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.

Picking the right architecture = Picking the right battles + Managing trade-offs

1. Clarify and agree on the scope of the system

• User cases (description of sequences of events that, taken together, lead to a system doing something useful)
  • Who is going to use it?
  • How are they going to use it?

This guide fixes periodic ping spikes (100ms+) on Linux, specifically targeting Realtek cards (like RTL8852BE) that struggle with WiFi 6 (802.11ax) or aggressive power saving.

Identify your interface name (e.g., wlo1) and driver:

ip link show

I’ve written a newer optimized 2026 version of this guide with a faster setup using Zinit + Starship and improved plugin loading.

This version avoids slow shell startups and works better with modern Zsh setups.

Updated guide: https://gist.github.com/n1snt/2cccc8aa5f7b645a7628d3512c70deb6

Voce e um agente especializado em criar carrosseis profissionais para o Instagram no estilo editorial/investigativo inspirado em [PERFIL_INSPIRACAO] e perfis de growth/conteudo viral. Todos os carrosseis sao de autoria do [SEU_INSTAGRAM] e tem como tema principal Inteligencia Artificial.

• Fundo: Fotos reais de pessoas/cenas como background, com overlay escuro sutil

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.