https://archworks.co/tags/ai/enSun, 14 Jun 2026 00:00:00 +0000https://archworks.co/posts/knowledge-graph-from-my-own-words/Sun, 14 Jun 2026 00:00:00 +0000https://archworks.co/posts/knowledge-graph-from-my-own-words/RAG over your notes gives an AI a pile of text. A knowledge graph gives it entities and relationships. Here is how I build one only from my own words: collect, extract triples, dedupe, normalise, and read and write it live during a conversation.https://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.https://archworks.co/posts/self-hosted-llms-subagents-skills/Sun, 07 Jun 2026 00:00:00 +0000https://archworks.co/posts/self-hosted-llms-subagents-skills/Five layers on top of a local model: a single-slot model swap, model tiering, narrow agents with isolated context, skills that wrap an API as one tool call, and a memory layer that learns from its own runs. The discipline matters more than the model size.