TradingAgents

What you can do with it

• Run a team of AI analysts on a company ticker and date to get a written report with a rating
• Backtest the agents' decisions over a grid of tickers and dates, using only data published by each date
• Use different AI providers for different roles, including local models through Ollama, and save reports as an HTML page

Ways a business could use it

• Produce structured background research on listed companies for an internal investment or market-research review
• Use it as a working example when building your own multi-agent AI workflows for analysis and reporting

Can you use it commercially?

Free to use, change and sell, including in paid products. Keep the copyright notice.

Not legal advice. Read the project's licence file before building a product on it.

Getting it running

It is a Python package with a command-line interface, and the release notes mention Docker support, so you need API keys for an AI provider and for market data.

Follow the official instructions in the project README.

Things to check

• Designed for research only; the authors say it is not financial or investment advice
• Results vary with the model used and are non-deterministic, so output should not be relied on for real money decisions
• Needs paid AI provider API keys, and some data sources may need their own keys
• Running many agents per analysis can use a lot of API credit
• Automated trading carries a risk of financial loss