https://cruver.ai/tags/automation/ Recent content in Automation on Hullabalooing Hugo en Wed, 21 Jan 2026 14:00:00 +0000 https://cruver.ai/second-brain/posts/n8n-mobile-access-via-matrix-1769025724/ Wed, 21 Jan 2026 14:00:00 +0000 https://cruver.ai/second-brain/posts/n8n-mobile-access-via-matrix-1769025724/ <p>My org-roam knowledge base is the center of how I think and work. But it lives in Emacs, which means I can only capture ideas when I&rsquo;m at my computer. I wanted a way to feed my second brain from anywhere, using just my phone—but I refused to put my notes in someone else&rsquo;s cloud. The solution had to be entirely self-hosted. What I built combines Matrix for messaging, n8n for orchestration, and an MCP server that bridges to org-roam, all running on my own infrastructure.</p> https://cruver.ai/gpu-ai/posts/gpu-config-management/ Wed, 21 Jan 2026 00:00:00 -0700 https://cruver.ai/gpu-ai/posts/gpu-config-management/ <p>Dynamic switching between GPU configurations based on workload needs.</p> <h2 id="overview">Overview<a class="anchor" href="#overview">#</a></h2> <p>Rather than running a single fixed configuration, I dynamically switch between GPU configurations. A Python service manages the transitions via HTTP API.</p> <h2 id="available-configurations">Available Configurations<a class="anchor" href="#available-configurations">#</a></h2> <table> <thead> <tr> <th>Config</th> <th>Model</th> <th>Use Case</th> </tr> </thead> <tbody> <tr> <td><code>big-chat</code></td> <td>Llama 3.3 70B (TP=2)</td> <td>Maximum quality chat</td> </tr> <tr> <td><code>coder</code></td> <td>Qwen3 32B (TP=2)</td> <td>Coding tasks with thinking mode</td> </tr> <tr> <td><code>dual-chat</code></td> <td>Qwen3 8B + 14B</td> <td>Two models, different tasks</td> </tr> <tr> <td><code>image-chat</code></td> <td>Qwen 7B + ComfyUI</td> <td>Text + image generation</td> </tr> </tbody> </table> <p>Configuration files are stored as compose YAML files.</p>