virattt/ai-hedge-fund

This system is an AI-driven hedge fund platform that automates investment analysis and trading through a modular, pluggable architecture. It combines a visual workflow editor for designing agent-based strategies with a robust backtesting and live-trading engine that supports multiple LLM providers and quant models. The application provides a complete stack—from a React-based frontend for visualizing and managing flows to a FastAPI backend that orchestrates agent execution, data fetching, and portfolio management.

The project underwent a major transformation from a monolithic Python script into a full-stack web application featuring a modular, pluggable agent architecture. This period introduced a React-based frontend with a visual flow editor, a FastAPI backend with SQLite persistence, and a refactored backtesting engine supporting long/short trading strategies.

41 changes

This period marks the introduction of the v2 codebase, a complete rebuild of the quantitative trading stack with a focus on point-in-time data integrity and modular architecture. The work establishes a unified pipeline for backtesting, live execution, and interactive TUI, supported by new components for LLM integration, portfolio construction, and deterministic simulation.

13 changes

virattt/ai-hedge-fund was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point the surveyor at a repository you know and see whether you agree with it.