concept

LLM Wiki

created 2026-04-19 knowledge-management · ai · second-brain

LLM Wiki

The foundational pattern behind the Kulify Second Brain. Proposed by Andrej Karpathy as an alternative to RAG.

Core Idea

Instead of re-deriving knowledge from raw documents on every query (RAG), have the LLM incrementally build and maintain a persistent wiki. Knowledge is compiled once, kept current, and compounds over time.

Three Layers

  1. Raw Sources — Immutable documents (articles, papers, data) that the LLM reads but never modifies
  2. The Wiki — LLM-generated markdown files (summaries, entity pages, concept pages, comparisons). The LLM owns this layer entirely
  3. The Schema — A configuration document (CLAUDE.md) that defines structure, conventions, and workflows. Co-evolved by human and LLM

Three Operations

  • Ingest: Drop a new source → LLM reads it, writes summary, updates 10-15 related wiki pages
  • Query: Ask questions → LLM reads relevant pages, synthesizes answers. Good answers get filed back
  • Lint: Periodically health-check for contradictions, stale claims, orphan pages, missing cross-references

Why It Works

Humans abandon wikis because maintenance burden grows faster than value. LLMs eliminate that cost. The human curates sources, directs analysis, and asks good questions. The LLM handles all bookkeeping.

Karpathy likens this to Vannevar Bush’s 1945 Memex vision — a personal knowledge store with associative trails — where the LLM finally solves the maintenance problem.

  • index.md — Content catalog for finding pages
  • log.md — Chronological append-only record of operations

How We Use It

The kulify Second Brain implements this pattern directly. See CLAUDE.md for the schema.