Graphsub pitches in-memory graph DB for agent data: don't trust one AI corp with it all

arthurcolle · x · 2026-09-30

Replying to lux's question about how to store agent-generated data, arthurcolle describes Graphsub, a fast in-memory graph database built at Distributed for this use case.

Key point: data you create with your agent should inform future interactions and could serve as a training set, but shouldn't be entrusted to a single cloud AI company — "imagine all your emails as datasets controlled by one cloud AI vendor."

Related event: Debates Emerge Over Agent Data Ownership and Storage(2 posts)→

Original post →

More from coding & agent

coding & agent channel →