What is TradingAgents?
TradingAgents is a multi-agent framework from Tauric Research that models the division of labour inside a real trading firm. It sits in the Finance & Market Agents category of the Agents & Automation tools and is open-source, written in Python and licensed Apache-2.0. To get started: clone and create an environment.
Overview
TradingAgents is a multi-agent framework from Tauric Research that models the division of labour inside a real trading firm. Specialised LLM agents each take one role — fundamentals, sentiment, news and technical analysts, bullish and bearish researchers, a trader, a risk-management team and a portfolio manager — and they debate each other before a decision is produced, rather than a single prompt answering the whole question.
The analyst team gathers the inputs: company financials, aggregated news headlines and social chatter, macro indicators, and technical indicators such as MACD and RSI. The researcher team then argues both sides of the resulting thesis, the trader composes those reports into a call, and the risk team and portfolio manager review it against volatility and liquidity before the final decision is recorded.
It is built on LangGraph and is deliberately provider-agnostic: OpenAI, Google, Anthropic, xAI, DeepSeek, Qwen, GLM, MiniMax, OpenRouter, Azure OpenAI and Amazon Bedrock are supported, as are local models through Ollama or any OpenAI-compatible server such as vLLM or LM Studio. The framework is Apache-2.0, has an accompanying paper (arXiv 2412.20138), and its authors state plainly that it is built for research and is not financial, investment or trading advice.
What it does
- Role-specialised agents: fundamentals, sentiment, news and technical analysts, plus trader, risk team and portfolio manager
- Structured bull-versus-bear researcher debate before a position is proposed
- Built on LangGraph, with checkpoint resume and a persistent decision log
- Wide provider support — OpenAI, Google, Anthropic, xAI, DeepSeek, Qwen, GLM, MiniMax, OpenRouter, Azure and Bedrock — plus Ollama and OpenAI-compatible local servers
- Interactive CLI for picking tickers, analysis date, provider and research depth, and a Python package for use in your own code
- Works with any market Yahoo Finance covers via exchange-suffixed tickers (0700.HK, 7203.T, RELIANCE.NS, 600519.SS) and crypto pairs like BTC-USD
Getting started
Clone the repo, install it into a fresh environment, set the API key for whichever LLM provider you want to drive the agents, then launch the CLI.
Clone and create an environment
The README uses conda, but any environment manager works.
git clone https://github.com/TauricResearch/TradingAgents.git
cd TradingAgents
conda create -n tradingagents python=3.12
conda activate tradingagentsInstall the package
Install TradingAgents and its dependencies from the checkout.
pip install .Set your provider keys
Export the key for the provider you plan to use; Alpha Vantage supplies market data. You can also copy .env.example to .env and fill it in there.
export OPENAI_API_KEY=...
export ANTHROPIC_API_KEY=...
export ALPHA_VANTAGE_API_KEY=...Run the CLI
The interactive CLI asks for tickers, an analysis date, the LLM provider and research depth, then streams each agent's progress as it runs. A Docker path (docker compose run --rm tradingagents) is available too.
tradingagentsCommands and code are distilled from the project's own documentation — always check the official repo for the latest.
When to use it
- Studying how role-specialised agents and structured debate change an LLM's decision quality
- A worked reference for multi-agent design: analyst fan-out, adversarial review, then a single decision-maker
- Backtesting research on how different backbone models reason over the same market inputs
- Prototyping finance-flavoured agent pipelines over live news, fundamentals and technical indicators
How TradingAgents compares
TradingAgents alongside other open-source finance & market agents tools AI/TLDR tracks, ranked by GitHub stars.
| Tool | Stars | What it does |
|---|---|---|
| TradingAgents | ★ 120k | An LLM trading firm: analysts, bull-bear researchers, trader and risk agents |
| Daily Stock Analysis | ★ 67.5k | LLM research pipeline for A-share, Hong Kong, US, Japanese, Korean and Taiwanese tickers: pulls quotes, indicators and news, writes a decision dashboard and pushes it to chat or email. |
| Vibe-Trading | ★ 37.5k | An open-source trading research workspace from HKUDS: natural-language market research, multi-agent analyst teams, cross-market backtests, and an MCP server for Claude, Cursor and other clients. |
| AI Berkshire | ★ 17k | Value-investing research skills for Claude Code and Codex that turn the methods of Buffett, Munger, Duan Yongping and Li Lu into structured, multi-agent research workflows. |
| QuantDinger | ★ 13.4k | A self-hosted trading stack that carries an idea from AI market research to a Python strategy, a server-side backtest and paper or live execution on crypto exchanges and brokers, driven from the web, an API or MCP. |
| a-stock-data | ★ 11.4k | A single-file agent skill that gives AI coding assistants China A-share market data (quotes, research, fund flow, filings, macro, futures and more) from 34 mostly keyless sources. |
| ValueCell | ★ 11k | A multi-agent platform for financial work, pairing deep-research, news and strategy agents over US, Hong Kong, China and crypto market data, with credentials kept on the local device. |
| FinRobot | ★ 8.4k | Multi-agent equity-research platform where DCF, WACC and Monte Carlo figures are computed by deterministic Python operators and the LLM only writes the narrative. |