Knowledge Compile: Incremental LLM-Powered Knowledge Extraction Without Databases, Embeddings, or Graphs

Compile once, grep forever - 192 ancient texts across 1,800 years, 18x token reduction, $36 total cost, zero infrastructure. LLMs are better curators than retrievers. The companion to grep-is-all-you-need (#4): instead of using LLMs at query time to retrieve, use them at compile time to extract concepts and FAQs that grep can search instantly.Note (2026-05-09): This version bundles English + 中文 in a single PDF (English first, then Chinese), generated directly from the canonical Markdown source files.