Skip to content

Instantly share code, notes, and snippets.

View trq's full-sized avatar

Tony R Quilkey trq

  • Sydney, Australia
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.

@dabit3
dabit3 / pi_tutorial.md
Last active November 16, 2026 05:14
How to Build a Custom Agent Framework with PI: The Agent Stack Powering OpenClaw

PI is a TypeScript toolkit for building AI agents. It's a monorepo of packages that layer on top of each other: pi-ai handles LLM communication across providers, pi-agent-core adds the agent loop with tool calling, pi-coding-agent gives you a full coding agent with built-in tools, session persistence, and extensibility, and pi-tui provides a terminal UI for building CLI interfaces.

These are the same packages that power OpenClaw. This guide walks through each layer, progressively building up to a fully featured coding assistant with a terminal UI, session persistence, and custom tools.

By understanding how to compose these layers, you can build production-grade agentic software on your own terms, without being locked into a specific abstraction.

Pi was created by @badlogicgames. This is a great writeup from him that explains some of the design decisions made when creating it.

The stack

@ChristopherA
ChristopherA / README.md
Last active September 26, 2026 15:49
Self-Improving Claude Code: A bootstrap seed prompt that evolves into a sophisticated configuration system

Self-Improving Claude Code: A Bootstrap Seed

The Hypothesis

A single prompt (~1400 tokens), placed in a project's .claude/CLAUDE.md, can bootstrap a Claude Code instance into a self-improving system — one that captures learnings, extracts patterns, evolves its own configuration, and gets meaningfully better at helping its user with each session.

No pre-built infrastructure required. No user-level config. No hooks, skills, templates, or elaborate folder hierarchies. Just a seed and the affordances Claude Code already provides.

Background

@patricknelson
patricknelson / - Using Xdebug in Docker.md
Last active April 29, 2026 00:48
Using Xdebug in Docker (works with PhpStorm)

Using Xdebug in Docker

Getting setup and running with Xdebug in a docker container these days is now fairly simple and is composed of two main steps:

  1. Ensure you've got XDebug installed and enabled in your PHP docker image, for example:
    # Installing Xdebug with PHP 7.3 images:
    RUN pecl install xdebug \
      && docker-php-ext-enable xdebug
@cdelaitre
cdelaitre / docker-compose-tick.yml
Last active March 22, 2021 20:01
Monitor Docker Swarm with the InfluxData TICK Stack
version: '3'
services:
# FRONT
chronograf:
# Full tag list: https://hub.docker.com/r/library/chronograf/tags/
image: chronograf
deploy:
replicas: 1
placement:
constraints:
@tortuetorche
tortuetorche / FiniteAuditTrailTrait.php
Created July 12, 2016 15:32
FiniteStateMachine and FiniteAuditTrail Traits for Laravel 5.1 (WIP)
<?php namespace App\Finite;
/**
* The FiniteAuditTrail Trait.
* This plugin, for the Finite package (see https://github.com/yohang/Finite), adds support for keeping an audit trail for any state machine.
* Having an audit trail gives you a complete history of the state changes in your stateful model.
* Prerequisites:
* 1. Install Finite package (https://github.com/yohang/Finite#readme)
* 2. Use FiniteStateMachine in your model (https://gist.github.com/tortuetorche/6365575)
* Usage: in your Stateful Class use this trait after FiniteStateMachine trait, like this "use FiniteAuditTrailTrait;".
#!/bin/bash
current=$PWD
cd $HOME
sudo brew install zsh
chsh -s /bin/zsh $USER
brew tap thoughtbot/formulae
#!/bin/bash
current=$PWD
cd $HOME
sudo apt-get install zsh
chsh -s /bin/zsh $USER
wget https://thoughtbot.github.io/rcm/debs/rcm_1.3.0-1_all.deb
@ericelliott
ericelliott / gitclean.sh
Created January 31, 2016 04:57
gitclean.sh - cleans merged/stale branches from origin
git remote prune origin
git branch -r --merged master | egrep -iv '(master|develop)' | sed 's/origin\///g' | xargs -n 1 git push --delete origin
@leedm777
leedm777 / docker-run-ssh.sh
Created August 12, 2015 15:29
Run docker, forwarding your SSH agent into the container
#!/bin/sh
#
# Forwards SSH agent into a Docker container running in the active
# docker-machine
#
PROGNAME=$(basename $0)
NAME=$(docker-machine active)