<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Eparch blog</title><description>Eparch is an open-source, self-hostable control plane for building, deploying, and governing AI agents on open-weight models — on infrastructure you own.</description><link>https://eparch.ai/</link><item><title>Anatomy of a governed LLM request</title><link>https://eparch.ai/blog/anatomy-of-a-governed-llm-request/</link><guid isPermaLink="true">https://eparch.ai/blog/anatomy-of-a-governed-llm-request/</guid><description>A technical walkthrough of what happens between an agent asking for a completion and a model generating one — JWT auth, OPA policy, rate limits, budgets, semantic cache, routing, and audit.</description><pubDate>Thu, 23 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Introducing Eparch</title><link>https://eparch.ai/blog/introducing-eparch/</link><guid isPermaLink="true">https://eparch.ai/blog/introducing-eparch/</guid><description>Why we built an open-source, self-hostable control plane for governed AI agents on open-weight models — and what ships in v1.</description><pubDate>Thu, 23 Jul 2026 00:00:00 GMT</pubDate></item></channel></rss>