<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Session on Euijun's Personal Blog</title><link>https://elbanic.github.io/tags/session/</link><description>Recent content in Session on Euijun's Personal Blog</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><lastBuildDate>Mon, 18 May 2026 06:22:00 +0900</lastBuildDate><atom:link href="https://elbanic.github.io/tags/session/index.xml" rel="self" type="application/rss+xml"/><item><title>「Agentic AI Dev Note」 Managing Agent Memory in a Distributed Systems</title><link>https://elbanic.github.io/posts/managing-agent-memory-in-a-distributed-systems/</link><pubDate>Mon, 18 May 2026 06:22:00 +0900</pubDate><guid>https://elbanic.github.io/posts/managing-agent-memory-in-a-distributed-systems/</guid><description>&lt;p&gt;In &lt;a href="https://elbanic.github.io/posts/develop-and-operating-agents-in-a-distributed-environment/"&gt;Part 1&lt;/a&gt;, we discussed stateless containers for running Agents in a distributed system. However, the Agents we interact with seem to behave statefully. When a user asks an Agent a question, it answers, and as the conversation progresses, the Agent maintains the context of previous discussions. To achieve this, the system is designed by separating the request processing area from the memory area, fetching the conversation history from memory whenever needed.&lt;/p&gt;</description></item></channel></rss>