Databricks launches MemCurrent, tripling agent pass rates with persistent memory
matei_zaharia · x · 2026-10-21
Matei Zaharia boosts Databricks' launch of MemCurrent, a persistent memory architecture for production agents combining episodic and derived memory across three access patterns: plugins that log/load context automatically, on-demand tools, and an offline "dreaming" pipeline that consolidates memory in the background.
Agents carry forward user preferences, prior corrections, metric definitions and successful workflows instead of rediscovering them each session. On an internal benchmark built from real enterprise data, MemCurrent triples agent pass rates while using 31% fewer tokens and running 26% faster. It ships in Agent Bricks' Memory offering and already powers memory in Genie.
More from coding & agent
- Research agent Épi sets 120 records, narrows n-queens constant interval 84x — dair_ai · 2026-10-21
- Compaction hooks in practice: keep last n messages verbatim, summarize the rest for full agent continuity — MoonL88537 · 2026-10-21
- The blank prompt box hides real operational burden: context, workflow and supervision fall on users — _AustinCalvert_ · 2026-10-21
- DeepMind paper: self-evolving agents forget as they learn — fastest learner GEPA also breaks old tasks most — rohanpaul_ai · 2026-10-21
- arXiv: Are Self-Evolving Agents Continual Learners? Plasticity comes at the cost of stability — rohanpaul_ai · 2026-10-21
- PM OS vs Team OS vs Company OS: how to layer your AI setup and which to build first — aakashgupta · 2026-10-21