Verified project record

TauricResearch/TradingAgents

A multi-agent LLM framework that mirrors a real-world trading firm by deploying specialized agents to collaboratively evaluate market conditions and inform trading decisions. It deploys specialized agents for fundamentals, sentiment, news, and technical analysis, followed by structured researcher debates and risk management.

Project overview

Project type: AI Agent · Workflow · Data Processing
Use cases: Search & Research · Data Analysis
Deployment: Refer to project documentation
License: Apache-2.0

Best for

Researchers, developers, and data teams investigating multi-agent collaboration for deep research and AI data analysis.
Users needing a simulated exchange environment with structured bull and bear debates, persistent decision logging, and checkpoint resumption.

Key capabilities

Deploys specialized agents (Fundamentals, Sentiment, News, Technical) to evaluate company financials, aggregate sentiment from social/news, monitor macro indicators, and detect trading patterns.
Comprises bullish and bearish researchers who critically assess insights through structured debates to balance potential gains against risks.
Composes reports from analysts and researchers to make informed trading decisions, determining the timing and magnitude of trades.
Continuously evaluates portfolio risk and adjusts strategies, with the Portfolio Manager approving or rejecting transaction proposals for the simulated exchange.
Works with any market Yahoo Finance covers, using exchange-suffixed tickers, and automatically resolves company identity and alpha benchmarks.
Supports multiple LLM providers including OpenAI, Google, Anthropic, xAI, DeepSeek, Qwen, GLM, MiniMax, OpenRouter, Ollama, Azure OpenAI, and AWS Bedrock.
Always-on persistent log appending completed decisions, realized returns, and reflections to memory for future runs.
Opt-in saving of state after each node so a crashed or interrupted run resumes from the last successful step instead of starting over.

Limitations and risks

LLM-driven sampling is non-deterministic, meaning two runs of the same ticker and date can differ.
Live social and news data changes over time, causing runs on the same historical date to see different inputs.
Backtest results are not guaranteed to match any published figure due to various model and data factors.
The framework is designed for research purposes and is not intended as financial, investment, or trading advice.

Getting started

Clone the repository and install via pip in a conda environment. Configure environment variables for API keys, launch the interactive CLI, and select a ticker, date, and analysis depth to begin.

Evidence and sources

GitHub project description: TradingAgents: Multi-Agents LLM Financial Trading Framework
README: TradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms.
README: By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively ev…
README: - Fundamentals Analyst: Evaluates company financials and performance metrics, identifying intrinsic values and potential red flags.
README: TradingAgents officially released! We have received numerous inquiries about the work, and we would like to express our thanks for the enthusiasm in our community.

Reviewed at: 2026-07-17T04:23:29Z