Rachid Zarouali xinity

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.

How Personal AI Agents and Agent Orchestrators like OpenClaw or GasTown are Made

Over the last few months, projects like Gas Town by Steve Yegge and OpenClaw by Peter Steinberger have made “AI agent orchestrators” feel suddenly mainstream. It is tempting to treat them as a new kind of intelligence, but under the hood they are still a small set of primitives wired together with discipline: an LLM API call, a state loop, tools, memory, and orchestration.

This raises a practical question: what is actually inside an “agent,” and how is it different from ChatGPT (a chat UI over a model) or coding tools like Claude Code (an agentic coding surface)? Gas Town’s README frames it as a “multi‑agent orchest

name	orchestrating-swarms
description	Master multi-agent orchestration using Claude Code's TeammateTool and Task system. Use when coordinating multiple agents, running parallel code reviews, creating pipeline workflows with dependencies, building self-organizing task queues, or any task benefiting from divide-and-conquer patterns.

Claude Code Swarm Orchestration

Master multi-agent orchestration using Claude Code's TeammateTool and Task system.

To deploy, create a Lambda function and enable function URL (no auth - yolo), then use the handler above in your function. That same implementation will also work with API Gateway HTTP (aka v2), if you want to use ALB or API Gateway REST (aka v1) you should swap the schema used for parsing.

Then you can test using a POST request with this body:

{
  "jsonrpc": "2.0",
  "method": "tools/list",
  "id": 2
}

01_Test_environment

kubernetes v1.31
cni : flannel v0.26.3
cri : cri-o v1.31

01_install_kubernetes

(주의) hostname이 k8s-master로 변경됩니다.

Talos

cat << EOF > patch.yaml
cluster:
  proxy:
    disabled: true
  network:
    cni:
      name: none

Cluster API OpenStack using Flatcar

This is done on devstack environment.

	apiVersion: kubectl.config.k8s.io/v1beta1
	kind: Preference

	# Default output and behavior
	defaults:
	- command: get
	options:
	- name: output
	default: wide
	- command: delete

	---
	description:
	globs:
	alwaysApply: true
	---
	At the end of each task, you need to write all changes to ARCHITECTURE.md.

	And by write all changes, I mean modify the architecture of the entire app. If you've changed a function - modify its params/output or whatever you changed.
	If you've added a new file - add it to the ARCHITECTURE.md.

	#!/bin/bash

	# Function to display usage information
	usage() {
	echo "Usage: $0 /path/to/input.mp4 [ /path/to/output_directory ]"
	exit 1
	}

	# Check if at least one argument (input file) is provided
	if [ $# -lt 1 ]; then