Professional-grade SDK for algorithmic trading on prediction markets.

Documentation • Examples • Contributing

Neural SDK is a Python framework for building algorithmic trading strategies on prediction markets. It provides data collection, strategy development, backtesting, and trade execution with production-grade reliability.

All market data comes from Kalshi's live production API via RSA-authenticated requests, using the same infrastructure that powers their trading platform.

• Authentication: RSA signature implementation for Kalshi API
• Historical Data: Collect and analyze real trade data with cursor-based pagination
• Real-time Streaming: REST API and FIX protocol support for live market data
• Strategy Framework: Pre-built strategies (mean reversion, momentum, arbitrage)
• Risk Management: Kelly Criterion, position sizing, stop-loss automation
• Backtesting Engine: Test strategies on historical data before going live
• Order Execution: Ultra-low latency FIX protocol integration (5-10ms)

pip install neural-sdk
pip install "neural-sdk[trading]"  # with trading extras

Create a .env file with your Kalshi credentials:

KALSHI_API_KEY_ID=your_api_key_id
KALSHI_PRIVATE_KEY_BASE64=base64_encoded_private_key
KALSHI_ENV=prod

The SDK automatically loads credentials from the .env file.

from neural.auth.http_client import KalshiHTTPClient

client = KalshiHTTPClient()
markets = client.get('/markets')
print(f"Connected! Found {len(markets['markets'])} markets")

from neural.data_collection.kalshi_historical import KalshiHistoricalDataSource
from neural.data_collection.base import DataSourceConfig

config = DataSourceConfig(
    source_type="kalshi_historical",
    ticker="NFLSUP-25-KCSF",
    start_time="2024-01-01",
    end_time="2024-12-31"
)

source = KalshiHistoricalDataSource(config)
trades_data = []

async def collect_trades():
    async for trade in source.collect():
        trades_data.append(trade)
        if len(trades_data) >= 1000:
            break

import asyncio
asyncio.run(collect_trades())
print(f"Collected {len(trades_data)} trades")

from neural.analysis.strategies import MeanReversionStrategy
from neural.analysis import Backtester

strategy = MeanReversionStrategy(lookback_period=20, z_score_threshold=2.0)
engine = Backtester(initial_capital=10000)
results = engine.backtest(strategy, start_date="2024-01-01", end_date="2024-12-31")

print(f"Total Return: {results['total_return']:.2%}")
print(f"Sharpe Ratio: {results['sharpe_ratio']:.2f}")

from neural.trading.client import TradingClient

trader = TradingClient()
order = trader.place_order(
    ticker="NFLSUP-25-KCSF",
    side="yes",
    count=10,
    price=52
)
print(f"Order placed: {order['order_id']}")

See the examples/ directory for working code samples:

• 01_init_user.py - Authentication setup
• stream_prices.py - Real-time price streaming
• test_historical_sync.py - Historical data collection
• 05_mean_reversion_strategy.py - Strategy implementation
• 07_live_trading_bot.py - Automated trading bot

pytest
pytest --cov=neural tests/

1. Fork the repository
2. Create a feature branch: git checkout -b feature/amazing-feature
3. Make changes and add tests
4. Run tests: pytest
5. Commit: git commit -m "Add amazing feature"
6. Push: git push origin feature/amazing-feature
7. Open a Pull Request

See CONTRIBUTING.md for detailed guidelines.

git clone https://github.com/IntelIP/Neural.git
cd neural
pip install -e ".[dev]"
pytest
ruff check .
black --check .

• Documentation: neural-sdk.mintlify.app
• Examples: examples/
• Issues: GitHub Issues
• Discussions: GitHub Discussions

This project is licensed under the MIT License - see LICENSE file for details.