The first real-world AI hedge fund framework in crypto, fully open source! AIBrokers is a framework designed to create multi AI agents for managing hedge funds. These AI agents act as professional traders, operating 24/7 to manage investments for their owners. My vision and aspiration are that, with unlimited contributions from the community, AIBrokers can outperform hedge funds, whales, and market makers in the future. AIBrokers is open source and welcomes contributions from anyone.
This system employs several agents working together:
- Trader Behavior Agent: Gather on-chain trader behavior, traders actions, etc.
- Quant Agent: calculates signals like MACD, RSI, Bollinger Bands, etc.
- Sentiment Agent: gathers, analyzes crypto market sentiment from social media, news, and on-chain data to support trading strategies, etc.
- Fundamental Agent: evaluates crypto projects' tokenomics, on-chain data, market performance, and ecosystem to guide long-term investment decisions, etc.
- Technical Analyst Agent: analyzes crypto price charts, trends, and indicators to identify trading opportunities and optimize entry/exit points, etc.
- Rish manager: assesses market volatility, portfolio exposure, and potential risks to minimize losses and optimize risk-reward ratios.
- Fund Manager Agent: makes final trading decisions and generates orders, etc.
Note: the system simulates trading decisions, it does not actually trade.
Clone the repository:
git clone https://github.com/AI-Brokers/AIBrokers.git
- Install Poetry (if not already installed):
curl -sSL https://install.python-poetry.org | python3 -- Install dependencies:
poetry install- Set up your environment variables:
# Create .env file for your API keys
cp .env.example .env
export OPENAI_API_KEY='your-api-key-here' # Get a key from https://platform.openai.com/poetry run python src/main.py --crypto BTCExample Output:
You can also specify a --show-reasoning flag to print the reasoning of each agent to the console.
poetry run python src/main.py --crypto BTC --show-reasoningYou can optionally specify the start and end dates to make decisions for a specific time period.
poetry run python src/main.py --crypto BTC --start-date 2024-01-01 --end-date 2024-03-01 poetry run python src/backtester.py --crypto BTCExample Output:
Starting backtest...
Date Crypto Action Quantity Price Cash colatteralLong collateralShort Total Value
-----------------------------------------------------------------------------------------------------------
2024-12-16 BTC long 100000 103124.30 0.00 0.97 0 100030.57
2024-12-17 BTC short 103816 107026.90 0.09 0 0.97 103816.19
2024-12-18 BTC long 103397 107458.50 0.53 0.96 0 103160.69
2024-12-19 BTC long 100433 104617.30 0.14 0.96 0 100432.75
2024-12-20 BTC short 94863 98815.90 0.41 0 0.96 94863.67
You can optionally specify the start and end dates to backtest over a specific time period.
poetry run python src/backtester.py --crypto BTC --start-date 2024-01-01 --end-date 2024-03-01AIBrokers/
├── src/
│ ├── agents/ # Agent definitions and workflow│
│ │ ├── market_data.py # Market data agent
│ │ ├── portfolio_manager.py # Portfolio management agent
│ │ ├── risk_manager.py # Risk management agent
│ │ ├── sentiment.py # Sentiment analysis agent
│ │ ├── state.py # Agent state
│ │ ├── technicals.py # Technical analysis agent│
│ ├── tools/ # Agent tools
│ │ ├── api.py # API tools
│ ├── backtester.py # Backtesting tools
│ ├── main.py # Main entry point
├── pyproject.toml
├── ...
- Fork the repository
- Create a feature branch
- Commit your changes
- Push to the branch
- Create a Pull Request
- Chat Box/ Social Bot/ Signal Bot
- The Autonomous AI-Driven Hedge Fund
- AI-Powered Copilot Trading Assistant
- X: https://x.com/aibrokers_xyz
- Discord: https://discord.gg/fsvxUZJ2
- Media Kit: https://drive.google.com/drive/folders/1SKjgkHd0j-iClgCxsuVcYfHyxB-cvqhI?usp=sharing
- Schema Inspired: https://github.com/virattt/ai-hedge-fund
This project is licensed under the MIT License - see the LICENSE file for details.