<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Self-Hosted on Phil Wheat</title><link>https://philwheat.net/tags/self-hosted/</link><description>Recent content in Self-Hosted on Phil Wheat</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Tue, 13 Oct 2026 09:00:00 -0500</lastBuildDate><atom:link href="https://philwheat.net/tags/self-hosted/index.xml" rel="self" type="application/rss+xml"/><item><title>Gamentic</title><link>https://philwheat.net/links/gamentic/</link><pubDate>Tue, 13 Oct 2026 09:00:00 -0500</pubDate><guid>https://philwheat.net/links/gamentic/</guid><description>&lt;p&gt;Self-hosted dungeon RPG.&lt;/p&gt;&#10;&lt;p&gt;Gamentic&amp;rsquo;s docs/blueprints page describes the architecture in one line: a self-hosted AI dungeon RPG where one local LLM plays every role through purpose-built contexts (agents); whatever it wants to change in the world must pass a validated tool into SQLite as the single source of truth; a FastAPI &amp;ldquo;brain&amp;rdquo; resolves one turn per request and pushes late media over SSE; the frontend is a no-build vanilla SPA, with image and voice as optional local services. The site is an interactive blueprint of the agents, engine, state, and repo tree. A nicely disciplined pattern for LLM-with-tooling-state projects.&lt;/p&gt;</description></item><item><title>RAGFlow</title><link>https://philwheat.net/links/ragflow/</link><pubDate>Tue, 13 Oct 2026 08:49:00 -0500</pubDate><guid>https://philwheat.net/links/ragflow/</guid><description>&lt;p&gt;RAGFlow is an open-source (infiniflow/ragflow) &amp;ldquo;context layer&amp;rdquo; for agents: an ingestion pipeline that parses multi-format documents into rich semantic representations (template-based, layout-aware chunking is the flagship claim — tables and structure included), hybrid retrieval combining vector search + BM25 + custom scoring and re-ranking, and a visual agent-workflow builder with MCP/tool integration. Hosted cloud with a free tier, or self-hosted from GitHub. The deep chunking approach is what &amp;ldquo;implicit data&amp;rdquo; extraction would rest on; worth a hands-on eval against txtai given the pace of change.&lt;/p&gt;</description></item></channel></rss>