Wiki Index
> Content catalog. Every maintained wiki page is listed with a one-line summary.
> Read this first to find relevant pages for any query.
> Last updated: 2026-05-10 | Total pages: 9
Entities
- addy-osmani — Author of the "Agent Harness Engineering" X Article; frames agent quality as model plus harness.
- andrej-karpathy — Person referenced as the inspiration source for the LLM Wiki pattern.
- hermes-agent — Agent framework used here to ingest, query, lint, and maintain the markdown wiki.
- jaya-gupta — Author of "The next biggest moat in AI," framing company shape and talent systems as the durable moat in AI.
Concepts
- harness-engineering — Discipline of improving prompts, tools, context, hooks, sandboxes, memory, and feedback loops around AI agents.
- llm-wiki-pattern — Persistent markdown knowledge base pattern built from raw sources, maintained pages, and schema.
- organizational-moats — Defensibility created by organizational shape, talent density, status, authority, and institutional design.
- self-improving-knowledge-base — Knowledge base workflow where an agent maintains links, summaries, index, and lint health over time.
Comparisons
- llm-wiki-vs-obsidian — Tradeoffs between an agent-maintained LLM Wiki and an Obsidian-centered workflow.
Queries