Skip to content

Instantly share code, notes, and snippets.

View Gr1N's full-sized avatar
🚴‍♂️

Nikita Grishko Gr1N

🚴‍♂️
View GitHub Profile

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.

@danieleggert
danieleggert / GPG and git on macOS.md
Last active March 20, 2026 13:01
How to set up git to use the GPG Suite

GPG and git on macOS

Setup

No need for homebrew or anything like that. Works with https://www.git-tower.com and the command line.

  1. Install https://gpgtools.org -- I'd suggest to do a customized install and deselect GPGMail.
  2. Create or import a key -- see below for https://keybase.io
  3. Run gpg --list-secret-keys and look for sec, use the key ID for the next step
  4. Configure git to use GPG -- replace the key with the one from gpg --list-secret-keys
@dlebech
dlebech / cache.py
Created March 20, 2016 16:51
Python LRU cache that works with coroutines (asyncio)
"""Global LRU caching utility. For that little bit of extra speed.
The caching utility provides a single wrapper function that can be used to
provide a bit of extra speed for some often used function. The cache is an LRU
cache including a key timeout.
Usage::
import cache
@cache.memoize
@takluyver
takluyver / asyncio_magic.py
Created January 25, 2016 11:53
Cell magic for 'await' expressions in IPython
# (c) Thomas Kluyver, 2016
# Use it under the MIT license
# This is fairly experimental. Use at your own risk.
import ast
from ast import Call, Attribute, Name, Load
import asyncio as asyncio_mod
#import astpp
from IPython.utils.text import indent
@paulmiu
paulmiu / install_mosh.md
Last active November 8, 2019 18:30
Set up mosh (mobile shell) on Uberspace and Mac OS X

##Set up mosh (mobile shell) on Uberspace and Mac

First of all you have to email the Uberspace team (hallo@uberspace.de) and ask for opening an UDP port for mosh (don't forget to mention your username and uberspace server [you can get it with the command hostname]).

####On the Uberspace server:

Issue following command to execute the script from below:

curl -L http://goo.gl/PBo45c | bash
@region23
region23 / golang_books_sites.md
Last active April 3, 2026 19:08
Полезные ресурсы для изучающих Go

На русском языке

Русскоязычные сайты и сообщества

English resources

@joegoggins
joegoggins / .vimrc
Last active November 25, 2024 16:24
Mac Vim .vimrc file
" Use Vim settings, rather then Vi settings (much better!).
" This must be first, because it changes other options as a side effect.
set nocompatible
" ================ General Config ====================
set number "Line numbers are good
set backspace=indent,eol,start "Allow backspace in insert mode
set history=1000 "Store lots of :cmdline history
set showcmd "Show incomplete cmds down the bottom
@sloria
sloria / bobp-python.md
Last active July 9, 2026 10:52
A "Best of the Best Practices" (BOBP) guide to developing in Python.

The Best of the Best Practices (BOBP) Guide for Python

A "Best of the Best Practices" (BOBP) guide to developing in Python.

In General

Values

  • "Build tools for others that you want to be built for you." - Kenneth Reitz
  • "Simplicity is alway better than functionality." - Pieter Hintjens
@dypsilon
dypsilon / frontendDevlopmentBookmarks.md
Last active June 30, 2026 18:13
A badass list of frontend development resources I collected over time.