.db` (override the base with `TRADINGAGENTS_CACHE_DIR`). Use `--clear-checkpoints` to reset all of them before a run.\n\n```bash\ntradingagents analyze --checkpoint # enable for this run\ntradingagents analyze --clear-checkpoints # reset before running\n```\n\n```python\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"checkpoint_enabled\"] = True\nta = TradingAgentsGraph(config=config)\n_, decision = ta.propagate(\"NVDA\", \"2026-01-15\")\n```\n\n## Contributing\n\nWe welcome contributions from the community! Whether it's fixing a bug, improving documentation, or suggesting a new feature, your input helps make this project better. If you are interested in this line of research, please consider joining our open-source financial AI research community [Tauric Research](https://tauric.ai/).\n\n## Citation\n\nPlease reference our work if you find *TradingAgents* provides you with some help :)\n\n```\n@misc{xiao2025tradingagentsmultiagentsllmfinancial,\n title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, \n author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang},\n year={2025},\n eprint={2412.20138},\n archivePrefix={arXiv},\n primaryClass={q-fin.TR},\n url={https://arxiv.org/abs/2412.20138}, \n}\n```\n"}, "b0f6058299ed0e31677a1e3eb31b662aca10abd4": {"t": 1785766188.5943928, "n": 11292, "h": "6fd859089d40133e", "c": "\n ![](\"assets/TauricResearch.png\")
\n
\n\n\n\n\n\n---\n\n# TradingAgents: Multi-Agents LLM Financial Trading Framework\n\n## News\n- [2026-03] **TradingAgents v0.2.3** released with multi-language support, GPT-5.4 family models, unified model catalog, backtesting date fidelity, and proxy support.\n- [2026-03] **TradingAgents v0.2.2** released with GPT-5.4/Gemini 3.1/Claude 4.6 model coverage, five-tier rating scale, OpenAI Responses API, Anthropic effort control, and cross-platform stability.\n- [2026-02] **TradingAgents v0.2.0** released with multi-provider LLM support (GPT-5.x, Gemini 3.x, Claude 4.x, Grok 4.x) and improved system architecture.\n- [2026-01] **Trading-R1** [Technical Report](https://arxiv.org/abs/2509.11420) released, with [Terminal](https://github.com/TauricResearch/Trading-R1) expected to land soon.\n\n\n\n> 🎉 **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.\n>\n> So we decided to fully open-source the framework. Looking forward to building impactful projects with you!\n\n\n\n🚀 [TradingAgents](#tradingagents-framework) | ⚡ [Installation & CLI](#installation-and-cli) | 🎬 [Demo](https://www.youtube.com/watch?v=90gr5lwjIho) | 📦 [Package Usage](#tradingagents-package) | 🤝 [Contributing](#contributing) | 📄 [Citation](#citation)\n\n
\n\n## TradingAgents Framework\n\nTradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively evaluates market conditions and informs trading decisions. Moreover, these agents engage in dynamic discussions to pinpoint the optimal strategy.\n\n\n ![](\"assets/schema.png\")
\n
\n\n> TradingAgents framework is designed for research purposes. Trading performance may vary based on many factors, including the chosen backbone language models, model temperature, trading periods, the quality of data, and other non-deterministic factors. [It is not intended as financial, investment, or trading advice.](https://tauric.ai/disclaimer/)\n\nOur framework decomposes complex trading tasks into specialized roles. This ensures the system achieves a robust, scalable approach to market analysis and decision-making.\n\n### Analyst Team\n- Fundamentals Analyst: Evaluates company financials and performance metrics, identifying intrinsic values and potential red flags.\n- Sentiment Analyst: Analyzes social media and public sentiment using sentiment scoring algorithms to gauge short-term market mood.\n- News Analyst: Monitors global news and macroeconomic indicators, interpreting the impact of events on market conditions.\n- Technical Analyst: Utilizes technical indicators (like MACD and RSI) to detect trading patterns and forecast price movements.\n\n\n ![](\"assets/analyst.png\")
\n
\n\n### Researcher Team\n- Comprises both bullish and bearish researchers who critically assess the insights provided by the Analyst Team. Through structured debates, they balance potential gains against inherent risks.\n\n\n ![](\"assets/researcher.png\")
