ai-agent

TradingAgents-CN

Name: TradingAgents-CN
Author: hsliuping

基于多智能体LLM的中文金融交易框架 - TradingAgents中文增强版

31,143 stars6,555 forksPythonUpdated 7/24/2026100% free · open source

What it does

TradingAgents-CN is a Chinese financial trading framework based on multi-agent LLM, allowing users to build and deploy AI-powered trading agents for financial markets.

Install / run

pip install -r requirements.txt

When to use it

•When you need to automate trading decisions in Chinese financial markets
•When you want to leverage LLM models for financial forecasting and trading
•When you require a customizable framework for backtesting and evaluating trading strategies

Quick start

1Clone the repository using `git clone https://github.com/hsliuping/TradingAgents-CN.git`
2Create a new trading agent by modifying the `agents` directory and adding your own trading logic
3Configure the `config.yml` file to specify your trading environment and parameters
4Run the framework using `python main.py` to start the trading simulation
5Monitor and analyze the trading performance using the built-in visualization tools

Ready-to-paste prompt

python main.py --agent MyAgent --market SZSE --start-date 2022-01-01 --end-date 2022-12-31

Heads up: Make sure you have the necessary dependencies installed, including `tensorflow` and `pandas`, and that your Python version is compatible with the framework (Python 3.8+ recommended)

Saves to your device

How TradingAgents-CN works

Codeflow

Free to inspect

TradingAgents-CN is a very large Python project (~238k lines across 940 code files, plus 316 test files). Setup is light: installs like a normal app — add your API keys. Reading the code is optional. Last commit a month ago, Other license, has a test suite.

Size

Very large codebase

~238k lines · 940 code files · days to read — use, don't read

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)