<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
    <channel>
        <title>AI Agents - Category - Mansour Rahimi</title>
        <link>https://mansour.dev/categories/ai-agents/</link>
        <description>AI Agents - Category - Mansour Rahimi</description>
        <generator>Hugo -- gohugo.io</generator><language>en-us</language><lastBuildDate>Sun, 18 Oct 2026 10:00:00 &#43;0200</lastBuildDate><atom:link href="https://mansour.dev/categories/ai-agents/" rel="self" type="application/rss+xml" /><item>
    <title>Building a Local AI Agent</title>
    <link>https://mansour.dev/iris/</link>
    <pubDate>Sun, 18 Oct 2026 10:00:00 &#43;0200</pubDate>
    <author>Mansour</author>
    <guid>https://mansour.dev/iris/</guid>
    <description><![CDATA[<p>Recently I was working on building a local AI agent <strong><a href="https://github.com/m4ns0ur/iris" target="_blank" rel="noopener noreffer ">Iris</a></strong>. An open-source project experiencing how to build a practical AI assistant that runs locally and can do more than just answer questions.</p>
<p>My focus is on the foundations of a capable agent: minimal planning, tool use, and breaking complex goals into manageable steps. The challenge is making these workflows reliable and useful, even when working with smaller local language models.</p>]]></description>
</item>
</channel>
</rss>
