augustin-laurent

LLM Wiki: Building Durable Memory for AI Agents

Development agents such as Codex, Claude Code, Gemini CLI, or OpenCode can explore a repository, understand an architecture, fix bugs, and produce a significant amount of work. Yet they all face the same fundamental limitation: a large part of what they learn during a task disappears when a new session starts or when the context is compressed.

An agent may spend several minutes understanding why a component uses an apparently strange architecture, discover that an older approach caused a race condition, identify multiple implicit business constraints, and then solve the problem. A few weeks later, a new agent may have to reconstruct the exact same reasoning from the codebase, tickets, ADRs, and Git history.

The LLM Wiki aims to solve this problem.

It is not simply about giving the model more documentation. It is about turning knowledge acquired by humans and agents into persistent, structured, navigable, and continuously maintained memory.

augustin-laurent

Date of the guide : April, 2026

Introduction

In this post, I will provide the setup that makes the most sense on Arch Linux today to install NVIDIA CUDA for a GeForce RTX and newer NVIDIA GPUs. On current Arch, you can install everything you need from the official repositories, so AUR access is not required for the main CUDA setup.

CUDA is NVIDIA GPU computing platform. If you want GPU acceleration for workloads such as PyTorch, TensorFlow, or custom CUDA code, this is the stack you need. NVIDIA CUDA installation docs still focus on officially qualified distros, while TensorFlow explicitly says its Linux GPU instructions officially target Ubuntu and may also work on other distros. This guide is therefore an Arch-oriented practical guide using the current Arch packages and the official framework install methods.

augustin-laurent

Date of the guide : April, 2026

Introduction

In this post, I will provide the solution that worked on my system on how to install Radeon Open Compute (ROCm) on Arch (linux- 6.19.11.arch1-1) for RX 6900 XT (Should work on other 6000 series and more recent). ROCm is an open-source software platform that allows GPU-accelerated computation. This tool is a prerequist to use GPU Acceleration on TensorFlow or PyTorch.

Prerequisites

augustin-laurent

December 3rd 2023

Introduction

In this post, I will provide the solution that worked on my system on how to install Radeon Open Compute (ROCm) on Ubuntu 22.04 for RX 6900 XT (Should work on other 6000 series). ROCm is an open-source software platform that allows GPU-accelerated computation. This tool is a prerequist to use GPU Acceleration on TensorFlow or PyTorch.

Prerequisites