These standards describe how to design and write TypeScript code in this codebase. They are especially intended for agents: before adding patterns, libraries, adapters, or abstractions, read the existing code and prefer the local convention unless it conflicts with the safety/correctness principles below.
When rules pull in different directions, use this order:
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.
| const randomInteger = (min: number, max: number) => | |
| Math.floor(Math.random() * (max - min + 1)) + min; | |
| export const getFutureExpiryDate = () => { | |
| const now = new Date(); | |
| now.setFullYear(now.getFullYear() + randomInteger(1, 5)); | |
| return {month: randomInteger(1, 12), year: now.getFullYear().toString().slice(2)}; | |
| } | |
| export const getPastExpiryDate = () => { |
This bot trades Polymarket's "BTC Up or Down" 5-minute binary markets. Every 5 minutes, Polymarket opens a market asking: "Will BTC be higher or lower than the opening price when this 5-minute window closes?" You buy "Up" or "Down" tokens at some price (e.g. $0.50–$0.95), and if you're right, each token pays out $1.00. If you're wrong, you lose your bet.
The bot uses technical analysis on real-time Binance BTC price data to predict the outcome, then places the trade on Polymarket right before the window closes — when we have the most information but (ideally) before the token price has fully priced in the outcome.
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
sudo pacman -Syu zsh
You do not need to install manjaro-zsh-config and all the other related packages like zsh-syntax-highlighting, zsh-history-substring-search, zsh-autosuggestions, etc., as we will use Oh My Zsh.
