Joon An joonan30

LLM Wiki: Building a Personal Knowledge Base for Academic Papers with AI Agents

A methodology for using Claude Code + OpenAI Codex CLI to build and maintain a structured, searchable wiki from academic PDFs — designed for researchers who read dozens of papers and want compounding knowledge.

The Concept

Inspired by Karpathy's LLM Wiki pattern:

Original PDF → LLM markdown summary (sources/) → Structured wiki page (wiki/) → Overview synthesis

LLM Wiki — AI for Biology

중요: Git 워크트리 사용 금지

모든 파일은 메인 브랜치에 직접 저장한다. Git worktree를 생성하지 않는다.

A personal knowledge base for AI/deep learning papers in biology research. Follows Karpathy's LLM Wiki pattern: Original PDF → LLM markdown summary (sources) → Structured wiki page (wiki).

Language policy: All wiki content is in English. Conversation with Claude can be in Korean or English.

	import sys

	match = []
	with open(sys.argv[1]) as fh:
	for line in fh:
	if line in match:
	pass
	else:
	match.append(pass)

	---
	- hosts: <hostname>
	remote_user: ec2-user
	vars:
	s3_spiegel_path: user_s3bucket/path/
	remote_spiegel_dir: data

	tasks:
	- name: Installing R
	yum: name=R state=latest

	# Get date
	date = sapply(strsplit(as.character(Sys.Date()), '-', fixed = T), paste, collapse = "")

	## biomart and AnnotationDbi
	# Map a gene id to get an ENTREZ id.
	require(AnnotationDbi)
	require(org.Mm.eg.db) # mice

	entrez = mapIds(org.Mm.eg.db,
	keys=ens_gene, # has to be a vector

	# terminal color scheme
	export PS1="\[\033[36m\]\u\[\033[m\]@\[\033[32m\]\h:\[\033[33;1m\]\w\[\033[m\]\$ "
	export CLICOLOR=1
	export LSCOLORS=ExFxBxDxCxegedabagacad
	alias ls='ls -GFh'

	# python 3
	import multiprocessing as mp
	from multiprocessing import Pool, cpu_count

	number_threads = 8

	## Creating a pool for parallel processing
	pool = mp.Pool(number_threads)
	pool.imap_unordered(os.system, cmds )
	pool.close()

	// Use Gists to store code you would like to remember later on
	console.log(window); // log the "window" object to the console

	library(rtracklayer)
	library(tidyverse)

	d <- rtracklayer::import('gencode.v19.annotation.gtf.gz') %>%
	as.data.frame() %>%
	filter(type == 'transcript')