AutoHedge

AutoHedge is an enterprise-grade autonomous agent hedge fund that trades on your behalf. It combines swarm intelligence and specialized AI agents to perform end-to-end market analysis, risk management, and execution with minimal human intervention.

Current support: Full autonomous trading on Solana. Coming soon: Coinbase and additional exchanges.

Overview

AutoHedge is built to be the world's most powerful autonomous agent hedge fund. It runs continuous analysis, generates and validates trading theses, sizes risk, and executes orders across supported venues. The system is designed for institutional reliability: structured outputs, comprehensive logging, and a risk-first architecture that scales from single strategies to multi-venue, multi-asset deployment.

Features

• Multi-Agent Architecture: Specialized agents for each stage of the trading pipeline

  • Director Agent: strategy and thesis generation
  • Quant Agent: technical and statistical analysis
  • Risk Management Agent: position sizing and risk assessment
  • Execution Agent: order generation and execution

• Real-Time Market Analysis: Integration with live market data for analysis and execution

• Risk-First Design: Built-in risk management and position sizing before any execution

• Structured Output: JSON-formatted recommendations and analysis for downstream systems

• Enterprise Logging: Detailed, configurable logging for audit and debugging

• Extensible Framework: Modular design for custom strategies and new venues

Supported Venues

Quick Start

Installation

pip install -U autohedge

Environment Variables

# Jupiter API (token price & search tools)
# Get a key at https://portal.jup.ag
JUPITER_API_KEY=

# OpenAI (experimental agents)
OPENAI_API_KEY=
ANTHROPIC_API_KEY=
WORKSPACE_DIR="agent_workspace"

# Trading
WALLET_PRIVATE_KEY=""

See .env.example for a full reference.

Basic Usage

autohedge 

Architecture

AutoHedge uses a multi-agent pipeline where each agent has a defined responsibility:

graph TD
    A[Director Agent] --> B[Quant Agent]
    B --> C[Risk Manager]
    C --> D[Execution Agent]
    D --> E[Trade Output]

Contributing

Contributions are welcome. See Contributing Guidelines for details.

1. Fork the repository
2. Create a feature branch (git checkout -b feature/AmazingFeature)
3. Commit changes (git commit -m 'Add some AmazingFeature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

License

MIT License. See LICENSE for details.

Acknowledgments

• Swarms for the AI agent framework

Support

• Issue Tracker: GitHub Issues
• Community: Discord

AutoHedge by The Swarm Corporation