Briefs

BriefsNewsAvailable now1 min read

Databricks adds MemCurrent persistent memory architecture to Agent Bricks and Genie

Databricks introduced MemCurrent, a persistent memory architecture for production AI agents now powering Agent Bricks Memory and Genie.

Databricks adds MemCurrent persistent memory architecture to Agent Bricks and Genie — image from Databricks
Image: Databricks

Summary

Databricks introduced MemCurrent, a persistent memory architecture for production AI agents that now powers Agent Bricks Memory and Genie. MemCurrent uses episodic memory for raw session traces and derived memory for distilled learnings, combined via plugins, agent tools, and an offline dreaming pipeline. Databricks states MemCurrent triples pass rates over agents without memory while reducing token usage and latency.

What changed

  • Databricks introduced MemCurrent, a persistent memory architecture for production AI agents.
  • MemCurrent now powers Agent Bricks Memory and Genie.
  • MemCurrent combines episodic memory for raw session traces and derived memory for distilled learnings.
  • MemCurrent integrates plugins, agent tools, and an offline dreaming pipeline for memory access and consolidation.

Availability

Available now

“MemCurrent is built into Agent Bricks' Memory offering, powered by Lakebase.”

Founder takeaway

Agent developers using Agent Bricks can build custom agents with MemCurrent memory components, including a session store, memory store, and automatic dreaming pipeline.

Source

DatabricksMemCurrent: Designing Persistent Memory for Production Agents

Announced Checked

Researched and drafted with AI from the official sources above, then checked automatically before publishing. Spotted a mistake? Tell us.

SharePost on XLinkedIn

Related

More briefs

All briefs
  1. AWS logo on a FounderHeist card

    NewsAvailable now

    Amazon Quick adds smart approvals for agentic AI actions

    Amazon Quick introduces smart approvals to automate routine agentic tasks while keeping human oversight for high-impact actions.

    AWS1 min read

  2. ElevenLabs introduces Cue forced alignment AI model — image from ElevenLabs

    NewsAvailable now

    ElevenLabs introduces Cue forced alignment AI model

    ElevenLabs releases Cue, an AI forced alignment model that places every character in an audio file on a precise timeline and powers its Scribe model family.

    ElevenLabs1 min read

  3. GitHub makes Copilot Memory generally available on paid Copilot plans — image from GitHub

    NewsAvailable now

    GitHub makes Copilot Memory generally available on paid Copilot plans

    GitHub introduces new AI intelligence capabilities including Copilot Memory, dreaming, and multi-repository code search.

    GitHub1 min read

One email, every Monday

Briefs are published here through the day. Monday Heist is the email: one useful AI workflow, the files to use it, and the catch. The first issue is being prepared; subscribers get it first. Free, and you can leave in one click.

One email. Every Monday.