multi-agent

TradingAgents

Name: TradingAgents
Author: TauricResearch

TradingAgents: Multi-Agents LLM Financial Trading Framework

110,311 stars+825★ this week21,217 forksPythonUpdated 10/3/2026100% 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

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

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

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/tradingagents && curl -fsSL https://workflowstacks.com/api/skills/tradingagents/claude-skill -o ~/.claude/skills/tradingagents/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

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

You give

Market data

1Data Input

Market data is collected

2Analysis

Specialized agents analyze data

tradingagents/__init__.py

3Discussion

Agents discuss optimal strategy

4Decision

Trading decision is made

main.py

You get

Trading decisions

Where to start reading

1
README.md
Start here — what it does and how to install it
2
main.py
Where the program starts running
3
pyproject.toml
Dependencies and the commands it exposes
4
.env.example
The API keys and settings you must provide
5
tradingagents/__init__.py
Inside tradingagents/ — the main logic begins here

What's in each folder

tradingagents/Core code — the actual logic71 files

cli/Command-line entry points8 files

scripts/Helper scripts1 files

tests/Tests — proof it works56 files

assets/Images & static assets10 files

.github/CI / automation (GitHub Actions)1 files

READMEHas testsDocumentedCI checksDocker readyApache-2.0 licenseUpdated this month

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/tradingagents && curl -fsSL https://workflowstacks.com/api/skills/tradingagents/claude-skill -o ~/.claude/skills/tradingagents/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

TauricResearch

Language

Python