Wiring the local model fleet into Coder Agents forced a realization. A policy router ignores the model name on the request and chooses a backend from the request itself, so Coder needs one generic default model instead of one entry per backend.
Before I settle the local model policy for the homelab router, I ran GPT-5.5, Strix Qwen, RTX 5090 Qwen, and Spark DeepSeek through the same Coder Agents feature task. DeepSeek won the implementation quality round, while Strix taught me why policy needs speed data too.
After adding Strix Halo to the homelab, I wired Strix, Spark, and the RTX 5090 workstation into Coder Agents as explicit model choices, with the policy router still handling the default local path.
A random Tuesday sends an agent over SSH into the homelab to check every piece of software running there. Coder jumps two full versions, cloudflared and RustDesk get patched, and llama.cpp pulls in 317 commits, all with zero manual steps.
My gaming rig’s Windows partition used to cost me 15-45 minutes of manual clicking every time I booted into it. One afternoon: a Coder workspace talking to it over Tailscale and SSH, an inventory script that catalogs every update channel on the machine, three Scheduled Tasks that actually do the work, a toast notification bug that took longer to fix than the automation itself, and a Next.js dashboard on Vercel to see it all without ever touching the machine.
115 days after building this blog from a cabana in Cabo, I spent one afternoon — 2:54 PM to 6:23 PM, back to back — running a chain of admin panel improvements: image upload, a visual TODO viewer, drag-and-drop reorder, a “launch agent” button, four rounds of troubleshooting it, and three mobile layout bugs found by actually using it on my phone at the end.
An AI Transformation team at a Fortune 500 financial services firm told me they’ve shipped 19,000 skills across 175 unique Coder workspace types in six months. That’s not a headcount story. It’s proof that as AI intelligence becomes a commodity, the real competitive advantage shifts to how businesses codify and distribute their proprietary workflows.
I kept typing the same paragraph into Coder Agents chat every time a session ran long or I needed to SSH into the homelab. A Slack conversation with a colleague turned that annoyance into five reusable slash commands — and along the way I discovered Coder Agents actually has two entirely separate skill systems, only one of which the `/` menu will ever show you.
Sometimes your agent’s turn just ends with no result — no error, no output, nothing. Nudging it usually gets you the answer that was there the whole time. It’s tempting to write that off as a UX hiccup. Sometimes it’s a real bug, and finding out is part of the fun of vibe coding. A walkthrough of why that’s worth investigating, when it crosses the line into “file this,” and how to do it well — using a hanging GitHub tool call as the live example.
I put Qwen 3.6 27B, Qwen 3.6 35B-A3B, Qwythos-9B, GLM-4.7-Flash, and Nemotron-3-Nano through the same real coding task on my homelab RTX 5090. Along the way I had to live-patch two separate llama.cpp bugs — and even after fixing them, I couldn’t fully prove one model’s failure wasn’t the harness’s fault.
I gave five local LLMs and one frontier cloud model the same coding task on my homelab: build a tag manager for the blog’s admin panel. Only two shipped anything. Here’s what happened.
A second user joined the homelab Coder instance and couldn’t push to GitHub. What looked like a missing config turned into five chained problems, a domain migration aftershock, an agent-debugging-an-agent meta-moment, and the discovery that the same credential helper bug had been “fixed” four times in ten days — and never actually deployed.
While waiting for massive open source models to download, I tackled the homelab backlog: custom domain for my Coder instance via Cloudflare Tunnel, security hardening (with a gotcha that could kill your AI search visibility), and wiring up MCP servers to give agents superpowers.