ChipaDocs

API Reference

🦉 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

This section documents every module in the AthenaAI codebase: full signatures, parameters, return values, side effects, and internals developers need when extending the bot. Every fact here is drawn from the source in the repository — file paths are given on each page.

For conceptual explanations of the algorithms, see the concepts section; for how to run the bot, see the quickstart.

Entry points

ModulePageWhat it does
main (main.py)main.mdLive-trading entry point: loads .env, builds BotConfig, runs the bot
train (train.py)see CLI reference and trainer.mdStandalone training CLI
src.configconfig.mdBotConfig dataclass — every tuneable knob
src.botbot.mdAITradingBot — orchestrates the three async loops

src.core — models and market analysis

ModulePageWhat it does
src.core.modelsmodels.mdEnsemblePredictor — 5-model voting ensemble with online learning
src.core.feature_enginefeature-engine.mdFeatureEngine — 40 core + 17 experimental features from candles
src.core.regimeregime.mdRegimeDetector — trending/ranging/volatile classification
src.core.expiryexpiry.mdExpirySelector — scores and learns the best trade expiry

src.trading — execution, risk, and adaptation

ModulePageWhat it does
src.trading.strategystrategy.mdAdaptiveStrategy — blocks losing regimes/hours, adjusts confidence
src.trading.money_managermoney-manager.mdMoneyManager — Kelly stake sizing and daily loss limit
src.trading.journaljournal.mdTradeJournal — SQLite persistence (schema documented)
src.trading.performanceperformance.mdPerformanceTracker — in-memory W/L/P&L/drawdown stats
src.trading.feature_labfeature-lab.mdFeatureLab — masks anti-predictive experimental features

src.training — standalone trainer

ModulePageWhat it does
src.training.trainertrainer.mdTrainer / TrainerConfig — full offline training pipeline
src.training.datasetdataset.mdCSV loading and parallel sample generation
src.training.devicedevice.mdCUDA / MPS / CPU device detection
src.training.torch_modeltorch-model.mdTorchMLPClassifier — picklable GPU MLP

src.utils — shared primitives

ModulePageWhat it does
src.utils.candlecandle.mdCandle and TradeRecord dataclasses
src.utils.enumsenums.mdDirection and Regime enums
src.utils.loggerlogger.mdShared log instance and format

Import graph at a glance

main.py ──▶ src.bot ──▶ src.core.*  src.trading.*  src.utils.*
train.py ─▶ src.training ─▶ src.core.models / feature_engine, src.utils.*

Both entry points produce/consume the same brain file (a pickle of EnsemblePredictor state) — see models.md and the persistence guide.

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.