Tosin Akinosho tosin2013

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.

Cursor's Memory Bank

I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read ALL memory bank files at the start of EVERY task - this is not optional.

I HAVE a project manager that I can communicate with using. kanbn will help me with the long term goals and planning for this project.


====================================================
COMMAND: kanbn help

Cursor's Memory Bank

I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read ALL memory bank files at the start of EVERY task - this is not optional.

Memory Bank Structure

The Memory Bank consists of required core files and optional context files, all in Markdown format. Files build upon each other in a clear hierarchy:

flowchart TD

What is this about?

This gist describes how to set up standalone kubelet + CRI-O + CNI on Fedora Core 31. The goal is to place a Kubernetes Pod manifest on an single node and access the application from the network. This guide has been tested on x86-64 and armv7 deployments.

Prepare the system

Make sure the system is up to date:

dnf -y update

My Openshift Cheatsheet

Openshift build secrets for cloning git repos using SSH Keys

To create ssh secret:

oc create secret generic sshsecret \
    --from-file=ssh-privatekey=$HOME/.ssh/id_rsa

OCP 4.2/4.3 All-In-One (UPI mode)

This document assume reader is familiar with the OCP4x installation process.

Before Deployment

Setup the install-config.yaml to deploy a single master and no workers
```
apiVersion: v1
baseDomain: example.com
```

OCP 4.2/4.3 All-In-One (UPI mode)

This document assume reader is familiar with the OCP4x installation process.

Before Deployment

Setup the install-config.yaml to deploy a single master and no workers
```
apiVersion: v1
baseDomain: example.com
```

	# Sources
	# https://openwrt.org/docs/guide-user/network/wifi/guestwifi/guest-wlan
	# https://openwrt.org/docs/guide-user/network/wifi/guestwifi/extras

	WIFI_DEV="radio0"
	WIFI_PASSWORD="guest"

	# Configure network
	uci -q delete network.guest
	uci set network.guest="interface"

	---
	apiVersion: v1
	kind: ServiceAccount
	metadata:
	name: cleaner
	---
	kind: Role
	apiVersion: rbac.authorization.k8s.io/v1
	metadata:
	name: cleaner

	#
	# The following script will
	# - Create Linux bridge $BR_WAN, $BR_LAN
	# - Install IP addresses and basic routes
	# - Enable proxy_arp on $BR_WAN
	# - Enable ip_forward
	# - Enable MASQUERADE on $IF_INET

	# - $BR_LAN, $BR_WAN has to be allowed in ~/.usr/etc/qemu/bridge.conf
	#