Alexandre Girard Davila alx

Depends on:

Octopress git repo
tar
rsync
rake

Fill in the variables appropriately and copy to hooks/post-receive in your bare git repo

git_branch: git branch which holds the source files for the live site

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.

	check process merb_app_master
	with pidfile /home/deploy/legodata/slice/shared/pids/production-merb.main.pid
	start program = "/home/deploy/bin/monit_merb_mpc slice start_master /home/deploy/legodata -c2 -n4000"
	stop program = "/home/deploy/bin/monit_merb_mpc slice stop_master /home/deploy/legodata"
	#if totalmem is greater than 80.0 MB for 2 cycles then restart # eating up memory?
	group master.slice.legodata.com

	# Worker configuration (one for each worker port required)
	check process merb_app_4000
	with pidfile /home/deploy/legodata/slice/shared/pids/production-merb.4000.pid

	/* The API controller
	Exports 3 methods:
	* post - Creates a new thread
	* list - Returns a list of threads
	* show - Displays a thread and its posts
	*/


	var Thread = require('../models/thread.js');
	var Post = require('../models/post.js');