\n
\n\n### Trader Agent\n- Composes reports from the analysts and researchers to make informed trading decisions. It determines the timing and magnitude of trades based on comprehensive market insights.\n\n\n ![](\"assets/trader.png\")
\n
\n\n### Risk Management and Portfolio Manager\n- Continuously evaluates portfolio risk by assessing market volatility, liquidity, and other risk factors. The risk management team evaluates and adjusts trading strategies, providing assessment reports to the Portfolio Manager for final decision.\n- The Portfolio Manager approves/rejects the transaction proposal. If approved, the order will be sent to the simulated exchange and executed.\n\n\n ![](\"assets/risk.png\")
\n
\n\n## Installation and CLI\n\n### Installation\n\nClone TradingAgents:\n```bash\ngit clone https://github.com/TauricResearch/TradingAgents.git\ncd TradingAgents\n```\n\nCreate a virtual environment in any of your favorite environment managers:\n```bash\nconda create -n tradingagents python=3.13\nconda activate tradingagents\n```\n\nInstall the package and its dependencies:\n```bash\npip install .\n```\n\n### Docker\n\nAlternatively, run with Docker:\n```bash\ncp .env.example .env # add your API keys\ndocker compose run --rm tradingagents\n```\n\nFor local models with Ollama:\n```bash\ndocker compose --profile ollama run --rm tradingagents-ollama\n```\n\n### Required APIs\n\nTradingAgents supports multiple LLM providers. Set the API key for your chosen provider:\n\n```bash\nexport OPENAI_API_KEY=... # OpenAI (GPT)\nexport GOOGLE_API_KEY=... # Google (Gemini)\nexport ANTHROPIC_API_KEY=... # Anthropic (Claude)\nexport XAI_API_KEY=... # xAI (Grok)\nexport DEEPSEEK_API_KEY=... # DeepSeek\nexport DASHSCOPE_API_KEY=... # Qwen (Alibaba DashScope)\nexport ZHIPU_API_KEY=... # GLM (Zhipu)\nexport OPENROUTER_API_KEY=... # OpenRouter\nexport ALPHA_VANTAGE_API_KEY=... # Alpha Vantage\n```\n\nFor enterprise providers (e.g. Azure OpenAI, AWS Bedrock), copy `.env.enterprise.example` to `.env.enterprise` and fill in your credentials.\n\nFor local models, configure Ollama with `llm_provider: \"ollama\"` in your config.\n\nAlternatively, copy `.env.example` to `.env` and fill in your keys:\n```bash\ncp .env.example .env\n```\n\n### CLI Usage\n\nLaunch the interactive CLI:\n```bash\ntradingagents # installed command\npython -m cli.main # alternative: run directly from source\n```\nYou will see a screen where you can select your desired tickers, analysis date, LLM provider, research depth, and more.\n\n\n ![](\"assets/cli/cli_init.png\")
\n
\n\nAn interface will appear showing results as they load, letting you track the agent's progress as it runs.\n\n\n ![](\"assets/cli/cli_news.png\")
\n
\n\n\n ![](\"assets/cli/cli_transaction.png\")
\n
\n\n## TradingAgents Package\n\n### Implementation Details\n\nWe built TradingAgents with LangGraph to ensure flexibility and modularity. The framework supports multiple LLM providers: OpenAI, Google, Anthropic, xAI, OpenRouter, and Ollama.\n\n### Python Usage\n\nTo use TradingAgents inside your code, you can import the `tradingagents` module and initialize a `TradingAgentsGraph()` object. The `.propagate()` function will return a decision. You can run `main.py`, here's also a quick example:\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2026-01-15\")\nprint(decision)\n```\n\nYou can also adjust the default configuration to set your own choice of LLMs, debate rounds, etc.\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"llm_provider\"] = \"openai\" # openai, google, anthropic, xai, openrouter, ollama\nconfig[\"deep_think_llm\"] = \"gpt-5.4\" # Model for complex reasoning\nconfig[\"quick_think_llm\"] = \"gpt-5.4-mini\" # Model for quick tasks\nconfig[\"max_debate_rounds\"] = 2\n\nta = TradingAgentsGraph(debug=True, config=config)\n_, decision = ta.propagate(\"NVDA\", \"2026-01-15\")\nprint(decision)\n```\n\nSee `tradingagents/default_config.py` for all configuration options.\n\n## Contributing\n\nWe welcome contributions from the community! Whether it's fixing a bug, improving documentation, or suggesting a new feature, your input helps make this project better. If you are interested in this line of research, please consider joining our open-source financial AI research community [Tauric Research](https://tauric.ai/).