Use AI to author, iterate, and evaluate strategies inside a local trading-system workflow under your control.
Community AI Studio supports loginless direct BYOK or a supported local model. Optional hosted inference is disclosed separately.
Specialized strategy builders organized by trading approach.
Create a reviewed candidate set under explicit user constraints.
Choose the model route and parameters, inspect generated candidates, and explicitly start local validation or backtesting. Generation and backtest results are not proof of statistical validity.
AI explains why a strategy fails and suggests concrete fixes.
AI can summarize observed failure evidence and suggest possible next tests. The user reviews the explanation and decides whether to create another candidate.
Sharpe ratios and max drawdown explained in human terms.
Not everyone speaks quant. StratCraft AI interprets your backtest metrics and writes plain language summaries: what the numbers mean, whether the strategy is viable, and what to try next.
AI-assisted organization for an inspectable research library.
Naming, tags, and categories help keep a growing candidate library navigable while preserving user review and the evidence behind each decision.
Free tier includes the C++ backtest engine, regime detection, and YFinance + Dukascopy data: everything you need to start building at scale.