In simple English
This tool simulates a financial trading firm using multiple artificial intelligence agents. Different agents handle company financials, news, market sentiment, and technical indicators. They debate potential trades among themselves before a final manager approves or rejects the order. You run it from the command line or inside Python scripts by providing your own language model API keys. The software is free and open-source under the Apache 2.0 licence, but running frequent large model queries will incur costs from your provider.
What it is
TradingAgents is a Python framework built with LangGraph that coordinates multiple language model agents to perform collaborative financial analysis and backtesting. It supports a wide range of model providers, local execution via Ollama, and point-in-time financial data loading for historical testing.
What it is good for
Solo developers and researchers who want to experiment with multi-agent financial analysis, test trading strategies against historical market data, or automate routine stock research workflows.
- Coordinates multiple specialized AI roles including fundamental, technical, and sentiment analysts.
- Supports a broad range of language model providers and local models through Ollama or OpenAI-compatible endpoints.
- Includes built-in backtesting tools to evaluate strategy performance over a grid of dates and tickers.
- Requires familiarity with Python virtual environments and command-line interfaces to install and run.
- API usage costs for multiple collaborative language model calls can add up quickly during extensive backtests.
- Financial markets are unpredictable, and the framework is intended for research rather than guaranteed trading returns.
Manual multi-analyst stock research and custom trading bot scaffolding.
LangGraph
- virattt/ai-hedge-fund64k stars
An alternative multi-agent AI hedge fund framework that uses different language models to analyze stocks and make trading decisions.
- jesse-ai/jesse8.7k stars
A Python framework for writing crypto trading strategies, testing them against past prices, and running them live.
- hummingbot/hummingbot20k stars
A free framework for writing and running automated trading programs on cryptocurrency exchanges.
- lballabio/QuantLib7.7k stars
The long-established free library for pricing and risk-managing financial instruments.
git clone https://github.com/TauricResearch/TradingAgents.git cd TradingAgents uv venv --python 3.13 source .venv/bin/activate pip install .