\n\n## Citation\n\nPlease reference our work if you find *TradingAgents* provides you with some help :)\n\n```\n@misc{xiao2025tradingagentsmultiagentsllmfinancial,\n title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, \n author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang},\n year={2025},\n eprint={2412.20138},\n archivePrefix={arXiv},\n primaryClass={q-fin.TR},\n url={https://arxiv.org/abs/2412.20138}, \n}\n```\n"}, "10c136f49c82e11f0e324c9c50cda1638a8ed5a7": {"t": 1785766190.5339255, "n": 10993, "h": "a58e216685dd4e9b", "c": "\n \n
\n\n\n\n\n\n---\n\n# TradingAgents: Multi-Agents LLM Financial Trading Framework\n\n## News\n- [2026-03] **TradingAgents v0.2.3** released with multi-language support, GPT-5.4 family models, unified model catalog, backtesting date fidelity, and proxy support.\n- [2026-03] **TradingAgents v0.2.2** released with GPT-5.4/Gemini 3.1/Claude 4.6 model coverage, five-tier rating scale, OpenAI Responses API, Anthropic effort control, and cross-platform stability.\n- [2026-02] **TradingAgents v0.2.0** released with multi-provider LLM support (GPT-5.x, Gemini 3.x, Claude 4.x, Grok 4.x) and improved system architecture.\n- [2026-01] **Trading-R1** [Technical Report](https://arxiv.org/abs/2509.11420) released, with [Terminal](https://github.com/TauricResearch/Trading-R1) expected to land soon.\n\n\n\n> 🎉 **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.\n>\n> So we decided to fully open-source the framework. Looking forward to building impactful projects with you!\n\n\n\n🚀 [TradingAgents](#tradingagents-framework) | ⚡ [Installation & CLI](#installation-and-cli) | 🎬 [Demo](https://www.youtube.com/watch?v=90gr5lwjIho) | 📦 [Package Usage](#tradingagents-package) | 🤝 [Contributing](#contributing) | 📄 [Citation](#citation)\n\n
\n\n## TradingAgents Framework\n\nTradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively evaluates market conditions and informs trading decisions. Moreover, these agents engage in dynamic discussions to pinpoint the optimal strategy.\n\n\n \n
\n\n> TradingAgents framework is designed for research purposes. Trading performance may vary based on many factors, including the chosen backbone language models, model temperature, trading periods, the quality of data, and other non-deterministic factors. [It is not intended as financial, investment, or trading advice.](https://tauric.ai/disclaimer/)\n\nOur framework decomposes complex trading tasks into specialized roles. This ensures the system achieves a robust, scalable approach to market analysis and decision-making.\n\n### Analyst Team\n- Fundamentals Analyst: Evaluates company financials and performance metrics, identifying intrinsic values and potential red flags.\n- Sentiment Analyst: Analyzes social media and public sentiment using sentiment scoring algorithms to gauge short-term market mood.\n- News Analyst: Monitors global news and macroeconomic indicators, interpreting the impact of events on market conditions.\n- Technical Analyst: Utilizes technical indicators (like MACD and RSI) to detect trading patterns and forecast price movements.\n\n\n \n
\n\n### Researcher Team\n- Comprises both bullish and bearish researchers who critically assess the insights provided by the Analyst Team. Through structured debates, they balance potential gains against inherent risks.\n\n\n \n
\n\n### Trader Agent\n- Composes reports from the analysts and researchers to make informed trading decisions. It determines the timing and magnitude of trades based on comprehensive market insights.\n\n\n \n
\n\n### Risk Management and Portfolio Manager\n- Continuously evaluates portfolio risk by assessing market volatility, liquidity, and other risk factors. The risk management team evaluates and adjusts trading strategies, providing assessment reports to the Portfolio Manager for final decision.\n- The Portfolio Manager approves/rejects the transaction proposal. If approved, the order will be sent to the simulated exchange and executed.\n\n\n \n
