Skip to content

Instantly share code, notes, and snippets.

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.

@rameerez
rameerez / telegram-mtproxy.md
Last active November 11, 2026 00:39
Telegram Proxy How-To: complete and up-to-date MTProxy tutorial

How to set up a Telegram Proxy (MTProxy)

Telegram proxies can help people connect when Telegram is blocked. Telegram apps support them directly, so sharing a proxy can be as simple as sending someone a link.

I've used MTProxy to run my public Telegram proxy, which you can use if you don't want to set up your own.

A proxy cannot simply decrypt Telegram's encrypted message traffic, but it can observe client IP addresses, connection times, traffic volume and destinations. Its logs may retain that information. MTProxy is not a VPN or an anonymity guarantee, and it does not turn ordinary Telegram cloud chats into end-to-end encrypted Secret Chats. Choose an operator you trust.

Read this before choosing the software

@devinschumacher
devinschumacher / cloud-gpus.md
Last active August 28, 2026 05:23
Cloud GPU Hosting Rentals // The Best Servers, Services & Providers [RANKED!]
title The Best Cloud GPU Providers for Artificial Intelligence & Machine Learning
tags
cloud gpu providers
cloud gpu
artificial intelligence

Cloud GPUs: Servers, Providers & Everything You Would Ever Need

@sts10
sts10 / rust-command-line-utilities.markdown
Last active October 30, 2026 05:57
A curated list of command-line utilities written in Rust

A curated list of command-line utilities written in Rust

Note: I have moved this list to a proper repository. I'll leave this gist up, but it won't be updated. To submit an idea, open a PR on the repo.

Note that I have not tried all of these personally, and cannot and do not vouch for all of the tools listed here. In most cases, the descriptions here are copied directly from their code repos. Some may have been abandoned. Investigate before installing/using.

The ones I use regularly include: bat, dust, fd, fend, hyperfine, miniserve, ripgrep, just, cargo-audit and cargo-wipe.

  • atuin: "Magical shell history"
  • bandwhich: Terminal bandwidth utilization tool
@v0lkan
v0lkan / nginx.conf
Last active October 12, 2026 05:01
Configuring NGINX for Maximum Throughput Under High Concurrency
user web;
# One worker process per CPU core.
worker_processes 8;
# Also set
# /etc/security/limits.conf
# web soft nofile 65535
# web hard nofile 65535
# /etc/default/nginx
@plentz
plentz / nginx.conf
Last active November 8, 2026 01:36
Best nginx configuration for improved security(and performance)
# to generate your dhparam.pem file, run in the terminal
openssl dhparam -out /etc/nginx/ssl/dhparam.pem 2048