QuantCell is a professional quantitative trading platform with high-performance backtesting, real-time market data, AI-powered strategy generation, and unified multi-exchange trading. Write strategies in pure Python with an intuitive API, run lightning-fast backtests, and deploy to production seamlessly.
from strategy.core import Strategy, StrategyConfig class SmaCrossConfig(StrategyConfig): """SMA Cross Strategy Configuration""" def __init__(self): self.fast_period = 10 self.slow_period = 30 class SmaCrossStrategy(Strategy): """Dual SMA Cross Strategy""" def on_bar(self, bar): # Update price history self.prices.append(bar.close) # Calculate SMA fast_sma = self.calc_sma(self.fast_period) slow_sma = self.calc_sma(self.slow_period) # Golden cross: buy signal if fast_sma > slow_sma and self.is_flat(): self.buy(self.config.trade_size) # Death cross: sell signal elif fast_sma < slow_sma and self.is_long(): self.sell(self.config.trade_size)
Everything you need to develop, test, and deploy professional trading strategies
Self-developed high-performance backtesting engine supporting both event-driven and vectorized execution modes. Intelligent caching and parallel processing for maximum speed.
AI-powered strategy generation with thinking chain support. Automatically generate, validate, and optimize trading strategies using large language models.
WebSocket-based real-time data streaming with automatic reconnection. Support for multiple data sources and historical data management.
Unified API for Binance, OKX, and more. Seamlessly switch between exchanges with consistent interface for both backtesting and live trading.
Professional K-line charts with technical indicators, trade markers, backtest replay, and comprehensive performance analysis dashboards.
Comprehensive risk controls with position sizing, stop-loss, take-profit, and portfolio-level risk monitoring for safer trading.
Clean separation of concerns with adapter pattern design. Use the same strategy code for both backtesting and live trading across multiple exchanges.
Strategy core separated from execution engines. Seamlessly switch between backtesting and live trading with the same strategy code.
Self-developed execution engine with intelligent caching and parallel processing for lightning-fast backtests and real-time trading.
Rich hook functions for customization plus AI strategy generation with thinking chain support for automated strategy development.
Write your strategy in pure Python. QuantCell handles the complexity.
from strategy.core import Strategy, StrategyConfig class SmaCrossConfig(StrategyConfig): """SMA Cross Strategy Config""" def __init__(self, instrument_ids, bar_types): super().__init__(instrument_ids, bar_types) self.fast_period = 10 self.slow_period = 30 class SmaCrossStrategy(Strategy): """Dual SMA Cross Strategy""" def on_bar(self, bar): # Update price history self.prices.append(bar.close) # Calculate SMA values fast_sma = self.calc_sma(self._config.fast_period) slow_sma = self.calc_sma(self._config.slow_period) # Golden cross: buy signal if fast_sma > slow_sma and self.is_flat(): self.buy(bar.instrument_id, self._config.trade_size) # Death cross: sell signal elif fast_sma < slow_sma and self.is_long(): self.sell(bar.instrument_id, self._config.trade_size)
Clean, Pythonic interface that feels natural to quantitative traders and developers alike.
Pre/post processing hooks for data, signals, and positions. Customize without modifying core code.
Automatic caching, parallel execution, and Numba JIT compilation for maximum performance.
QuantCell is proudly open source. Join our growing community of traders and developers.