AgentsNEWData platformsTestingHuman in loop: unclear
Databricks puts agent memory in Beta, built on its MemCurrent research
Databricks says Agent Memory keeps sessions, distills facts and preferences in a background pipeline, and runs on Lakebase. In its internal benchmarks the design tripled agent pass rate while using 31% fewer tokens.
Why it matters: Stateless agents redo yesterday's work; in Databricks' example a repeat question fell from 11 tool calls to 2, and developers can read, export and delete stored memories.
On the Frontier watch →From Drop #037 · Wed, Oct 21 · Morning