\n\n## Installation and CLI\n\n### Installation\n\nClone TradingAgents:\n```bash\ngit clone https://github.com/TauricResearch/TradingAgents.git\ncd TradingAgents\n```\n\nCreate a virtual environment in any of your favorite environment managers:\n```bash\nconda create -n tradingagents python=3.13\nconda activate tradingagents\n```\n\nInstall the package and its dependencies:\n```bash\npip install .\n```\n\n### Docker\n\nAlternatively, run with Docker:\n```bash\ncp .env.example .env # add your API keys\ndocker compose run --rm tradingagents\n```\n\nFor local models with Ollama:\n```bash\ndocker compose --profile ollama run --rm tradingagents-ollama\n```\n\n### Required APIs\n\nTradingAgents supports multiple LLM providers. Set the API key for your chosen provider:\n\n```bash\nexport OPENAI_API_KEY=... # OpenAI (GPT)\nexport GOOGLE_API_KEY=... # Google (Gemini)\nexport ANTHROPIC_API_KEY=... # Anthropic (Claude)\nexport XAI_API_KEY=... # xAI (Grok)\nexport OPENROUTER_API_KEY=... # OpenRouter\nexport ALPHA_VANTAGE_API_KEY=... # Alpha Vantage\n```\n\nFor local models, configure Ollama with `llm_provider: \"ollama\"` in your config.\n\nAlternatively, copy `.env.example` to `.env` and fill in your keys:\n```bash\ncp .env.example .env\n```\n\n### CLI Usage\n\nLaunch the interactive CLI:\n```bash\ntradingagents # installed command\npython -m cli.main # alternative: run directly from source\n```\nYou will see a screen where you can select your desired tickers, analysis date, LLM provider, research depth, and more.\n\n\n \n
\n\nAn interface will appear showing results as they load, letting you track the agent's progress as it runs.\n\n\n \n
\n\n\n \n
\n\n## TradingAgents Package\n\n### Implementation Details\n\nWe built TradingAgents with LangGraph to ensure flexibility and modularity. The framework supports multiple LLM providers: OpenAI, Google, Anthropic, xAI, OpenRouter, and Ollama.\n\n### Python Usage\n\nTo use TradingAgents inside your code, you can import the `tradingagents` module and initialize a `TradingAgentsGraph()` object. The `.propagate()` function will return a decision. You can run `main.py`, here's also a quick example:\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2026-01-15\")\nprint(decision)\n```\n\nYou can also adjust the default configuration to set your own choice of LLMs, debate rounds, etc.\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"llm_provider\"] = \"openai\" # openai, google, anthropic, xai, openrouter, ollama\nconfig[\"deep_think_llm\"] = \"gpt-5.4\" # Model for complex reasoning\nconfig[\"quick_think_llm\"] = \"gpt-5.4-mini\" # Model for quick tasks\nconfig[\"max_debate_rounds\"] = 2\n\nta = TradingAgentsGraph(debug=True, config=config)\n_, decision = ta.propagate(\"NVDA\", \"2026-01-15\")\nprint(decision)\n```\n\nSee `tradingagents/default_config.py` for all configuration options.\n\n## Contributing\n\nWe welcome contributions from the community! Whether it's fixing a bug, improving documentation, or suggesting a new feature, your input helps make this project better. If you are interested in this line of research, please consider joining our open-source financial AI research community [Tauric Research](https://tauric.ai/).\n\n## Citation\n\nPlease reference our work if you find *TradingAgents* provides you with some help :)\n\n```\n@misc{xiao2025tradingagentsmultiagentsllmfinancial,\n title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, \n author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang},\n year={2025},\n eprint={2412.20138},\n archivePrefix={arXiv},\n primaryClass={q-fin.TR},\n url={https://arxiv.org/abs/2412.20138}, \n}\n```\n"}, "4641c03340c70e0e75e74234c998325164c72b36": {"t": 1785766192.1037755, "n": 10751, "h": "8915e860acdc92df", "c": "\n \n
