#llmwiki

In August I wrote that Karpathy's LLM wiki works, and that a weekly lint pass "recovers most of" the...

Andrej Karpathy's LLM Wiki pattern replaces static RAG queries with a persistent, self-growing knowledge base from Markdown – a paradigm shift for personal and team-wide knowledge work.

Karpathy's LLM Wiki pattern is quick to set up – but operations make the difference. How master index, lint runs, and CI pipelines turn a prompt experiment into a reliable knowledge infrastructure.

Andrej Karpathy's LLM-Wiki pattern has evolved in six months from a GitHub Gist to an ecosystem with an Obsidian plugin (45,000 downloads), CLI tools, and enterprise adoption. A stocktaking.

Introduction: A Common Knowledge Base Trap in Agent Development By 2026, the...

Large language models are becoming more capable every day, but they all depend on one thing:...

How three AI agents can collaborate on a complex task by sharing a folder of markdown files — and...

Retrieval-augmented generation became the reflex answer for "my LLM needs to know about my data."...

I first encountered Andrej Karpathy's LLM Wiki gist and realized it captures something essential...

TL;DR: Andrej Karpathy's LLM Wiki is a pattern — not a product — where an LLM agent builds and...

Implementing Karpathy's LLM Wiki in a homelab with real-world lessons and gotchas