monotalk (櫻井健) kemsakurai

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.

A Team Charter Template is proposed here to help YaST team members to define the team chapter. Please, feel free to add/remove/modify the points in this team charter if you consider it.

Why a Team Charter

That is the first question everyone of us make to ourselves. But there are some good reasons to have one:

この和訳メモは以下のリンク先の記事の和訳です。

https://www.linkedin.com/pulse/microservices-client-side-load-balancing-amit-kumar-sharma/

マイクロサービス: クライアントサイドロードバランシング

プロダクションでのフェイルセーフ性を確保するために、同じアプリケーションを複数のインスタンスにデプロイします。同じアプリケーションをホストする論理的なサーバ（ノード）のグループは Application Clusterを構成します。

伝統的なアプローチ

Python ロギング方法

Python 組み込みの logging モジュールを使う。

logging — Python 用ロギング機能

Logging HOWTO

Good logging practice in Python

WebRTC コトハジメ

更新:	2026-06-08
作者:	@voluntas
バージョン:	2026.1
URL:	https://voluntas.github.io/

	// chromeを利用して、ユーザ一覧を表示しつつconsoleで↓を実行すると、現在の参加者からランダムで一人表示することができます

	const names_array = document.querySelector("[aria-label='参加者']").innerText.split("\n").filter((word)=> !word.match(/\（\|メイン\|ミュート\|主催者\|画面共有\|その他の操作\|keep_off\|more_vert\|keep\|domain_disabled/))
	const names_set = new Set(names_array)
	const names_uniq_array = Array.from(names_set)
	names_uniq_array[Math.floor(Math.random() * names_uniq_array.length)]

	function getYAML() {
	var ss = SpreadsheetApp.getActiveSpreadsheet();
	var dest = DocumentApp.openById(PropertiesService.getScriptProperties().getProperty("output_document_id"));

	var key = Browser.inputBox("Please enter the key of the Google Spreadsheet containing the content to be generated as a YAML file.");
	var source = SpreadsheetApp.openById(key);

	var output = "---\nen:\n";
	var sheets = source.getSheets();
	for (var i = 0; i < sheets.length; i++) {