Companion repository for the Code with Antonio video course · Watch on YouTube.
Build an AI trading bot with Python and backtest it with no real money: yfinance data, a classic strategy and GPT-6 Luna.
A bot that downloads real S&P 500 prices, tests a classic moving-average strategy, asks GPT-6 Luna every day whether to buy, sell or hold, and puts both against buy & hold in an honest backtest with $10,000 of fake money.
| # | Lesson | Video | Folder |
|---|---|---|---|
| 1 | What is an AI trading bot? | 0:00 | lessons/01-what-is-an-ai-trading-bot |
| 2 | Real market data with yfinance | 3:00 | lessons/02-real-market-data-with-yfinance |
| 3 | A classic strategy and your first backtest | 6:01 | lessons/03-a-classic-strategy-and-your-first-backtest |
| 4 | Let the AI decide | 9:42 | lessons/04-let-the-ai-decide |
| 5 | Don't let the AI cheat | 13:29 | lessons/05-don-t-let-the-ai-cheat |
| 6 | AI vs. the classics: the backtest | 17:02 | lessons/06-ai-vs-the-classics-the-backtest |
| 7 | Read the results honestly | 19:21 | lessons/07-read-the-results-honestly |
- Python 3.14 · uv 0.12.21 · yfinance 1.7.0 · Backtesting.py 0.6.6 · pandas 3.0.6 · openai 3.22.1 · gpt-6-luna · Ubuntu (Linux)
- Python 3.12+ and uv
cd app
uv sync
uv run data.py
uv run backtest.py
cp .env.example .env # add your OPENAI_API_KEY
uv run --env-file .env signals.pyREADME.md this file
lessons/ one folder per lesson: goal, timestamp, commands and files exactly as in the video
app/ the final working project
assets/ thumbnail
MIT — use it for anything, credit appreciated.
Generated on 2026-10-02 from the course scripts. Code with Antonio · AI tutor.