\n\n\n\n\n\n---\n\n# TradingAgents: Multi-Agents LLM Financial Trading Framework\n\n## News\n- [2026-03] **TradingAgents v0.2.3** released with multi-language support, GPT-5.4 family models, unified model catalog, backtesting date fidelity, and proxy support.\n- [2026-03] **TradingAgents v0.2.2** released with GPT-5.4/Gemini 3.1/Claude 4.6 model coverage, five-tier rating scale, OpenAI Responses API, Anthropic effort control, and cross-platform stability.\n- [2026-02] **TradingAgents v0.2.0** released with multi-provider LLM support (GPT-5.x, Gemini 3.x, Claude 4.x, Grok 4.x) and improved system architecture.\n- [2026-01] **Trading-R1** [Technical Report](https://arxiv.org/abs/2509.11420) released, with [Terminal](https://github.com/TauricResearch/Trading-R1) expected to land soon.\n\n\n\n> 🎉 **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.\n>\n> So we decided to fully open-source the framework. Looking forward to building impactful projects with you!\n\n\n\n🚀 [TradingAgents](#tradingagents-framework) | ⚡ [Installation & CLI](#installation-and-cli) | 🎬 [Demo](https://www.youtube.com/watch?v=90gr5lwjIho) | 📦 [Package Usage](#tradingagents-package) | 🤝 [Contributing](#contributing) | 📄 [Citation](#citation)\n\n
\n\n## TradingAgents Framework\n\nTradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively evaluates market conditions and informs trading decisions. Moreover, these agents engage in dynamic discussions to pinpoint the optimal strategy.\n\n\n \n
\n\n> TradingAgents framework is designed for research purposes. Trading performance may vary based on many factors, including the chosen backbone language models, model temperature, trading periods, the quality of data, and other non-deterministic factors. [It is not intended as financial, investment, or trading advice.](https://tauric.ai/disclaimer/)\n\nOur framework decomposes complex trading tasks into specialized roles. This ensures the system achieves a robust, scalable approach to market analysis and decision-making.\n\n### Analyst Team\n- Fundamentals Analyst: Evaluates company financials and performance metrics, identifying intrinsic values and potential red flags.\n- Sentiment Analyst: Analyzes social media and public sentiment using sentiment scoring algorithms to gauge short-term market mood.\n- News Analyst: Monitors global news and macroeconomic indicators, interpreting the impact of events on market conditions.\n- Technical Analyst: Utilizes technical indicators (like MACD and RSI) to detect trading patterns and forecast price movements.\n\n\n \n
\n\n### Researcher Team\n- Comprises both bullish and bearish researchers who critically assess the insights provided by the Analyst Team. Through structured debates, they balance potential gains against inherent risks.\n\n\n \n
\n\n### Trader Agent\n- Composes reports from the analysts and researchers to make informed trading decisions. It determines the timing and magnitude of trades based on comprehensive market insights.\n\n\n \n
\n\n### Risk Management and Portfolio Manager\n- Continuously evaluates portfolio risk by assessing market volatility, liquidity, and other risk factors. The risk management team evaluates and adjusts trading strategies, providing assessment reports to the Portfolio Manager for final decision.\n- The Portfolio Manager approves/rejects the transaction proposal. If approved, the order will be sent to the simulated exchange and executed.\n\n\n \n
\n\n## Installation and CLI\n\n### Installation\n\nClone TradingAgents:\n```bash\ngit clone https://github.com/TauricResearch/TradingAgents.git\ncd TradingAgents\n```\n\nCreate a virtual environment in any of your favorite environment managers:\n```bash\nconda create -n tradingagents python=3.13\nconda activate tradingagents\n```\n\nInstall the package and its dependencies:\n```bash\npip install .\n```\n\n### Required APIs\n\nTradingAgents supports multiple LLM providers. Set the API key for your chosen provider:\n\n```bash\nexport OPENAI_API_KEY=... # OpenAI (GPT)\nexport GOOGLE_API_KEY=... # Google (Gemini)\nexport ANTHROPIC_API_KEY=... # Anthropic (Claude)\nexport XAI_API_KEY=... # xAI (Grok)\nexport OPENROUTER_API_KEY=... # OpenRouter\nexport ALPHA_VANTAGE_API_KEY=... # Alpha Vantage\n```\n\nFor local models, configure Ollama with `llm_provider: \"ollama\"` in your config.\n\nAlternatively, copy `.env.example` to `.env` and fill in your keys:\n```bash\ncp .env.example .env\n```\n\n### CLI Usage\n\nLaunch the interactive CLI:\n```bash\ntradingagents # installed command\npython -m cli.main # alternative: run directly from source\n```\nYou will see a screen where you can select your desired tickers, analysis date, LLM provider, research depth, and more.\n\n\n \n
\n\nAn interface will appear showing results as they load, letting you track the agent's progress as it runs.\n\n\n \n
