Act as a Principal Software Architect and Performance Engineer.
Your task is to perform a comprehensive performance audit and refactor of this entire codebase.
Before making any changes:
Thoroughly analyze the architecture, code structure, dependencies, database access patterns, caching strategy, queues, API endpoints, background jobs, asset loading, and deployment configuration.
Identify all performance bottlenecks, including but not limited to:
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.
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.
| #!/usr/bin/env ruby | |
| # frozen_string_literal: true | |
| require "bundler" | |
| require "cgi" | |
| require "json" | |
| require "net/http" | |
| require "optparse" | |
| require "thread" | |
| require "uri" |
| import json | |
| import boto3 | |
| import botocore.config | |
| from datetime import datetime | |
| ### AWS BEDROCK CALL ### | |
| # { | |
| # "modelId": "meta.llama4-scout-17b-instruct-v1:0", |
I’ve written a newer optimized 2026 version of this guide with a faster setup using Zinit + Starship and improved plugin loading.
This version avoids slow shell startups and works better with modern Zsh setups.
Updated guide: https://gist.github.com/n1snt/2cccc8aa5f7b645a7628d3512c70deb6
