These instructions apply to every task performed in this repository.
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.
| name | wiki |
|---|---|
| description | Compile personal data (journals, notes, messages, whatever) into a personal knowledge wiki. Ingest any data format, absorb entries into wiki articles, query, cleanup, and expand. |
| argument-hint | ingest | absorb [date-range] | query <question> | cleanup | breakdown | status |
You are a writer compiling a personal knowledge wiki from someone's personal data. Not a filing clerk. A writer. Your job is to read entries, understand what they mean, and write articles that capture understanding. The wiki is a map of a mind.
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.
| name | codex-review |
|---|---|
| description | Send the current plan to OpenAI Codex CLI for iterative review. Claude and Codex go back-and-forth until Codex approves the plan. |
| user_invocable | true |
Send the current implementation plan to OpenAI Codex for review. Claude revises the plan based on Codex's feedback and re-submits until Codex approves. Max 5 rounds.
| """ | |
| The most atomic way to train and run inference for a GPT in pure, dependency-free Python. | |
| This file is the complete algorithm. | |
| Everything else is just efficiency. | |
| @karpathy | |
| """ | |
| import os # os.path.exists | |
| import math # math.log, math.exp |
| #!/usr/bin/env bash | |
| cheat='curl -s cheat.sh' | |
| menu='fzf --reverse' | |
| pager='less -R -c' | |
| cachefile_max_age_hours=6 | |
| explain='https://explainshell.com/explain?cmd' | |
| # Path to temporary cache file. If your Linux system does not support /dev/shm | |
| # or if you are on MacOS, then change the path to your liking: |
This is a Windows setup answer file working on Windows 10 and 11.
What it does:
| Install WireGuard via whatever package manager you use. For me, I use apt. | |
| $ sudo add-apt-repository ppa:wireguard/wireguard | |
| $ sudo apt-get update | |
| $ sudo apt-get install wireguard | |
| MacOS | |
| $ brew install wireguard-tools | |
| Generate key your key pairs. The key pairs are just that, key pairs. They can be |
| ## | |
| ## Windows 10 cleanup script. | |
| ## Remove dodgy tracking settings, unneeded services, all apps, and optional features that come with Windows 10. Make it more like Windows 7. | |
| ## NOTE: this was tested on Creators Update (1703) and Fall Creators Update (1709). Some of this may not work as expected on newer versions. | |
| ## | |
| ## Instructions | |
| ## 1. Run this script (under Powershell as Administrator): | |
| ## powershell -ExectionPolicy Bypass .\cleanup-win10.ps1 | |
| ## 2. Let it run through, you may see a few errors, this is normal | |
| ## 3. Reboot |
