kylemd

Local knowledge graph on a single RTX 5090: Graphiti + Ollama without the cloud

Technical writeup. Audience: anyone tracking issue #868 who wants to reproduce a fully local, temporal knowledge-graph memory layer for an LLM chat stack — no OpenAI key, no hosted Graphiti, one GPU.

1. What was built and why

The goal was a persistent memory layer for a self-hosted LibreChat + Ollama setup: not "stuff the last N turns into the prompt," but a real temporal knowledge graph where facts become entities and relationships, survive across sessions, and can be retrieved by semantic search rather than by chunk overlap. Concretely: the assistant should be able to store "Yurii lives in Kyiv" once, and surface it in an unrelated conversation a week later. Graphiti (getzep/graphiti) does the entity/edge extraction and bi-temporal bookkeeping on top of Neo4j; we already ran Neo4j and Ollama, so the only new moving part was a small service wrapping graphiti-core.

source

Move all emails older than 7 days to Archive/All Mail

in:inbox older_than:7d -is:starred

Move all emails you are cc'ed on older than 3 days to Archive/All Mail

cc:me older_than:3d -is:starred

Gmail Filters

Filters for turning Gmail into a productive workspace.

All the unread emails

is:unread

	import cv2
	import numpy as np
	import argparse
	from pathlib import Path
	import sys



	parser = argparse.ArgumentParser(description="Remove dust from an image with IR information in the alpha channel")
	parser.add_argument('image',

	### Basic ###
	# The directory to store the downloaded file.
	dir=${HOME}/Downloads
	# Downloads the URIs listed in FILE.
	input-file=${HOME}/.aria2/aria2.session
	# Save error/unfinished downloads to FILE on exit.
	save-session=${HOME}/.aria2/aria2.session
	# Save error/unfinished downloads to a file specified by --save-session option every SEC seconds. If 0 is given, file will be saved only when aria2 exits. Default: 0
	save-session-interval=60
	# Set the maximum number of parallel downloads for every queue item. See also the --split option. Default: 5

	#! /usr/bin/env python

	# from http://stackoverflow.com/questions/11524586/accessing-logcat-from-android-via-python
	import Queue
	import subprocess
	import threading
	import datetime

	class AsynchronousFileReader(threading.Thread):
	'''