A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

Want to inject some flavor into your everyday text chat? You're in luck! Discord uses Markdown, a simple plain text formatting system that'll help you make your sentences stand out. Here's how to do it! Just add a few characters before & after your desired text to change your text! I'll show you some examples...

What this guide covers:

• Text Formatting
• Organizational Text Formatting
  • Headers
• Subtext

다음은 QMD를 설치하고 현재 옵시디언 볼트를 collection으로 추가하는 프롬프트입니다. macOS 기준입니다. 다른 OS에서는 단계별로 보정이 필요합니다.

• macOS, Homebrew 설치됨
• Node.js 또는 Bun 설치됨 (node -v / bun -v로 확인)
• 옵시디언 볼트 루트 디렉토리에서 터미널 실행 (pwd로 확인)
• RAM 16GB 이상 권장 (로컬 임베딩 모델 구동)

A pattern for building personal knowledge bases using LLMs. Extended with lessons from building agentmemory, a persistent memory engine for AI coding agents.

This builds on Andrej Karpathy's original LLM Wiki idea file. Everything in the original still applies. This document adds what we learned running the pattern in production: what breaks at scale, what's missing, and what separates a wiki that stays useful from one that rots.

The core insight is correct: stop re-deriving, start compiling. RAG retrieves and forgets. A wiki accumulates and compounds. The three-layer architecture (raw sources, wiki, schema) works. The operations (ingest, query, lint) cover the basics. If you haven't read the original, start there.

A pattern for building personal knowledge bases using LLMs. Extended with lessons from building agentmemory, a persistent memory engine for AI coding agents.

This builds on Andrej Karpathy's original LLM Wiki idea file. Everything in the original still applies. This document adds what we learned running the pattern in production: what breaks at scale, what's missing, and what separates a wiki that stays useful from one that rots.

The core insight is correct: stop re-deriving, start compiling. RAG retrieves and forgets. A wiki accumulates and compounds. The three-layer architecture (raw sources, wiki, schema) works. The operations (ingest, query, lint) cover the basics. If you haven't read the original, start there.

• Enter plan mode for ANY non-trivial task (3+ steps or architectural decisions)
• If something goes sideways, STOP and re-plan immediately - don't keep pushing
• Use plan mode for verification steps, not just building
• Write detailed specs upfront to reduce ambiguity

• Use subagents liberally to keep main context window clean

Ghostty + Zoxide + Yazi + Oh-My-Zsh 完整配置

• Ghostty - 现代化 GPU 加速终端模拟器
• Zoxide - 智能目录跳转工具（cd 的智能替代）
• Yazi - 快速终端文件管理器
• Oh-My-Zsh - Zsh 配置框架