rohitg00

LLM Wiki v2

A pattern for building personal knowledge bases using LLMs. Extended with lessons from building agentmemory 10K Stars ⭐️, a persistent memory engine for AI coding agents.

This builds on Andrej Karpathy's original LLM Wiki idea file. Everything in the original still applies. This document adds what we learned running the pattern in production: what breaks at scale, what's missing, and what separates a wiki that stays useful from one that rots.

What the original gets right

The core insight is correct: stop re-deriving, start compiling. RAG retrieves and forgets. A wiki accumulates and compounds. The three-layer architecture (raw sources, wiki, schema) works. The operations (ingest, query, lint) cover the basics. If you haven't read the original, start there.

mvadu

#!/bin/bash
#~/bin/upnpPortMapper.sh
#sudo apt-get install miniupnpc
#crontab -l | grep upnp || echo $(crontab -l ; echo '*/5 * * * * ~/bin/upnpPortMapper.sh  >/dev/null 2>&1') | crontab -

export LC_ALL=C
router=$(ip r | grep default | cut -d " " -f 3)
gateway=$(upnpc -l | grep "desc: http://$router:[0-9]*/rootDesc.xml" | cut -d " " -f 3)
ip=$(upnpc -l | grep "Local LAN ip address" | cut -d: -f2)

attacus

This guide is unmaintained and was created for a specific workshop in 2017. It remains as a legacy reference. Use at your own risk.

Running your own encrypted chat service with Matrix and Riot

Workshop Instructor:

• Lilly Ryan @attacus_au

This workshop is distributed under a CC BY-SA 4.0 license.

What are we doing here?

pklaus

#undef HID_ENABLED

// Arduino Due ADC->DMA->USB 1MSPS
// by stimmer
// from http://forum.arduino.cc/index.php?topic=137635.msg1136315#msg1136315
// Input: Analog in A0
// Output: Raw stream of uint16_t in range 0-4095 on Native USB Serial/ACM

// on linux, to stop the OS cooking your data: 
// stty -F /dev/ttyACM0 raw -iexten -echo -echoe -echok -echoctl -echoke -onlcr