<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>AI Agent on AgentFlow HK — AI Tools &amp; Tutorials</title>
    <link>https://agentflow.dctt.uk/en/tags/ai-agent/</link>
    <description>Recent content in AI Agent on AgentFlow HK — AI Tools &amp; Tutorials</description>
    <generator>Hugo</generator>
    <language>en</language>
    <lastBuildDate>Mon, 01 Jun 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://agentflow.dctt.uk/en/tags/ai-agent/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>AI Agent Frameworks Compared 2026: LangGraph vs CrewAI vs AutoGen — Which One Should You Pick?</title>
      <link>https://agentflow.dctt.uk/en/posts/ai-agent-frameworks-comparison-2026/</link>
      <pubDate>Mon, 01 Jun 2026 00:00:00 +0000</pubDate>
      <guid>https://agentflow.dctt.uk/en/posts/ai-agent-frameworks-comparison-2026/</guid>
      <description>&lt;p&gt;By mid-2026, AI agents have moved from research labs to production dashboards. Gartner now predicts that over 40% of enterprise applications will embed AI agents by the end of this year — up from under 5% in 2025. But with a dozen frameworks competing for your attention, how do you choose the right one?&lt;/p&gt;&#xA;&lt;p&gt;Let&amp;rsquo;s break down the three most popular options: &lt;strong&gt;LangGraph&lt;/strong&gt;, &lt;strong&gt;CrewAI&lt;/strong&gt;, and the community-resurrected &lt;strong&gt;AutoGen (AG2)&lt;/strong&gt;.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Self-Host AI Agents with Docker: A Step-by-Step Guide Using Hermes Agent</title>
      <link>https://agentflow.dctt.uk/en/posts/docker-ai-agent-deployment-guide-2026/</link>
      <pubDate>Mon, 01 Jun 2026 00:00:00 +0000</pubDate>
      <guid>https://agentflow.dctt.uk/en/posts/docker-ai-agent-deployment-guide-2026/</guid>
      <description>&lt;h2 id=&#34;why-self-host-an-ai-agent&#34;&gt;Why Self-Host an AI Agent?&lt;/h2&gt;&#xA;&lt;p&gt;By mid-2026, AI agents like Claude Code, OpenAI Codex CLI, and open-source Hermes Agent have become essential developer tools. While most people use cloud-hosted versions, self-hosting gives you:&lt;/p&gt;&#xA;&lt;ul&gt;&#xA;&lt;li&gt;&lt;strong&gt;Data sovereignty&lt;/strong&gt; — your code and prompts never leave your machine&lt;/li&gt;&#xA;&lt;li&gt;&lt;strong&gt;Unlimited usage&lt;/strong&gt; — no API quotas when paired with local LLMs&lt;/li&gt;&#xA;&lt;li&gt;&lt;strong&gt;Full customization&lt;/strong&gt; — modify the code, add plugins, craft your own prompts&lt;/li&gt;&#xA;&lt;li&gt;&lt;strong&gt;Long-term cost savings&lt;/strong&gt; — no monthly SaaS subscriptions for heavy users&lt;/li&gt;&#xA;&lt;/ul&gt;&#xA;&lt;p&gt;This guide walks through deploying &lt;strong&gt;Hermes Agent&lt;/strong&gt; with Docker Compose — an open-source, provider-agnostic AI agent framework that can use local models (via Ollama) and cloud APIs (OpenAI, Anthropic, DeepSeek) in a mixed setup.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
