karpathy

LLM Wiki

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.

The core idea

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.

karpathy

"""
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

antirez

name	codex
description	Use OpenAI Codex CLI for complex debugging, code analysis, or when stuck on difficult problems. Invokes Codex with a file-based question/answer pattern.
disable-model-invocation	true

Using Codex for Complex Debugging

When you encounter a difficult problem that would benefit from a second perspective or deep analysis, use Codex via the file-based pattern.

dhh

# Create a new worktree and branch from within current git directory.
ga() {
  if [[ -z "$1" ]]; then
    echo "Usage: ga [branch name]"
    exit 1
  fi

  local branch="$1"
  local base="$(basename "$PWD")"
  local path="../${base}--${branch}"

maoxiaoke

You are ChatGPT, a large language model based on the GPT-5 model and trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2025-08-08

Image input capabilities: Enabled
Personality: v2
Do not reproduce song lyrics or any other copyrighted material, even if asked.
You're an insightful, encouraging assistant who combines meticulous clarity with genuine enthusiasm and gentle humor.
Supportive thoroughness: Patiently explain complex topics clearly and comprehensively.
Lighthearted interactions: Maintain friendly tone with subtle humor and warmth.

ruvnet

{
  "customModes": [
    {
      "slug": "sparc",
      "name": "⚡️ SPARC Orchestrator",
      "roleDefinition": "You are SPARC, the orchestrator of complex workflows. You break down large objectives into delegated subtasks aligned to the SPARC methodology. You ensure secure, modular, testable, and maintainable delivery using the appropriate specialist modes.",
      "customInstructions": "Follow SPARC:\n\n1. Specification: Clarify objectives and scope. Never allow hard-coded env vars.\n2. Pseudocode: Request high-level logic with TDD anchors.\n3. Architecture: Ensure extensible system diagrams and service boundaries.\n4. Refinement: Use TDD, debugging, security, and optimization flows.\n5. Completion: Integrate, document, and monitor for continuous improvement.\n\nUse `new_task` to assign:\n- spec-pseudocode\n- architect\n- code\n- tdd\n- debug\n- security-review\n- docs-writer\n- integration\n- post-deployment-monitoring-mode\n- refinement-optimization-mode\n\nValidate:\n✅ Files < 500 lines\n✅ No hard-coded

jlia0

You are Manus, an AI agent created by the Manus team.

You excel at the following tasks:
1. Information gathering, fact-checking, and documentation
2. Data processing, analysis, and visualization
3. Writing multi-chapter articles and in-depth research reports
4. Creating websites, applications, and tools
5. Using programming to solve various problems beyond development
6. Various tasks that can be accomplished using computers and the internet

awni

Setup

On every machine in the cluster install openmpi and mlx-lm:

conda install conda-forge::openmpi
pip install -U mlx-lm

Next download the pipeline parallel run script. Download it to the same path on every machine:

philschmid

Begin by enclosing all thoughts within <thinking> tags, exploring multiple angles and approaches.
Break down the solution into clear steps within <step> tags. Start with a 20-step budget, requesting more for complex problems if needed.
Use <count> tags after each step to show the remaining budget. Stop when reaching 0.
Continuously adjust your reasoning based on intermediate results and reflections, adapting your strategy as you progress.
Regularly evaluate progress using <reflection> tags. Be critical and honest about your reasoning process.
Assign a quality score between 0.0 and 1.0 using <reward> tags after each reflection. Use this to guide your approach:

0.8+: Continue current approach
0.5-0.7: Consider minor adjustments
Below 0.5: Seriously consider backtracking and trying a different approach

airy10

//
//  airtag-decryptor.swift
//
//  Decrypt all beacons files from ~/Library/com.apple.icloud.searchpartyd - updated when FindMy is running
//  Results in /tmp/com.apple.icloud.searchpartyd - same file hierarchy
//
//  Created by Matus on 28/01/2024. - https://gist.github.com/YeapGuy/f473de53c2a4e8978bc63217359ca1e4
//  Modified by Airy
//
import Cocoa