CloudAppSelf-hosted
Concepts
How a source becomes items, items become summaries, and summaries become one digest
The pipeline is the same in both routes: the cloud runs the open-source core for you, so what is described here is what happens on your own box too. These pages explain the mechanism once; the Cloud and Self hosting sections link here instead of repeating it.
Feeds and fetching
What counts as a source, how often it is read, deduplication, and what happens with a new source's backlog
Summarization
What the model receives per item, the summary rules, and how the reader profile shapes the output
Digest and delivery
Which items make it into a digest, how they are grouped and judged, and how delivery works
AI budget and costs
Where tokens go, how usage is bounded, and what you pay in each route