Skip to content

Instantly share code, notes, and snippets.

@rohitg00
rohitg00 / llm-wiki.md
Last active November 19, 2026 11:29 — forked from karpathy/llm-wiki.md
LLM Wiki v2 — extending Karpathy's LLM Wiki pattern with lessons from building agentmemory

LLM Wiki v2

A pattern for building personal knowledge bases using LLMs. Extended with lessons from building agentmemory 20K+ Stars ⭐️, 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.

What the original gets right

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.

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.

@aczw
aczw / update-content.yml
Last active September 13, 2026 20:06
GitHub Actions workflow for syncing Obsidian vault and Quartz (using Bun). Replace the placeholder values as necessary.
name: Update vault content
on:
schedule:
- cron: '0 11 * * MON' # Run every Monday at 11 AM UTC (6 AM EST, 7 AM EDT)
workflow_dispatch:
jobs:
update_vault_content:
runs-on: ubuntu-latest
@Cortexelus
Cortexelus / udio.py
Last active November 20, 2024 02:03
Automate Udio (2024-04-13)
# AUTOMATE UDIO
# by DADABOTS dadabots.com
# was working on 2024-04-13
# tldr; get your login cookie, use it to automate udio from python
import requests
import json
from time import sleep
import re
@alexchexes
alexchexes / CHANGELOG.md
Last active November 12, 2026 17:54
ChatGPT web-interface width fix (and other UI improvements)

2026-09-26

  • OpenAI rewrote the whole UI markup, breaking most features. This update fixes the essentials: chat width and the eye-bleeding black background.

2026-07-23

  • Fix/improve "Chat|Work" toggle: add an accent color for the active one, and remove styles meant for in-chat top bar buttons.

2026-07-19

  • Update for recent UI changes (black background bleeding in dark theme)

2026-07-09

@mattdesl
mattdesl / model.py
Created November 2, 2023 20:29
fork of latent consistency model with a couple small perf tweaks
import os
import torch
import time
from diffusers import DiffusionPipeline, AutoencoderTiny
from collections import namedtuple
PredictionResult = namedtuple('PredictionResult', [
'latents',
'step',
'steps',
@oclero
oclero / prettier-config-vscode.md
Last active February 21, 2026 13:22
Prettier configuration for VS Code and Hugo

Standard Way

  1. At the root of the repository, create a .prettierrc file:

    {
      "plugins": ["prettier-plugin-go-template"],
      "overrides": [
        {
          "files": ["*.html"],
@garg-aayush
garg-aayush / Steps_multiple_cuda_environments.md
Last active August 12, 2026 20:21
Managing multiple CUDA versions using environment modules in Ubuntu

Steps to manage multiple CUDA environments

Latest Update: May 19th, 2024

This gist contains all the steps required to:

  • Install multiple CUDA versions (e.g., CUDA 11.8 and CUDA 12.1
  • Manage multiple CUDA environments on Ubuntu using the utility called environment modules.
  • Use this approach to avoid CUDA environment conflicts.

Environment Modules is a package that provides for the dynamic modification of a user's environment via modulefiles. You can find more on it at https://modules.readthedocs.io/en/latest/

@coltonbh
coltonbh / docker-swarm-gpu.md
Last active July 20, 2026 22:42
Docker Swarm GPU Support

GPU Support For Docker Swarm

Docker compose has nice support for GPUs, K8s has moved their cluster-wide GPU scheduler from experimental to stable status. Docker swarm has yet to support the device option used in docker compose so the mechanisms for supporting GPUs on swarm are a bit more open-ended.

Basic documentation

@Shivampanwar
Shivampanwar / Install CUDA pytorch tensorflow.md
Last active November 12, 2020 20:10
Installing any version of CUDA on Ubuntu and installing GPU versions of both torch and tensorflow

It contains steps for installing CUDA. It further shows how one can install Tensorflow and Pytorch and use GPUs with them.Our motive is to get output as in the image below,

Cuda_TF_torch

where nvidia-smi, nvcc --version, torch.cuda.is_available(),tf.test.gpu_devic_name() all are working. Let's go then. I will specifically install CUDA 10.1 where both Tensorflow and Pytorch works fine.