Home / LLM agents & research
TauricResearch/TradingAgents
Multi-agent LLM framework for financial trading analysis
What it is
A Python framework that orchestrates multiple LLM-powered agents—analysts, researchers, traders, and managers—to analyze tickers and produce trading decisions. It pulls data from sources such as Yahoo, SEC EDGAR, FRED, Alpha Vantage, and social sentiment feeds, and supports backtesting over a ticker and date grid with point-in-time data integrity, configurable LLM providers, and a CLI for running analyses. Traders and researchers experimenting with agentic LLM workflows in finance will find it useful, though it is a research framework rather than a production trading product. Using it also requires API keys for the LLM and data providers you choose.
At a glance
Worth watchingOur rating, based on popularity, maintenance and how ready it is for real use.
| Best for | Developers |
|---|---|
| Used for | Strategy research, AI agents |
| Markets | Multi-market |
| Stack | Python |
| Learning curve | Moderate learning curve |
| Practical value | Medium practical value |
| Cost | Free, with paid APIs |
| Hardware | No GPU needed |
| Maintenance | Last commit 8 days ago |
GitHub stars, last 30 days
Daily snapshots since 2026-09-12 (up to 30 days): +5.8k over the period, now 110,520. Gaps mean no snapshot was taken that day.
TradingAgents: Multi-Agents LLM Financial Trading Framework