129 lines
2.8 KiB
ReStructuredText
129 lines
2.8 KiB
ReStructuredText
Quickstart Guide
|
|
================
|
|
|
|
Get started with OpenClaw Trading in 5 minutes.
|
|
|
|
Installation
|
|
------------
|
|
|
|
1. Clone the repository:
|
|
|
|
.. code-block:: bash
|
|
|
|
git clone https://github.com/yourusername/openclaw-trading.git
|
|
cd openclaw-trading
|
|
|
|
2. Create a virtual environment and install dependencies:
|
|
|
|
.. code-block:: bash
|
|
|
|
python -m venv .venv
|
|
source .venv/bin/activate # On Windows: .venv\Scripts\activate
|
|
pip install -e ".[dev]"
|
|
|
|
3. Verify installation:
|
|
|
|
.. code-block:: bash
|
|
|
|
python -c "import openclaw; print('OpenClaw installed successfully')"
|
|
|
|
Basic Usage
|
|
-----------
|
|
|
|
Economic Tracker Example
|
|
~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
The economic tracker is the core component for tracking agent finances:
|
|
|
|
.. code-block:: python
|
|
|
|
from openclaw.core.economy import TradingEconomicTracker
|
|
|
|
# Create an economic tracker
|
|
tracker = TradingEconomicTracker(
|
|
agent_id="demo_agent",
|
|
initial_capital=1000.0
|
|
)
|
|
|
|
# Check survival status
|
|
status = tracker.get_survival_status()
|
|
print(f"Status: {status.value}")
|
|
|
|
# Calculate decision costs
|
|
cost = tracker.calculate_decision_cost(
|
|
tokens_input=1000,
|
|
tokens_output=500,
|
|
market_data_calls=2
|
|
)
|
|
print(f"Decision cost: ${cost:.4f}")
|
|
|
|
# Simulate a trade
|
|
result = tracker.calculate_trade_cost(
|
|
trade_value=500.0,
|
|
is_win=True,
|
|
win_amount=50.0
|
|
)
|
|
print(f"Trade fee: ${result.fee:.4f}")
|
|
print(f"New balance: ${result.balance:.2f}")
|
|
|
|
Running the Complete Workflow
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
Use the trading workflow to analyze a stock:
|
|
|
|
.. code-block:: python
|
|
|
|
import asyncio
|
|
from openclaw.workflow.trading_workflow import TradingWorkflow
|
|
|
|
async def analyze_stock():
|
|
# Create workflow for AAPL
|
|
workflow = TradingWorkflow(
|
|
symbol="AAPL",
|
|
initial_capital=1000.0,
|
|
enable_parallel=True
|
|
)
|
|
|
|
# Run the analysis
|
|
result = await workflow.run()
|
|
|
|
# Print results
|
|
print(f"Signal: {result['signal']}")
|
|
print(f"Confidence: {result['confidence']:.2%}")
|
|
print(f"Recommended position: {result['position_size']:.2f}")
|
|
|
|
asyncio.run(analyze_stock())
|
|
|
|
Running Examples
|
|
----------------
|
|
|
|
The project includes several example scripts:
|
|
|
|
.. code-block:: bash
|
|
|
|
# Quickstart example
|
|
python examples/01_quickstart.py
|
|
|
|
# Workflow demo
|
|
python examples/02_workflow_demo.py
|
|
|
|
# Factor market example
|
|
python examples/03_factor_market.py
|
|
|
|
# Learning system example
|
|
python examples/04_learning_system.py
|
|
|
|
# Work-trade balance example
|
|
python examples/05_work_trade_balance.py
|
|
|
|
# Portfolio risk example
|
|
python examples/06_portfolio_risk.py
|
|
|
|
Next Steps
|
|
----------
|
|
|
|
* Read the :doc:`architecture` overview
|
|
* Explore the :doc:`api` reference
|
|
* Learn about :doc:`agents` and their roles
|
|
* Understand the :doc:`workflow` system
|