AthenaAI

🦉 AthenaAI is an AI-powered ensemble machine-learning trading bot for PocketOption, built on BinaryOptionsToolsV2 → Get it on GitLab
💬 Need help? Join the Chipa Discord · ⚡ Go no-code with ChipaEditor

AthenaAI is an AI-powered trading bot for PocketOption. It combines a five-model machine-learning ensemble (plus an optional GPU-trained neural network) with adaptive expiry selection, market regime detection, layered signal gating, and disciplined money management. Model state persists across restarts, and the bot keeps learning online from every resolved trade.

Risk note: Binary options trading involves substantial risk of loss. AthenaAI is a tool, not a guarantee of profit — past performance, including backtest and walk-forward results, does not guarantee future returns. Only trade with money you can afford to lose.

Start here

• Installation — Python setup, dependencies, and the BinaryOptionsToolsV2 wheel.
• Quickstart — from a fresh clone to a running bot in minutes.
• Configuration — how the three configuration layers fit together.

Guides

Task-oriented walkthroughs for operating the bot:

• Architecture — how all the pieces fit together, from candle stream to trade result.
• Live trading — running the bot day to day and reading its logs.
• Training the brain — offline training with train.py, including GPU training.
• Data formats — supported candle CSV formats and where to get data.
• Risk management — Kelly staking, loss limits, and cooldowns.
• Persistence — the brain file, expiry stats, and the SQLite trade journal.
• GPU training — CUDA/MPS setup and brain portability.
• Troubleshooting — symptoms, causes, and fixes.

Concepts

Deep dives into how AthenaAI makes decisions:

• The ensemble — five models (plus an optional MLP), vote weighting, and online learning.
• The feature engine — all 40 core and 17 experimental features, documented individually.
• Regime detection — trending, ranging, and volatile market classification.
• Expiry selection — how the AI picks a trade duration.
• Adaptive strategy — the self-tuning layer that blocks losing regimes, hours, and directions.
• Feature Lab — automatic masking of non-predictive experimental features.
• Signal gates — every check a signal must pass before a trade is placed.

Reference

Exhaustive, one-page-per-item reference material:

• Environment variables — every PO_* variable, one page each.
• Trainer CLI — every train.py flag, one page each.
• Advanced configuration — every BotConfig field without an environment variable, one page each.
• API reference — every module, class, and function in the codebase.

Requirements at a glance

Level Up Your AthenaAI Setup

• 🦉 Get AthenaAI on GitLab → — clone the source, open issues, and contribute improvements.
• 💬 Join the Chipa Discord → — get real-time support, share your results, and swap strategy ideas with other AthenaAI users.
• ⚡ Try ChipaEditor → — build, backtest, and deploy trading strategies without writing a line of code, with our AI-powered strategy editor.