# Manual Técnico de Inteligencia en la Dark Web (DARKINT)
## Guía de Autoaprendizaje Avanzado para Analistas
Este documento constituye el manual de referencia técnico y la guía de estudio autodidacta para el dominio de la Inteligencia en la Dark Web (**DARKINT**). Está diseñado para proporcionar los fundamentos teóricos detallados, la arquitectura de red subyacente y los procedimientos operativos necesarios para ejecutar investigaciones en entornos hostiles y redes de anonimato sin depender de plataformas comerciales.
---
## MÓDULO 0: Fundamentos Avanzados del CibercrimenA 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.
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.
| ### Version1 | |
| ExecutorService executor = Executors.newFixedThreadPool(Runtime.getRuntime().availableProcessors()); | |
| List<Callable<List<String>>> tareas = new ArrayList<>(); | |
| int chunkSize = usuarios.size() / Runtime.getRuntime().availableProcessors(); | |
| for (int i = 0; i < usuarios.size(); i += chunkSize) { | |
| int start = i; | |
| int end = Math.min(i + chunkSize, usuarios.size()); | |
| tareas.add(() -> { |
| #!/usr/bin/env bash | |
| set -euo pipefail | |
| IFS=$'\n' | |
| ##### CONFIGURACIÓN ##### | |
| OUTPUT_DIR="./output" | |
| SKIP_PDF=false | |
| SEND_MAIL=false | |
| EMAIL_RECIPIENT="example@example.com" | |
| HELP=false |
| #!/bin/bash | |
| set -e | |
| # ==================== COLORES ==================== | |
| RED='\033[0;31m' | |
| GREEN='\033[0;32m' | |
| YELLOW='\033[1;33m' | |
| BLUE='\033[1;34m' | |
| NC='\033[0m' # Sin color |
| nasm -f macho64 fast_memcpy.asm -o fast_memcpy.o | |
| clang -O2 test_memcpy.c fast_memcpy.o -o test_memcpy | |
| ./test_memcpy |
| import asyncio | |
| import os | |
| from textwrap import dedent | |
| from pyspark.sql import SparkSession | |
| from pyspark.sql.functions import col | |
| from agno.agent import Agent | |
| from agno.models.openai import OpenAIChat | |
| import requests | |
| from dotenv import load_dotenv | |
| import logging |
| # filepath: /Users/aironman/git/python-samples-2025/src/python_samples_2025/agno/agno-sample.py | |
| import os | |
| from agno.agent import Agent | |
| from agno.models.openai import OpenAIChat | |
| from dotenv import load_dotenv | |
| load_dotenv() | |
| # Obtén el token de la variable de entorno | |
| openai_api_key = os.getenv("OPENAI_API_KEY") | |
| if not openai_api_key: |
| ┌<▸> ~/g/python-samples-2025 | |
| └➤ poetry run python src/python_samples_2025/rag_ollama_transcriber.py | |
| ❌ Ollama no está corriendo. Intentando iniciarlo... | |
| ⏳ Iniciando Ollama... | |
| ✅ Ollama está listo. | |
| Modelos disponibles en Ollama: | |
| 1. my-codellama:latest | |
| 2. codellama:latest | |
| 3. neural-chat:latest | |
| 4. llama2:latest |