Databricks announced that the Electric team is joining Databricks to bring WASM Postgres to AI agent sandboxes—extending Databricks’ Postgres capabilities from the lakehouse to the edge.
Electric is leading the way in pioneering data primitives purpose-built for agents: PGlite gives every agent its own lightweight Postgres right where it runs, providing ultra-low latency access to local context, and Electric’s real-time sync engine synchronizes distributed state back to a central Lakebase, enabling teams of agents to collaborate without losing track of shared context, according to the company.
Electric’s real-time sync engine continuously synchronizes data between distributed agents and centralized Lakebase infrastructure, enabling agents to securely share information with the definitive record in the cloud while keeping fast, local context. The real-time sync architecture powers collaborative apps such as Google Docs, Figma, and Notion, and it turns out to be exactly what a fleet of agents needs to stay current while working in parallel.
Both Electric and Lakebase are built on Postgres, the open-source database technology that has become the default foundation for AI agents.
Lakebase delivers Postgres at production scale. PGlite brings WASM Postgres into the agent's own sandbox. Sync keeps the two consistent. By combining the power of Lakebase Postgres with the local execution of PGlite, agents get the lightweight databases they need to move fast and the infrastructure required to deploy at any scale, the companies said.
For developers, this means:
- Building collaborative, agentic applications on a single Postgres standard.
- Running Postgres directly inside the agent sandbox, giving each agent a lightweight database it needs to move fast.
- Keeping teams of agents in sync to instantly share context and act on fresh data, while centralizing control in Lakebase Postgres on cheap, durable object storage.
For more information about this news, visit www.databricks.com.