<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">
  <channel>
    <title>InfoQ - Cloud Architecture - News</title>
    <link>https://www.infoq.com</link>
    <description>InfoQ Cloud Architecture News feed</description>
    <item>
      <title>Cloudflare Completes Its Agent Infrastructure Stack with Browser Run Rebuild and Six-Layer Platform</title>
      <link>https://www.infoq.com/news/2026/05/cloudflare-agent-platform-stack/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Cloud+Architecture-news</link>
      <description>&lt;img src="https://www.infoq.com/styles/static/images/logo/logo_bigger.jpg"/&gt;&lt;p&gt;Cloudflare rebuilt Browser Run on its own Containers platform, delivering 4x higher concurrency and 50% faster response times. The upgrade completes a six-layer agent infrastructure stack: compute (Dynamic Workers + Sandboxes), orchestration (Dynamic Workflows), memory (Agent Memory), browsing (Browser Run), and commerce (Stripe Projects).&lt;/p&gt; &lt;i&gt;By Steef-Jan Wiggers&lt;/i&gt;</description>
      <category>Platform Engineering</category>
      <category>Cloud Architecture</category>
      <category>Cloud</category>
      <category>Cloudflare</category>
      <category>AI Architecture</category>
      <category>AI, ML &amp; Data Engineering</category>
      <category>DevOps</category>
      <category>Development</category>
      <category>Architecture &amp; Design</category>
      <category>news</category>
      <pubDate>Fri, 22 May 2026 09:21:00 GMT</pubDate>
      <guid>https://www.infoq.com/news/2026/05/cloudflare-agent-platform-stack/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Cloud+Architecture-news</guid>
      <dc:creator>Steef-Jan Wiggers</dc:creator>
      <dc:date>2026-05-22T09:21:00Z</dc:date>
      <dc:identifier>/news/2026/05/cloudflare-agent-platform-stack/en</dc:identifier>
    </item>
    <item>
      <title>OpenAI Outlines WebRTC Architecture for Low-Latency Voice AI at Scale</title>
      <link>https://www.infoq.com/news/2026/05/openai-voice-ai-scale/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Cloud+Architecture-news</link>
      <description>&lt;img src="https://res.infoq.com/news/2026/05/openai-voice-ai-scale/en/headerimage/OpenAI-voice-header-1779194151282.jpeg"/&gt;&lt;p&gt;OpenAI recently outlined how it adapted WebRTC for low-latency voice AI at global scale. The new architecture replaced a conventional media termination model with a relay-transceiver design better suited to Kubernetes and cloud load balancers. It keeps WebRTC session state in a dedicated transceiver layer while using relays to reduce public UDP exposure and keep media routing close to users.&lt;/p&gt; &lt;i&gt;By Eran Stiller&lt;/i&gt;</description>
      <category>Cloud Architecture</category>
      <category>WebRTC</category>
      <category>Realtime API</category>
      <category>Voice-enabled UI</category>
      <category>OpenAI</category>
      <category>DevOps</category>
      <category>Architecture &amp; Design</category>
      <category>news</category>
      <pubDate>Wed, 20 May 2026 12:30:00 GMT</pubDate>
      <guid>https://www.infoq.com/news/2026/05/openai-voice-ai-scale/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Cloud+Architecture-news</guid>
      <dc:creator>Eran Stiller</dc:creator>
      <dc:date>2026-05-20T12:30:00Z</dc:date>
      <dc:identifier>/news/2026/05/openai-voice-ai-scale/en</dc:identifier>
    </item>
    <item>
      <title>AWS WorkSpaces Now Lets AI Agents Operate Legacy Desktop Applications without APIs</title>
      <link>https://www.infoq.com/news/2026/05/aws-workspaces-ai-agents/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Cloud+Architecture-news</link>
      <description>&lt;img src="https://res.infoq.com/news/2026/05/aws-workspaces-ai-agents/en/headerimage/generatedHeaderImage-1778485554177.jpg"/&gt;&lt;p&gt;AWS announced that Amazon WorkSpaces can now serve as managed virtual desktops for AI agents in public preview. Agents authenticate through IAM and operate legacy applications via computer vision and input simulation without APIs. Reflex benchmarks show vision agents consume 45x more tokens than API agents.&lt;/p&gt; &lt;i&gt;By Steef-Jan Wiggers&lt;/i&gt;</description>
      <category>Agents</category>
      <category>Amazon Web Services</category>
      <category>Cloud Architecture</category>
      <category>Cloud</category>
      <category>AWS</category>
      <category>Automation</category>
      <category>Amazon</category>
      <category>AI Architecture</category>
      <category>AI, ML &amp; Data Engineering</category>
      <category>DevOps</category>
      <category>Development</category>
      <category>Architecture &amp; Design</category>
      <category>news</category>
      <pubDate>Wed, 13 May 2026 07:31:00 GMT</pubDate>
      <guid>https://www.infoq.com/news/2026/05/aws-workspaces-ai-agents/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Cloud+Architecture-news</guid>
      <dc:creator>Steef-Jan Wiggers</dc:creator>
      <dc:date>2026-05-13T07:31:00Z</dc:date>
      <dc:identifier>/news/2026/05/aws-workspaces-ai-agents/en</dc:identifier>
    </item>
  </channel>
</rss>
