<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Announcement | Introducing Agent Memory on Databricks in Announcements</title>
    <link>https://community.databricks.com/t5/announcements/announcement-introducing-agent-memory-on-databricks/m-p/174667#M1131</link>
    <description>&lt;P&gt;&lt;STRONG&gt;Agent Memory&lt;/STRONG&gt;&lt;SPAN&gt; is now available in Beta on Agent Bricks, Databricks’ agent developer platform. It gives agents durable sessions and long-term memory for facts, preferences, and workflows, so they can provide more personalized experiences while reducing repeated work across conversations.&lt;/SPAN&gt;&lt;/P&gt;
&lt;P&gt;&lt;FONT size="4"&gt;&lt;STRONG&gt;Key highlights&lt;/STRONG&gt;&lt;/FONT&gt;&lt;/P&gt;
&lt;UL&gt;
&lt;LI style="font-weight: 400;" aria-level="1"&gt;&lt;STRONG&gt;Persistent context across sessions&lt;/STRONG&gt;&lt;SPAN&gt;: Managed sessions preserve conversation history, while managed memory stores durable facts such as user preferences, past decisions, and domain knowledge.&lt;/SPAN&gt;&lt;/LI&gt;
&lt;LI style="font-weight: 400;" aria-level="1"&gt;&lt;STRONG&gt;Memory that improves over time&lt;/STRONG&gt;&lt;SPAN&gt;: Background memory pipelines distill conversations into durable memories, merge overlapping entries, and update facts when newer conversations contradict them.&lt;/SPAN&gt;&lt;/LI&gt;
&lt;LI style="font-weight: 400;" aria-level="1"&gt;&lt;STRONG&gt;Flexible recall and control&lt;/STRONG&gt;&lt;SPAN&gt;: Agents can recall or save memories through tools, or applications can retrieve relevant memories before a run. Developers can read, export, and delete stored entries and steer what a pipeline retains.&lt;/SPAN&gt;&lt;/LI&gt;
&lt;LI style="font-weight: 400;" aria-level="1"&gt;&lt;STRONG&gt;Built for production agents&lt;/STRONG&gt;&lt;SPAN&gt;: Session and memory stores are managed on Lakebase and work with frameworks including LangGraph, the OpenAI Agents SDK, and other Python frameworks.&lt;/SPAN&gt;&lt;/LI&gt;
&lt;LI style="font-weight: 400;" aria-level="1"&gt;&lt;STRONG&gt;Part of the Agent Bricks platform&lt;/STRONG&gt;&lt;SPAN&gt;: Combine memory with agent hosting, the Agent Bricks CLI, Databricks Sandbox, Unity Gateway, MCP tools, tracing, and evaluation.&lt;/SPAN&gt;&lt;/LI&gt;
&lt;/UL&gt;
&lt;P class="p8i6j01 paragraph"&gt;&lt;A style="background-color: #ff3621; color: white; padding: 10px 20px; text-decoration: none; border-radius: 5px; font-weight: bold; display: inline-block;" href="https://www.databricks.com/blog/introducing-agent-memory-databricks?utm_source=bambu&amp;amp;utm_medium=social&amp;amp;utm_campaign=advocacy" target="_blank" rel="noopener"&gt; &lt;span class="lia-unicode-emoji" title=":link:"&gt;🔗&lt;/span&gt; Read the full post here &lt;span class="lia-unicode-emoji" title=":backhand_index_pointing_left:"&gt;👈&lt;/span&gt;&lt;/A&gt;&lt;/P&gt;</description>
    <pubDate>Mon, 26 Oct 2026 17:32:40 GMT</pubDate>
    <dc:creator>Tushar_Parekar</dc:creator>
    <dc:date>2026-10-26T17:32:40Z</dc:date>
    <item>
      <title>Announcement | Introducing Agent Memory on Databricks</title>
      <link>https://community.databricks.com/t5/announcements/announcement-introducing-agent-memory-on-databricks/m-p/174667#M1131</link>
      <description>&lt;P&gt;&lt;STRONG&gt;Agent Memory&lt;/STRONG&gt;&lt;SPAN&gt; is now available in Beta on Agent Bricks, Databricks’ agent developer platform. It gives agents durable sessions and long-term memory for facts, preferences, and workflows, so they can provide more personalized experiences while reducing repeated work across conversations.&lt;/SPAN&gt;&lt;/P&gt;
&lt;P&gt;&lt;FONT size="4"&gt;&lt;STRONG&gt;Key highlights&lt;/STRONG&gt;&lt;/FONT&gt;&lt;/P&gt;
&lt;UL&gt;
&lt;LI style="font-weight: 400;" aria-level="1"&gt;&lt;STRONG&gt;Persistent context across sessions&lt;/STRONG&gt;&lt;SPAN&gt;: Managed sessions preserve conversation history, while managed memory stores durable facts such as user preferences, past decisions, and domain knowledge.&lt;/SPAN&gt;&lt;/LI&gt;
&lt;LI style="font-weight: 400;" aria-level="1"&gt;&lt;STRONG&gt;Memory that improves over time&lt;/STRONG&gt;&lt;SPAN&gt;: Background memory pipelines distill conversations into durable memories, merge overlapping entries, and update facts when newer conversations contradict them.&lt;/SPAN&gt;&lt;/LI&gt;
&lt;LI style="font-weight: 400;" aria-level="1"&gt;&lt;STRONG&gt;Flexible recall and control&lt;/STRONG&gt;&lt;SPAN&gt;: Agents can recall or save memories through tools, or applications can retrieve relevant memories before a run. Developers can read, export, and delete stored entries and steer what a pipeline retains.&lt;/SPAN&gt;&lt;/LI&gt;
&lt;LI style="font-weight: 400;" aria-level="1"&gt;&lt;STRONG&gt;Built for production agents&lt;/STRONG&gt;&lt;SPAN&gt;: Session and memory stores are managed on Lakebase and work with frameworks including LangGraph, the OpenAI Agents SDK, and other Python frameworks.&lt;/SPAN&gt;&lt;/LI&gt;
&lt;LI style="font-weight: 400;" aria-level="1"&gt;&lt;STRONG&gt;Part of the Agent Bricks platform&lt;/STRONG&gt;&lt;SPAN&gt;: Combine memory with agent hosting, the Agent Bricks CLI, Databricks Sandbox, Unity Gateway, MCP tools, tracing, and evaluation.&lt;/SPAN&gt;&lt;/LI&gt;
&lt;/UL&gt;
&lt;P class="p8i6j01 paragraph"&gt;&lt;A style="background-color: #ff3621; color: white; padding: 10px 20px; text-decoration: none; border-radius: 5px; font-weight: bold; display: inline-block;" href="https://www.databricks.com/blog/introducing-agent-memory-databricks?utm_source=bambu&amp;amp;utm_medium=social&amp;amp;utm_campaign=advocacy" target="_blank" rel="noopener"&gt; &lt;span class="lia-unicode-emoji" title=":link:"&gt;🔗&lt;/span&gt; Read the full post here &lt;span class="lia-unicode-emoji" title=":backhand_index_pointing_left:"&gt;👈&lt;/span&gt;&lt;/A&gt;&lt;/P&gt;</description>
      <pubDate>Mon, 26 Oct 2026 17:32:40 GMT</pubDate>
      <guid>https://community.databricks.com/t5/announcements/announcement-introducing-agent-memory-on-databricks/m-p/174667#M1131</guid>
      <dc:creator>Tushar_Parekar</dc:creator>
      <dc:date>2026-10-26T17:32:40Z</dc:date>
    </item>
  </channel>
</rss>

