An intelligent cryptocurrency trading bot that combines technical analysis with AI-powered market insights to make automated trading decisions.
- Python 3.11+
- Coinbase Advanced Trade API access
- Google Cloud Platform account
-
Clone the repository
git clone https://github.com/yourusername/AI-crypto-bot.git cd AI-crypto-bot -
Set up Python environment
python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate pip install -r requirements.txt
-
Configure your settings
cp .env.example .env # Edit .env with your API keys and preferences -
Test the new Phase 1 features
# Test the opportunity manager python test_opportunity_manager.py # Run the bot (automatically uses new prioritization) python main.py
-
Run in simulation mode
python main.py
- Opportunity Scoring: Analyzes all coins and ranks by trading opportunity strength
- Dynamic Capital Allocation: Allocates more capital to stronger signals (up to 60% max)
- Three-Phase Trading Cycle: Analyze β Rank β Execute for maximum efficiency
- Scalable Architecture: Automatically handles any number of trading pairs
- Multi-Strategy Trading: Combines trend following, mean reversion, and momentum strategies
- AI-Powered Analysis: Uses Google Gemini for market analysis and decision making
- Adaptive Strategy Manager: Adjusts strategy weights based on market conditions
- Risk Management: Comprehensive position sizing and safety mechanisms
- Real-time Dashboard: Web-based monitoring and performance tracking
- Enhanced Logging: Detailed opportunity scoring and allocation insights
- Automated Reports: Daily email summaries with AI-generated insights
- Performance Tracking: Historical analysis and strategy optimization
- Cloud Deployment: Ready-to-deploy on Google Cloud Platform and AWS
- Windows Compatible: Cross-platform file locking and process management
The bot now intelligently prioritizes trading opportunities across multiple assets:
- BTC-EUR: Bitcoin to Euro
- ETH-EUR: Ethereum to Euro
- SOL-EUR: Solana to Euro
- Easily Expandable: Add more pairs in configuration - the system automatically handles prioritization
- Analyze All Pairs: Simultaneously analyzes all configured trading pairs
- Opportunity Scoring: Ranks opportunities using confidence, momentum, consensus, and market regime
- Smart Capital Allocation: Distributes capital based on signal strength (stronger signals get more)
- Priority Execution: Executes best opportunities first, ensuring optimal capital utilization
- Simulation Mode: Test strategies without real money
- Risk Controls: Position limits, stop losses, and allocation caps
- Comprehensive Testing: Extensive test suite with 90%+ coverage
- Backtesting: Historical performance validation
For detailed information, see the Developer Documentation:
- Phase 1 Implementation - Complete Phase 1 technical details
- Opportunity Manager - Core prioritization logic
- Backtesting Analysis - Critical information about LLM backtesting limitations
- Technical strategies (momentum, mean_reversion, trend_following) can be accurately backtested
- LLM strategy uses Google Gemini API and cannot be simulated - backtest results are approximations only
- Live performance tracking monitors actual bot decisions from trading logs (not simulated)
- Trading Strategies - How the bot makes decisions
- Configuration Guide - Complete setup instructions
- Backtesting Strategy - Systematic backtesting approach
- Deployment Guides - Cloud and local deployment
- Troubleshooting - Common issues and solutions
Perfect for testing and development:
# See docs/deployment/local-development.md
python main.py # Runs in simulation mode by defaultAutomated deployment with monitoring:
# See docs/deployment/gcp-deployment.md
bash gcp_deployment/setup_gcp.shEnterprise deployment with auto-scaling:
# See docs/deployment/aws-deployment.md
bash aws_setup/setup_ec2.sh- Educational Purpose: This bot is designed for learning and research
- Financial Risk: Cryptocurrency trading involves significant financial risk
- No Guarantees: Past performance does not guarantee future results
- Use at Your Own Risk: Always understand the code before trading with real money
- Not Financial Advice: This software does not provide investment advice
We welcome contributions! Please see our development documentation for:
- Code structure and architecture
- Testing requirements and standards
- Development setup and workflows
This project is licensed under the MIT License - see the LICENSE file for details.
- Documentation: Check the docs/ folder for comprehensive guides
- Issues: Report bugs and request features on GitHub Issues
- Troubleshooting: See docs/TROUBLESHOOTING.md
Remember: Always start with simulation mode and thoroughly understand the system before considering live trading.