Electric joins Databricks to bring WASM Postgres to AI agent sandboxes

Summary

Databricks says Electric is joining the company to extend its Postgres capabilities from the lakehouse to AI agent sandboxes. The post frames agentic applications as requiring both durable governed state and rapidly changing local context: agents choose data at runtime, operate in sandboxed environments where cloud databases are reached over the network, and collaborate while working in parallel. Electric’s PGlite is a lightweight Postgres database built for WebAssembly that runs inside an agent, application, browser tab, or device, while its real-time sync engine synchronizes distributed data with centralized Lakebase infrastructure. PGlite’s weekly downloads reportedly grew from 1 million to 13 million in twelve months, and the sync architecture is described as keeping agents’ shared context current. Combined, Lakebase, PGlite, and synchronization are presented as a Postgres-based foundation for collaborative agentic applications at production scale.

Context

Agentic applications need durable governed state alongside fast-moving local context. Agents decide what data to access at runtime, often run in sandboxed environments, and work in groups that need a current shared view to avoid stale state, duplicated work, and conflicting conclusions.

Approach / What changed

Databricks is combining Lakebase Postgres with Electric’s PGlite, a lightweight WASM Postgres database that runs inside an agent sandbox, and Electric’s real-time synchronization engine, which keeps distributed agents connected to centralized Lakebase infrastructure.

Takeaways

• PGlite runs Postgres inside an agent, application, browser tab, or user device, providing local execution rather than requiring a separate database server.
• Electric’s real-time sync engine synchronizes data between distributed agents and centralized Lakebase infrastructure, allowing agents to share current context while retaining local access.
• PGlite’s weekly downloads grew from 1 million to 13 million in twelve months, according to the post.

Related reading