stock/examples/README.md

OpenClaw Trading Examples

This directory contains example scripts demonstrating various features of OpenClaw Trading.

Quick Start

1. Basic Economic Tracking (01_quickstart.py)

Demonstrates the core economic tracking system:

• Creating an economic tracker
• Checking survival status
• Calculating decision costs
• Simulating trades
• Tracking balance history

python examples/01_quickstart.py

2. Workflow Demo (02_workflow_demo.py)

Shows how to use the LangGraph workflow system:

• Creating a trading workflow
• Running parallel analysis
• Getting trading signals
• Handling workflow results

python examples/02_workflow_demo.py

3. Factor Market (03_factor_market.py)

Demonstrates the factor market system:

• Browsing available factors
• Purchasing factors
• Using factors in analysis
• Factor unlocking mechanism

python examples/03_factor_market.py

4. Learning System (04_learning_system.py)

Shows how to use the learning system:

• Browsing available courses
• Enrolling agents in courses
• Completing courses
• Applying learned skills

python examples/04_learning_system.py

5. Work-Trade Balance (05_work_trade_balance.py)

Demonstrates the work-trade balance mechanism:

• Monitoring agent performance
• Switching to work mode
• Earning through work
• Returning to trading

python examples/05_work_trade_balance.py

6. Portfolio Risk Management (06_portfolio_risk.py)

Shows portfolio-level risk management:

• Managing multiple positions
• Calculating portfolio risk
• Risk-adjusted position sizing
• Stop-loss and take-profit

python examples/06_portfolio_risk.py

Running All Examples

To run all examples at once:

# Make executable
chmod +x examples/run_all.sh

# Run all
./examples/run_all.sh

Or manually:

for script in examples/0*.py; do
    echo "Running $script..."
    python "$script"
    echo ""
done

Custom Examples

Creating a Custom Agent

from openclaw.agents.base import BaseAgent

class MyCustomAgent(BaseAgent):
    def analyze(self, symbol: str):
        # Your analysis logic here
        return {"signal": "buy", "confidence": 0.8}

# Usage
agent = MyCustomAgent("my_agent", initial_capital=1000.0)
result = agent.analyze("AAPL")

Running a Backtest

from openclaw.backtest.engine import BacktestEngine

engine = BacktestEngine()
engine.configure(
    symbols=["AAPL"],
    start_date="2023-01-01",
    end_date="2023-12-31",
    initial_capital=10000.0
)

results = engine.run()
print(f"Total Return: {results.total_return:.2%}")

Using the Workflow

from openclaw.workflow.trading_workflow import TradingWorkflow

workflow = TradingWorkflow(
    symbol="AAPL",
    initial_capital=1000.0,
    enable_parallel=True
)

result = await workflow.run()
print(f"Signal: {result['signal']}")
print(f"Confidence: {result['confidence']:.2%}")

Jupyter Notebook Tutorials

For interactive tutorials, see the notebooks/ directory:

1. 01_getting_started.ipynb - Introduction to OpenClaw
2. 02_agent_comparison.ipynb - Comparing different agents
3. 03_backtesting.ipynb - Backtesting strategies
4. 04_custom_strategies.ipynb - Creating custom strategies

To start Jupyter:

jupyter notebook notebooks/

Prerequisites

Ensure you have OpenClaw installed:

pip install -e "."

Or set PYTHONPATH:

export PYTHONPATH=/path/to/openclaw/src:$PYTHONPATH

Additional Resources

• Full Documentation
• API Reference
• Architecture Guide