The conviction engine for autonomous crypto trading agents. 376 metrics across 8 factor classes, multi-factor backtesting, signal persistence, and regime analysis — 21 tools for AI agents via MCP.
Enables AI-driven quant research by exposing backtesting, portfolio optimization, and performance analytics tools through MCP, allowing iterative strategy refinement with built-in overfitting guardrails.
Enables quantitative trading research by providing tools to backtest strategies, list market datasets, review forward-test logs, and search previously rejected hypotheses, all through an MCP interface.
Enables quant research, strategy generation, backtesting, and paper trading from natural language prompts, integrating with AI agents via an MCP server.
