<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Projects on Vitor Pontual | The VeePee Hub</title>
    <link>https://vitorpontual.com/tags/projects/</link>
    <description>Recent content in Projects on Vitor Pontual | The VeePee Hub</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Wed, 18 Feb 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://vitorpontual.com/tags/projects/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>The February Shipping Spree</title>
      <link>https://vitorpontual.com/posts/february-shipping-spree/</link>
      <pubDate>Wed, 18 Feb 2026 00:00:00 +0000</pubDate>
      <guid>https://vitorpontual.com/posts/february-shipping-spree/</guid>
      <description>&lt;p&gt;February is shaping up to be the month the commit graph caught fire. After a quiet summer and a slow ramp through the fall, January flipped a switch — and February just kept going. 429 contributions in the last year, and most of the green is piled into the last eight weeks.&lt;/p&gt;&#xA;&lt;p&gt;The result? Four new services joining the three I &lt;a href=&#34;https://vitorpontual.com/posts/new-self-hosted-services/&#34;&gt;launched earlier this month&lt;/a&gt;. That brings the total to seven self-hosted, AI-powered tools running on my home infrastructure — no cloud subscriptions, no API bills, all local.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Putting Claude to Work!</title>
      <link>https://vitorpontual.com/posts/new-self-hosted-services/</link>
      <pubDate>Wed, 11 Feb 2026 00:00:00 +0000</pubDate>
      <guid>https://vitorpontual.com/posts/new-self-hosted-services/</guid>
      <description>&lt;p&gt;I&amp;rsquo;ve been busy building AI-powered tools on my self-hosted infrastructure. Today I&amp;rsquo;m adding three new services to the site:&lt;/p&gt;&#xA;&lt;h2 id=&#34;newsfeed&#34;&gt;Newsfeed&lt;/h2&gt;&#xA;&lt;p&gt;An AI-powered news aggregator inspired by Kevin Rose&amp;rsquo;s Nylon project. It pulls from 800+ RSS feeds, uses embeddings to cluster related articles into multi-source stories, and generates LLM headlines and syntheses. A Gravity Engine scores stories based on source count, author reputation, and my personal interests.&lt;/p&gt;&#xA;&lt;h2 id=&#34;ollama-fleet-manager&#34;&gt;Ollama Fleet Manager&lt;/h2&gt;&#xA;&lt;p&gt;A dashboard and intelligent proxy for managing multiple Ollama GPU servers. It monitors model states, VRAM usage, and system metrics in real-time. The proxy emulates the standard Ollama API, routing requests to the optimal server — prioritizing those with the model already loaded.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
