Preparedness collection
Mixed practical sources
Current examples include Appropedia, Ready.gov, Kiwix ZIM archives, PDFs, and other resilience reference material, all combined into one searchable library.
Collections
The collection behind the demo.
The hosted app runs on a preparedness-focused collection assembled from practical reference sources, offline archives, and document libraries. This is the library behind the demo, and it shows the kind of bounded, inspectable collection you can run yourself later.
Looking for other source material? Browse the Kiwix library to see the kinds of offline archives you can turn into your own collections.
Active collections
A deployable library, not just a chat box
The value is not just the chat interface. It is the library behind it: named sources, clear boundaries, portable collections, and a system you can point at your own data later.
The hosted demo shows the interaction. The collection is the part you can inspect, adapt, expand, and carry into your own deployment.
Visible scale
Named sources, not a black box
This is not a black-box dataset. The demo is built from real sources with clear collection boundaries, so you can see what is being searched and what is not.
Why it matters
Same engine, different data
The demo happens to use preparedness sources, but the software is not limited to that. The same runtime can search websites, PDFs, video transcripts, and ZIM archives once they have been prepared for the system.
The runtime and the library stay separate
Most search tools bundle their knowledge with the application. Disaster Clippy treats the collection as a first-class artifact that can be versioned, released, and distributed independently. Under the hood, packs are the portable unit. What matters here is simpler: you can update the library without rebuilding the app.
What is in the example deployment
The current demo collection is preparedness-oriented on purpose. It mixes household emergency guidance, practical DIY material, survival and resilience references, and offline-friendly archives. It is broad enough to feel useful, but still bounded enough to inspect.
Kiwix ZIM archives are an especially useful bootstrap path. If you already trust a Kiwix library, you can use those archives as source material for a local Disaster Clippy deployment and start with material you already know.
Building your own collection
The public repo includes ingestion tooling for websites, PDFs, and video archives. Point it at a source, run the pipeline, and you get a collection the runtime can load. The same tools used to build the preparedness example are available for your own data.
The workflow is straightforward: choose a source, ingest it, package it, and run the same search interface against it. That same workflow is what lets the preparedness example become a library you can reuse, extend, or replace with your own sources.