Vera Gwei — ETH/USD Signal Desk (Python)

Vera Gwei is the ETH/USD desk from the Synthetic Capital / Charting the Rubicon AI Agents Fund — isolated into a single standalone Python script you can run yourself. It reproduces the exact decision the fund's Vera Gwei desk makes.

What it does

Where the Bitcoin desk fades extremes, Vera follows momentum. She reads RSI(7) on 15-minute Ethereum bars, rides sustained directional moves, and steps aside into a dead-band around neutral, holding a fixed 60 minutes. Each run reads real ETH/USD candles and prints the desk's current call — LONG, SHORT, or FLAT — with entry, an ATR-based stop, and a 0–1 conviction score, as of the last completed candle.

Signal only. The script never places an order and never touches your account.

What's included

• vera_gwei_eth.py — the self-contained desk script (only dependencies: requests, pandas, numpy)
• SETUP_GUIDE — a plain-English, step-by-step setup guide for non-coders

Requirements

• Python 3 and pip install requests pandas numpy
• A free OANDA practice API token (read-only pricing)
• Optional: free Alpaca data API keys (used as a crypto price fallback)

Historical backtest — zero-fee paper model on real prices

• Archetype: selective RSI momentum · 15-minute · 540-day Alpaca history
• Net return +580.4% · Sharpe 2.31 · Max drawdown −27.1% · Win rate 48.1% · 4 of 4 positive walk-forward folds

A win rate below 50% alongside a strongly positive return is the signature of momentum: winners tend to be larger than losers, not more frequent.

Important: These figures are a zero-fee, zero-slippage paper model on historical data. They are not a forecast and not a promise of profit — live spread, commissions, and slippage will reduce results, and high-frequency crypto strategies are especially cost-sensitive. This is a research tool, not financial advice. Past performance does not indicate future results, and you are responsible for any trading decisions you make.