Latin BlackHacked

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.

Architectural Comparison: Claude Flow V3 vs Claude Code TeammateTool

Date: 2026-01-25 Analysis: Side-by-side comparison of Claude Flow V3 swarm architecture (developed by rUv) and Claude Code's TeammateTool (discovered in v2.1.19)

Executive Summary

A detailed analysis reveals striking architectural similarities between Claude Flow V3's swarm system and Claude Code's TeammateTool. The terminology differs, but the core concepts, data structures, and workflows are nearly identical.

FastAPI HTTP Proxy Application

Introduction

This FastAPI application serves as an HTTP proxy, forwarding client requests to an upstream API server and relaying the server's response back to the client. It supports arbitrary paths and HTTP methods, providing a versatile proxy solution for various API interactions.

Requirements

Python 3.6 or higher
FastAPI
Uvicorn
HTTPX

	"$schema" = 'https://starship.rs/config-schema.json'

	format = """
	[](red)\
	$os\
	$username\
	[](bg:peach fg:red)\
	$directory\
	[](bg:yellow fg:peach)\
	$git_branch\

	#!/usr/bin/env python3
	"""
	Script to convert requirements.txt to dependencies list for pyproject.toml for uv project

	Usage:

	Execute the script with:

	python3 requirementstxt_to_uv_pyprojecttoml.py path/to/requirements.txt

	# adapted from https://github.com/fastapi/fastapi/issues/1788
	from fastapi import FastAPI
	from starlette.requests import Request
	from starlette.responses import StreamingResponse
	from starlette.background import BackgroundTask
	import uvicorn
	import httpx

	API_KEY = os.getenv('API_KEY')

	# https://github.com/qtangs/chainlit/blob/b81f82c9eff86fc9fd6da6f8f9f09ec03d95d8e0/backend/chainlit/data/sql_alchemy_orm.py

	import datetime
	import json
	import logging
	import os
	import ssl
	import uuid
	from typing import Any, Callable, Dict, List, Optional, Union, cast

	import logging
	from http import HTTPStatus

	import httpx
	import uvicorn.logging
	from fastapi import FastAPI, HTTPException, Request, Response
	from fastapi.routing import APIRoute

	TARGET_URL = "http://127.0.0.1:8080" # Change this to the URL you want to proxy requests to

	import re
	import asyncio
	from pymongo import MongoClient
	from pymongo.collection import Collection as MongoCollection
	from pymongo.results import InsertOneResult, UpdateResult, DeleteResult
	from typing import Awaitable, Self

	mongo: MongoClient = None
	DATABASE_NAME = "kokomemo"

	from fastapi import FastAPI, Request
	from fastapi.responses import StreamingResponse
	from starlette.background import BackgroundTask
	import httpx

	app = FastAPI()

	client = httpx.AsyncClient(base_url="http://localhost:8000/")

	async def reverse_proxy(r: Request):