Building My Own Openclaw With Local LLM Model: The Xoul Development Story

Table of Contents Why I built it One-Click Setup Early Technical Decisions Architecture Overview QEMU VM — Giving the AI a Body Agent Loop — The 2-Phase Structure Multi-Model Tool Call Parser 3-Tier Memory Tool System and Self-Evolution Host Security — Tier 1/2 Model Desktop Client Multi-Client AI Evolving AI — The Test-Driven Evolution Loop Retrospective 1. Why I built it My day job involves building simulation software at a semiconductor company. In early 2025, while developing "Vibe Simulation" software utilizing LLMs, I really started to feel the potential of AI agents. Then, trying the Antigravity + Opus 4.6 combo at home totally blew my mind (I can't use it at work due to strict security policies...). Watching the AI write code, debug, and even seamlessly refactor made me wonder, "What if I expanded this into my daily life?" Combine that with the buzz around OpenClaw in the community—which the creator apparently built in just 10 days—and I was shocked once again. The catch? OpenC