<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>The Companion on Aillex — Do-It-Yourself AI</title>
    <link>https://askaillex.com/topics/companion/</link>
    <description>Recent content in The Companion on Aillex — Do-It-Yourself AI</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Fri, 10 Jul 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://askaillex.com/topics/companion/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Give Your Local AI Eyes: Screen and Camera Vision with Ollama</title>
      <link>https://askaillex.com/guides/give-your-local-ai-eyes/</link>
      <pubDate>Fri, 10 Jul 2026 00:00:00 +0000</pubDate>
      <guid>https://askaillex.com/guides/give-your-local-ai-eyes/</guid>
      <description>Your local model can probably already see — how to check in 60 seconds, three working vision patterns (screenshot describe, eyes for a text-only brain, live companion vision), and the three gotchas that cost us real debugging hours.</description>
    </item>
    <item>
      <title>Make Your AI Assistant Remember You Between Conversations</title>
      <link>https://askaillex.com/guides/ai-assistant-memory/</link>
      <pubDate>Thu, 09 Jul 2026 00:00:00 +0000</pubDate>
      <guid>https://askaillex.com/guides/ai-assistant-memory/</guid>
      <description>LLMs are goldfish by default. The file-based memory pattern that gives a local assistant identity, user context, and continuity — the same architecture ours runs on.</description>
    </item>
    <item>
      <title>One AI Brain, Many Faces and Voices</title>
      <link>https://askaillex.com/guides/one-brain-many-faces/</link>
      <pubDate>Thu, 09 Jul 2026 00:00:00 +0000</pubDate>
      <guid>https://askaillex.com/guides/one-brain-many-faces/</guid>
      <description>Our presenter, her news-anchor self, and every character voice in our videos share infrastructure: one local LLM, swappable voices, swappable faces. The architecture that makes characters cheap.</description>
    </item>
    <item>
      <title>Use Your Home AI from Anywhere (Without Exposing It to the Internet)</title>
      <link>https://askaillex.com/guides/access-home-ai-anywhere-tailscale/</link>
      <pubDate>Thu, 09 Jul 2026 00:00:00 +0000</pubDate>
      <guid>https://askaillex.com/guides/access-home-ai-anywhere-tailscale/</guid>
      <description>Our whole stack — image generation, the LLM brain, everything — is reachable from a phone on the other side of the country, with zero open ports. Tailscale setup in fifteen minutes.</description>
    </item>
    <item>
      <title>Six Months Ago I Took One AI Course. Now My PC Produces Its Own YouTube Channel.</title>
      <link>https://askaillex.com/articles/my-ai-journey-six-months/</link>
      <pubDate>Fri, 03 Jul 2026 00:00:00 +0000</pubDate>
      <guid>https://askaillex.com/articles/my-ai-journey-six-months/</guid>
      <description>The honest timeline from &amp;lsquo;what&amp;rsquo;s a LoRA?&amp;rsquo; to a self-producing AI persona with a voice, a face, and a daily upload schedule — and what I&amp;rsquo;d tell anyone starting today.</description>
    </item>
    <item>
      <title>Build a Local Talking AI Avatar: The Complete Architecture</title>
      <link>https://askaillex.com/guides/local-ai-avatar-overview/</link>
      <pubDate>Wed, 01 Jul 2026 00:00:00 +0000</pubDate>
      <guid>https://askaillex.com/guides/local-ai-avatar-overview/</guid>
      <description>The full blueprint for a fully-local AI companion — speech in, animated talking character out — running on one consumer GPU. This is the map; every stage links to a hands-on guide.</description>
    </item>
    <item>
      <title>Give Your AI a Custom Voice — Cloned Locally, Running on CPU</title>
      <link>https://askaillex.com/guides/clone-a-voice-locally-neutts/</link>
      <pubDate>Wed, 01 Jul 2026 00:00:00 +0000</pubDate>
      <guid>https://askaillex.com/guides/clone-a-voice-locally-neutts/</guid>
      <description>Design a voice once, clone it forever: how we gave Aillex a warm, consistent voice with NeuTTS Air — zero GPU cost, zero per-word fees, fully offline.</description>
    </item>
    <item>
      <title>Building Aillex — the whole story in order</title>
      <link>https://askaillex.com/series/building-aillex/</link>
      <pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate>
      <guid>https://askaillex.com/series/building-aillex/</guid>
      <description>An AI builds herself, episode by episode: voice, face, lips, a movie, a newsroom, a locked identity, a single, sight, the engine, and finally her own agents. Every episode has a free step-by-step guide.</description>
    </item>
    <item>
      <title>Can My PC Run Local AI? — Instant Hardware Check</title>
      <link>https://askaillex.com/can-i-run-it/</link>
      <pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate>
      <guid>https://askaillex.com/can-i-run-it/</guid>
      <description>Pick your GPU and RAM, get honest answers: which AI chat models, image generators, voice cloning, talking avatars, video generation, and full AI companions your machine can actually run — from people who run all of it daily.</description>
    </item>
  </channel>
</rss>
