Curiosity

Curiosity

Home

Learn Curiosity Workspace

Build, query, and extend the graph + search + AI platform.

Deploy and manage

Roll out Curiosity to Docker, Kubernetes, or your cloud of choice.

Build enterprise AI apps

Ship domain-specific AI apps with custom UIs, endpoints, and connectors.

Model your data as typed nodes and edges with stable keys.

Query with text, vector, and hybrid retrieval — permission-aware.

Ground LLMs, embeddings, and agents in your own graph.

Compose UIs in C# with our front-end component library.

Transpile C# to JavaScript and run it in the browser.

Test, ingest, sync, and promote workspaces from any shell.

Open Source Projects

Browse every open-source project Curiosity maintains.

Support

RSS / Atom

Polls one or more RSS or Atom feeds and ingests their items as _WebPage nodes. Optionally crawls the linked URL of each entry and stores the full article body.

variant=info text="Web / feeds" variant=secondary text="Anonymous"

What gets ingested

Element	Mapped to
Feed	`_Feed`
Item / entry	`_WebPage`
Authors	`_Contact`
Categories / tags	`_Tag`
Linked article body (when crawl enabled)	Text content on the `_WebPage`

Authentication

Type: Anonymous (a custom User-Agent header can be set).
Some private feeds support HTTP Basic auth via the URL; the connector will pass it through if present.

Access control mapping

Feed items are public — they land on _AccessGroup.Public.

Sync cadence

Default cron: every 15 minutes (configurable per feed).
Incremental sync: entry-ID dedup (guid for RSS, id for Atom). Items with a known ID are skipped; modified entries are detected via <updated> / pubDate.

Notable

Per-feed source-prefix string lets you namespace ingested items in the graph (e.g. tech-news/).
Optional full-article crawl: when enabled, the connector fetches the linked URL and stores the rendered body so search can index more than the feed summary.