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)→
More from coding & agent
- OpenAI DevDay's overlooked signals: plugin distribution window, Codex security agent, Decisions API — dhruv2038 · 2026-09-30
- CaptchaArena releases 50K verified CAPTCHA trajectories; 9B agent hits 71.7% Pass@1 — ColumbiaUniversity · 2026-09-30
- Meituan LongCat unveils DeepResearch multi-agent system scoring 55.25 on DeepResearchBench — Meituan LongCat Team · 2026-09-30
- Google's TabFM-Auto: LLM agent evolves data pipelines, lifting TabFM by 228 Elo and topping MLE-Bench — google · 2026-09-30
- LEGO-Anything: coding agents write Blender code to rebuild editable 3D scenes, 62.7% gains — AWS · 2026-09-30
- HybridCUA mixes GUI with CLI commands, hits 53.6% on OSWorld (+14.8 pts) — Tongbo Chen · 2026-09-30