Vadim vaad2

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.

Claude-SPARC Automated Development System For Claude Code

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Overview

The SPARC Automated Development System (claude-sparc.sh) is a comprehensive, agentic workflow for automated software development using the SPARC methodology (Specification, Pseudocode, Architecture, Refinement, Completion). This system leverages Claude Code's built-in tools for parallel task orchestration, comprehensive research, and Test-Driven Development.

Features

Cursor's Memory Bank

I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read ALL memory bank files at the start of EVERY task - this is not optional.

Memory Bank Structure

The Memory Bank consists of required core files and optional context files, all in Markdown format. Files build upon each other in a clear hierarchy:

flowchart TD

The Autonomous Agent Prompting Framework

This repository contains a disciplined, evidence-first prompting framework designed to elevate an Agentic AI from a simple command executor to an Autonomous Principal Engineer.

The philosophy is simple: Autonomy through discipline. Trust through verification.

This framework is not just a collection of prompts; it is a complete operational system for managing AI agents. It enforces a rigorous workflow of reconnaissance, planning, safe execution, and self-improvement, ensuring every action the agent takes is deliberate, verifiable, and aligned with senior engineering best practices.

I also have Claude Code prompting for your reference: https://gist.github.com/aashari/1c38e8c7766b5ba81c3a0d4d124a2f58

Populating Elasticsearch Index with Logstash

Logstash is a free and open server-side data processing pipeline that ingests data from a multitude of sources, transforms it, and then sends it to your favorite "stash."

This section describes how one can use it on UNIX to migrate data from a PostgreSQL database to elasticsearch.

The Prerequisites

The main point is to save the SSL/TLS keys those used by the web browser (SSLKEYLOGFILE=/tmp/tmp-google/.ssl-key.log).
In the example below we run brand new instance of Google Chrome (--user-data-dir=/tmp/tmp-google do the trick):
SSLKEYLOGFILE=/tmp/tmp-google/.ssl-key.log /Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome --user-data-dir=/tmp/tmp-google
Then run the Wireshark and open the Preferences -> Protocols -> SSL, where we put the path to the SSL keys log file into the (Pre)-Master-Secret log filename field.
Now all SSL/TLS traffic from this browser instance will be decrypted.

My first shot at fixing this was in tasks.py file below.

But then that just gave a "unhandled error in deferred", so I went on to use CrawlRunner.

That showed no output at all anymore, and didn't run as expected.

Eventually, I just settled on CELERY_WORKER_MAX_TASKS_PER_CHILD=1=1 in settings.py

Note: CELERY_WORKER_MAX_TASKS_PER_CHILD=1 is for django. Celery without django probably drops the CELERY_ prefix

	{
	"mcpServers": {
	"codex": {
	"type": "stdio",
	"command": "codex",
	"args": ["mcp-server"]
	}
	}
	}

	pragma solidity ^0.5.0;

	/**
	* SPDX-License-Identifier: UNLICENSED
	*/
	/**
	* @title SafeMath
	* @dev Math operations with safety checks that revert on error
	*/
	library SafeMath {

	var fpdefs = {
	vertex_shader :
	'attribute vec3 a_vertexPosition,a_vertexNormal;attribute vec2 a_vert' +
	'exTexture;uniform mat4 u_mvMatrix,u_pMatrix,u_nMatrix;uniform vec3 u' +
	'_lightPosition;varying vec3 v_normal;varying vec2 v_texture;varying ' +
	'vec3 v_eyeVec,v_lightRay;void main(){vec4 vertex=u_mvMatrix*vec4(a_v' +
	'ertexPosition,1.);v_normal=vec3(u_nMatrix*vec4(a_vertexNormal,1.));v' +
	'ec4 light=u_mvMatrix*vec4(u_lightPosition,1.);v_lightRay=vertex.rgb-' +
	'light.rgb;v_eyeVec=-vec3(vertex.rgb);gl_Position=u_pMatrix*vertex;gl' +
	'_PointSize=1.;v_texture=a_vertexTexture*3.-vec2(1.,1.);}',