multi-agent

TradingAgents

Name: TradingAgents
Author: TauricResearch

TradingAgents: Multi-Agents LLM Financial Trading Framework

98,226 stars18,920 forksPythonUpdated 7/18/2026100% free · open source

What it does

TradingAgents is a multi-agent framework for building and testing financial trading strategies using large language models (LLMs) in Python

Install / run

pip install -r requirements.txt

When to use it

•When you need to develop and evaluate multiple trading strategies against each other
•When you want to incorporate LLMs into your trading decision-making processes
•When you require a flexible and customizable framework for backtesting and evaluating trading agents

Quick start

1 Clone the TradingAgents repository using `git clone https://github.com/TauricResearch/TradingAgents.git`
2Navigate to the `examples` directory and run `python simple_trading_agent.py` to see a basic example
3Modify the `config.json` file to define your own trading agents and LLM models
4Use the `trading_agent.py` script to run your custom trading agents, e.g., `python trading_agent.py --agent my_agent --model my_llm`
5Evaluate the performance of your trading agents using the `backtest.py` script, e.g., `python backtest.py --agent my_agent --start_date 2020-01-01 --end_date 2020-12-31`

Ready-to-paste prompt

python trading_agent.py --agent my_agent --model my_llm --paperTrading --verbose

Heads up: Make sure you have the required dependencies, including `transformers` and `pandas`, and that your Python version is compatible (Python 3.8 or later) before running the framework

Saves to your device

Topics

agent

finance

llm

multiagent

trading

How TradingAgents works

Codeflow

Free to inspect

TradingAgents is a medium Python project (~11k lines across 81 code files, plus 56 test files). Setup is light: installs like a normal app — add your API keys. Reading the code is optional. Last commit a month ago, Apache-2.0 license, has a test suite.

Size

Medium codebase

~11k lines · 81 code files · ~2 h to skim

Setup

One-command install

Installs like a normal app — add your API keys. Reading the code is optional.

Runs on

Python · Docker

Needs API keys (.env)

Python 100%

What happens, step by step

Tool analyzes market conditions