Skip to content

Home

Jump to bottom
iAmGiG edited this page Nov 15, 2025 · 3 revisions

AutoTrader Wiki

Powered by AgentEdge - Autonomous AI agents seeking trading edge

Welcome to the AutoTrader wiki - a production-ready algorithmic trading platform featuring a multi-agent AI architecture.

⚠️ IMPORTANT DISCLAIMER

THIS SOFTWARE IS FOR EDUCATIONAL AND RESEARCH PURPOSES ONLY.

  • NOT FINANCIAL ADVICE: This system does not provide financial, investment, or trading advice.
  • USE AT YOUR OWN RISK: Trading involves substantial risk of loss.
  • NO WARRANTIES: Provided "as-is" without guarantees of profitability.
  • PAST PERFORMANCE ≠ FUTURE RESULTS: Historical results do not guarantee future performance.

🎯 Project Overview

AutoTrader combines validated pure-math MACD+RSI strategies with human-in-loop oversight for paper/live trading via Alpaca Markets.

Core Philosophy: Pure mathematical indicators + human decision making > complex AI sentiment analysis

📊 Current Status (November 2025)

✅ Production Ready

  • VoterAgent: Validated 0.856 Sharpe ratio, 36.6% return (2024-2025)
  • main.py CLI: Fully functional command-line interface
  • Alpaca Integration: Paper trading operational, live trading ready
  • Position Management: Real-time tracking with broker-as-truth reconciliation
  • Trading Cycle: Cost-efficient daily routines (90% fewer API calls)
  • Scheduler System: Interactive CLI with background daemon support

🚧 In Development

  • Multi-Agent System: Scanner, Risk, Executor, Orchestrator agents
  • Event Bus: Agent communication infrastructure
  • OHLCV Entry Planning: Intraday entry optimization (Issue #366)

🚀 Quick Start

Installation

# Clone repository
git clone https://github.com/iAmGiG/AutoTrader-AgentEdge.git
cd AutoTrader-AgentEdge

# Create environment
conda create -n AutoTrader python=3.10
conda activate AutoTrader
pip install -e .

Configuration

Create config/config.yaml:

POLYGON_IO: "your_key_here"
ALPHA_VANTAGE_KEY: "your_key_here"
ALPACA_PAPER_API_KEY: "your_key_here"
ALPACA_PAPER_SECRET: "your_key_here"
ALPACA_ENDPOINT: "https://paper-api.alpaca.markets/v2"

First Trade

# Launch interactive CLI
python main.py

# Interactive session:
> buy 10 AAPL              # Execute trade
> check my alerts          # Position alerts
> show portfolio           # Account status
> /schedule                # Scheduler management

📚 Wiki Pages

Getting Started

Core Concepts

User Guides

Developer Guides

🎓 Key Features

Validated Performance

  • Sharpe Ratio: 0.856 (excellent risk-adjusted returns)
  • Total Return: 36.6% (2024-2025 validation period)
  • Win Rate: 51.4%
  • Max Drawdown: -10.10%
  • Strategy: Pure MACD(13/34/8) + RSI(14/30/70) - NO LLM calls

Cost-Efficient Architecture

  • 90% fewer API calls vs reactive trading systems
  • Intelligent caching with 85%+ hit rate
  • Batch operations minimize rate limiting
  • GTC orders reduce monitoring overhead

Production-Grade Infrastructure

  • Broker-as-truth reconciliation prevents state drift
  • Position tracking across system restarts
  • Order lifecycle management (bracket, stop, trailing)
  • Market hours awareness and handling
  • Interactive scheduler with background daemon

🏗️ AgentEdge Architecture

Multi-Agent Trading System built with Microsoft AutoGen framework:

  • VoterAgent - Production-ready MACD+RSI voting (0.856 Sharpe)
  • ScannerAgent - Market opportunity identification (in development)
  • RiskAgent - Portfolio risk management (in development)
  • ExecutorAgent - Trade execution (in development)
  • TradingOrchestrator - Multi-agent coordination (in development)

🔗 External Resources

📞 Support

  • GitHub Issues: Primary support channel
  • Documentation: See /docs directory in repo
  • Wiki: This wiki for guides and tutorials

Last Updated: November 2025 Status: VoterAgent Production-Ready (0.856 Sharpe) | Interactive CLI Operational

Clone this wiki locally