<?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>AnythingLLM on Vinh Thang's AI Tech Notes</title><link>https://vinhthang.dev/tags/anythingllm/</link><description>Recent content in AnythingLLM on Vinh Thang's AI Tech Notes</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 24 Aug 2026 18:43:00 +0700</lastBuildDate><atom:link href="https://vinhthang.dev/tags/anythingllm/index.xml" rel="self" type="application/rss+xml"/><item><title>Autonomous AI Infrastructure: AnythingLLM, PostgreSQL 18 pgvector, and the Antigravity CLI (agy) System Agent</title><link>https://vinhthang.dev/posts/self-hosted-ai-agent-architecture/</link><pubDate>Mon, 24 Aug 2026 18:43:00 +0700</pubDate><guid>https://vinhthang.dev/posts/self-hosted-ai-agent-architecture/</guid><description>&lt;p&gt;Most self-hosted AI setups stop at running a basic chat UI connected to a remote API. But what if your self-hosted AI wasn&amp;rsquo;t just a conversational bot, but a &lt;strong&gt;fully empowered autonomous system agent&lt;/strong&gt; capable of managing your infrastructure, installing command-line tools, debugging services, and querying custom vector databases?&lt;/p&gt;
&lt;p&gt;In this post, I will explore our complete self-hosted AI architecture running on an Always Free cloud Kubernetes cluster—featuring &lt;strong&gt;AnythingLLM&lt;/strong&gt;, &lt;strong&gt;PostgreSQL 18 with &lt;code&gt;pgvector&lt;/code&gt;&lt;/strong&gt;, and the &lt;strong&gt;Google Antigravity CLI (&lt;code&gt;agy&lt;/code&gt;)&lt;/strong&gt;.&lt;/p&gt;</description></item></channel></rss>