https://whitematter.tech/tags/hermes/ Recent content in Hermes on WhiteMatterTech https://whitematter.tech/images/whitemattertech-blog-thumbnail.png https://whitematter.tech/images/whitemattertech-blog-thumbnail.png Hugo -- 0.142.0 en 2026 WhiteMatterTech Mon, 31 Aug 2026 00:00:00 +0000 https://whitematter.tech/posts/hermes-encrypted-agent-authority/ Mon, 31 Aug 2026 00:00:00 +0000 https://whitematter.tech/posts/hermes-encrypted-agent-authority/ <hr> <h1 id="introduction">Introduction</h1> <p>Hermes is the agent I use when a conversation has to reach the infrastructure. I address <code>@hermes:white.fm</code> in an end-to-end encrypted Matrix room. Hermes reasons through the local model route in my cluster, then invokes a finite set of tools against services with their own operational boundaries.</p> <p>Three previous pieces describe the components in isolation: <a href="https://whitematter.tech/posts/heterogeneous-ollama/">the local Ollama router</a>, <a href="https://whitematter.tech/posts/encrypted-matrix-notification-hub/">the encrypted Matrix notification hub</a>, and <a href="https://whitematter.tech/posts/mcp-server-fleet/">the MCP server fleet</a>. Hermes is where those systems meet. Matrix provides the private conversation, Ollama provides the default inference path, and Model Context Protocol (MCP) servers supply the functions through which an answer may become an action.</p>