Anonymous builderabout 2 months agoJudging locked: Self-Evolving Agents Hackathon

Shrek

A self-improving multi-agent trading system that analyzes real-time market data, executes trades, and continuously improves itself based on performance

Review the project

Start with the source code, then open the demo or video if available.

View GitHub repository
Project description
Shrek is a multi-agent stock forecasting system for stocks. News, historical, and real-time analyst agents generate standardized directional signals, which a forecaster combines using bounded, learned weights. Each agent selects its own equation through structured Gemini reasoning, and every prediction records the prompt, equation, model, policy version, and configuration used for full auditability. A daily learning cycle compares forecasts with actual stock closing prices and adjusts the weights based on performance.
Project links
Tools used
  • Replay.io
  • Pioneer
  • Guild.ai
  • Actian