<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Agentmemory on Thomas Talks AI: Claude Architecture, AI Agent Security, Claude Code &amp; Production Engineering</title>
    <link>https://thomasdevos.com/tags/agentmemory/</link>
    <description>Recent content in Agentmemory on Thomas Talks AI: Claude Architecture, AI Agent Security, Claude Code &amp; Production Engineering</description>
    <generator>Hugo -- 0.145.0</generator>
    <language>en-us</language>
    <copyright>Thomas De Vos ©</copyright>
    <lastBuildDate>Fri, 24 Jul 2026 10:44:00 +0100</lastBuildDate>
    <atom:link href="https://thomasdevos.com/tags/agentmemory/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>AI agent memory needs provenance and an expiry date</title>
      <link>https://thomasdevos.com/posts/2026-07-24.10.44.00-ai-agent-memory-needs-provenance-and-an-expiry-date/</link>
      <pubDate>Fri, 24 Jul 2026 10:44:00 +0100</pubDate>
      <guid>https://thomasdevos.com/posts/2026-07-24.10.44.00-ai-agent-memory-needs-provenance-and-an-expiry-date/</guid>
      <description>A practical guide to safe AI agent memory: provenance, scope, expiry, review, deletion, prompt injection controls, evals, and audit evidence for Claude Code and enterprise agents.</description>
    </item>
  </channel>
</rss>
