silverkors

# -*- coding: utf-8 -*-
from scene import *
from PIL import Image, ImageDraw, ImageFont


row_rects = []
row_keys = []
n_row_rects = []
n_row_keys = []

silverkors

# -*- coding: utf-8 -*-
from scene import *
from time import time
from copy import deepcopy
from PIL import Image, ImageDraw, ImageFont


global EventQ

def p_click():

silverkors

# -*- coding: utf-8 -*-
import os, sys, editor, shutil
from glob import glob
from scene import *
from time import time
from copy import deepcopy
from PIL import Image, ImageDraw, ImageFont

# https://gists.github.com/4034526

silverkors

Keybase proof

I hereby claim:

• I am silverkors on github.
• I am silverkors (https://keybase.io/silverkors) on keybase.
• I have a public key ASDbC1Tjx_lUDRkmnr5yA7RFXiUCMhqgP-7-SsGMobbxRQo

To claim this, I am signing this object:

silverkors

Ora CRM & Dossier System Architecture

System Overview

The Ora CRM and dossier system is a sophisticated relationship management platform built on PostgreSQL with pgvector extensions. It combines automatic signal extraction, time-decay scoring, contact lifecycle management, and comprehensive relationship tracking.

Key Stats:

• 16 service modules (~5,100 LOC)
• 10 core database tables
• 4 signal sources (iMessage, Email, OraChat, Archive)

silverkors

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.