https://archworks.co/tags/agents/enSun, 07 Jun 2026 00:00:00 +0000https://archworks.co/docs/self-hosted-llm-stack/Sun, 07 Jun 2026 00:00:00 +0000https://archworks.co/docs/self-hosted-llm-stack/The full writeup: a GPU host running llama.cpp + llama-swap behind a gateway, the OpenCode agent runtime on top, the single-slot constraint and the agents built around it, the five subagent rules, three-layer skills, a memory layer that learns, and the serving-optimization methodology that multiplied throughput on the same hardware.