TradingAgents: turning a 112K-star repo into a multi-agent trading research team
Roger_M_Taylor · x · 2026-10-30
Miles Deutscher walks through converting TradingAgents, an open-source project with 112K+ GitHub stars, into a multi-agent trading research system: instead of asking one AI whether a stock is a buy, build an AI investment team that debates the answer.
- Set up via Claude Code with a simple guide
- Connect market data, news, and fundamental analysis
- Bull and bear researchers debate the same asset (demo: Nvidia)
- Generate an HTML research report and review risk-adjusted portfolio recommendations
- Backtest strategies with Alpaca paper trading
Key insight: don't let one AI make the whole decision — make multiple agents challenge each other.
More from coding & agent
- Agentic MRI review takes 9th place out of 6299 teams in Kaggle RSNA knee abnormality detection — kagglingdieter · 2026-10-30
- Open-source Row-Bot demo: autonomous multi-turn agent finishes shop launch in 3 turns — Acceptable-Object390 · 2026-10-30
- Model choice is the least important decision in an AI project — alex_verem · 2026-10-30
- CapCut GPT in ChatGPT turns a prompt into a finished short video with script and voiceover in 5 minutes — thisguyknowsai · 2026-10-30
- Agent harness engineering: lessons from 57 papers — same model, 6x performance gap — Marmelab · 2026-10-30
- Two-person AI fight choreography on an RTX 3060: MiniMax H3 with first-frame, 18 storyboard frames and 3 LoRAs — JinnTsui · 2026-10-30