph, and I'm confused.
Two different uses of "offline", I think. From my own understanding:
To "go offline" means for something to become inaccessible that was once accessible "online". ("Offline" is an adverb.)
Meanwhile, an "offline" thing is one which is usable even without ever being "online". ("Offline" is an adjective.)
So it becomes:
> "Knowledge That Never [Becomes Inaccessible]"
> "Node for [Accessible-Without-Connection] Media, Archives, and Data"
But definitely confusing to put them right next to each other like that. You'd think a copyeditor would flag it or something.
My guess is
>Knowledge That Never Goes Offline
Means
>Knowledge That Never becomes inaccessible to you
While the next offline means you can access it even if you don't have access to a wider network.
At least that's how I would read it.
Really clever targeting of a niche. I’d be interested to hear if they find success!
Also https://kiwix.org/en/about/
I used it on a long train trip. There was no internet due to drone attacks, and with Kiwix I could browse pre-downloaded Wikis
I’m convinced that the multitude of off-line Internet tools is a ploy to keep any one of them from gaining traction
The ones mentioned in this thread all use Kiwix for off-line wikipedia, OSM for maps, Khan for educational videos. It looks like internet-in-a-box is aimed at working well on low-powered devices, whereas nomad expects beefy hardware and includes local AI. Not sure how WROLPi differs from internet-in-a-box.
Maybe it's like linux distros: all based on the same software, but optimized for different use-cases or preferences.
I mean, technically they use Kolibri for educational videos and exercises. A lot of them do come from Khan Academy, but we do a lot of work to make an offline first education platform, and also bring in a huge swathe of other open educational resources.
It could use some own wisdom not to use nodejs..
See I really want this in a simpler format. Like a single file embedded database on my filesystem that I can point a single/or few tools at for my model to use when it needs.
Why does it have to have AI? Ugh.
Because if you're stuck in your underground bunker, who else can you talk to?
You can use Kiwix, OpenStreetMap and Kolibri as an AI-free equivalent. Adding AI to those is exactly the differentiator of this project.
I get the hate on AI for many reasons (hype, resource greediness, threat to civilization, etc), but having a local LLM that could help guide and reason about the data within seems like a win, especially if it's optional.
This is really cool. Having offline Wikipedia + local LLMs in a single bundle is a great combo for emergency preparedness. Do you have any benchmarks on how it performs on lower-end hardware? Curious about minimum specs.
turns out I have the same setup (sans local LLMs - they are pretty useless on 2018 cards) but in Obsidian :)
whatever I think might be useful later, I capture through the web clipper extension. [0]
Great premise for a science fiction story
So how does that work?
It never goes offline by already being offline.
I was expecting the game from my childhood and was disappointed.
Yeah, that game was really ahead of its time. I still hold out hope some indie studio will attempt a spiritual successor.
[dead]
[dead]