Agentic framework that self-improves its stock portfolio strategy

AutoHypothesis is an open-source framework that automatically develops and tests stock trading strategies by iterating through different approaches until finding profitable ones. The system uses historical data from 2010 to present, testing strategies on the top 300 stocks while accounting for realistic trading costs of 10 basis points per trade. It stops when strategies pass validation tests or after 200 attempts, allowing researchers to customize everything from asset classes to scoring methods for automated quantitative finance research.