19 sources. One unified corpus.
Every Canton Network knowledge source you would search separately, indexed continuously and exposed through 88 MCP tools. The numbers below refresh every minute, straight from the production database.
How the data lands here
Each source is polled on its own cadence - the forum every 5 min, the SDK index every 6 hr, whitepapers every 24 hr. Anything changed since the last sync is upserted and re-embedded.
Why one corpus matters
Cross-source queries (“which CIP introduced this forum breakage?”) only work when forum, docs, CIPs, GitHub and proposals share a single semantic index.
Verify the numbers
The widget calls /api/v1/sources. Same endpoint anyone can hit - no caching, no embellishment.