\n\n\n \n
\n\n## TradingAgents Package\n\n### Implementation Details\n\nWe built TradingAgents with LangGraph to ensure flexibility and modularity. The framework supports multiple LLM providers: OpenAI, Google, Anthropic, xAI, OpenRouter, and Ollama.\n\n### Python Usage\n\nTo use TradingAgents inside your code, you can import the `tradingagents` module and initialize a `TradingAgentsGraph()` object. The `.propagate()` function will return a decision. You can run `main.py`, here's also a quick example:\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2026-01-15\")\nprint(decision)\n```\n\nYou can also adjust the default configuration to set your own choice of LLMs, debate rounds, etc.\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"llm_provider\"] = \"openai\" # openai, google, anthropic, xai, openrouter, ollama\nconfig[\"deep_think_llm\"] = \"gpt-5.4\" # Model for complex reasoning\nconfig[\"quick_think_llm\"] = \"gpt-5.4-mini\" # Model for quick tasks\nconfig[\"max_debate_rounds\"] = 2\n\nta = TradingAgentsGraph(debug=True, config=config)\n_, decision = ta.propagate(\"NVDA\", \"2026-01-15\")\nprint(decision)\n```\n\nSee `tradingagents/default_config.py` for all configuration options.\n\n## Contributing\n\nWe welcome contributions from the community! Whether it's fixing a bug, improving documentation, or suggesting a new feature, your input helps make this project better. If you are interested in this line of research, please consider joining our open-source financial AI research community [Tauric Research](https://tauric.ai/).\n\n## Citation\n\nPlease reference our work if you find *TradingAgents* provides you with some help :)\n\n```\n@misc{xiao2025tradingagentsmultiagentsllmfinancial,\n title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, \n author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang},\n year={2025},\n eprint={2412.20138},\n archivePrefix={arXiv},\n primaryClass={q-fin.TR},\n url={https://arxiv.org/abs/2412.20138}, \n}\n```\n"}, "e75d17bc51981b49ed47c6a2c2016100e0689e09": {"t": 1785766193.6249661, "n": 10584, "h": "46c3b0eff6759bf1", "c": "\n \n
\n\n\n\n\n\n---\n\n# TradingAgents: Multi-Agents LLM Financial Trading Framework\n\n## News\n- [2026-03] **TradingAgents v0.2.2** released with GPT-5.4/Gemini 3.1/Claude 4.6 model coverage, five-tier rating scale, OpenAI Responses API, Anthropic effort control, and cross-platform stability.\n- [2026-02] **TradingAgents v0.2.0** released with multi-provider LLM support (GPT-5.x, Gemini 3.x, Claude 4.x, Grok 4.x) and improved system architecture.\n- [2026-01] **Trading-R1** [Technical Report](https://arxiv.org/abs/2509.11420) released, with [Terminal](https://github.com/TauricResearch/Trading-R1) expected to land soon.\n\n\n\n> 🎉 **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.\n>\n> So we decided to fully open-source the framework. Looking forward to building impactful projects with you!\n\n\n\n🚀 [TradingAgents](#tradingagents-framework) | ⚡ [Installation & CLI](#installation-and-cli) | 🎬 [Demo](https://www.youtube.com/watch?v=90gr5lwjIho) | 📦 [Package Usage](#tradingagents-package) | 🤝 [Contributing](#contributing) | 📄 [Citation](#citation)\n\n
\n\n## TradingAgents Framework\n\nTradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively evaluates market conditions and informs trading decisions. Moreover, these agents engage in dynamic discussions to pinpoint the optimal strategy.\n\n\n \n
\n\n> TradingAgents framework is designed for research purposes. Trading performance may vary based on many factors, including the chosen backbone language models, model temperature, trading periods, the quality of data, and other non-deterministic factors. [It is not intended as financial, investment, or trading advice.](https://tauric.ai/disclaimer/)\n\nOur framework decomposes complex trading tasks into specialized roles. This ensures the system achieves a robust, scalable approach to market analysis and decision-making.\n\n### Analyst Team\n- Fundamentals Analyst: Evaluates company financials and performance metrics, identifying intrinsic values and potential red flags.\n- Sentiment Analyst: Analyzes social media and public sentiment using sentiment scoring algorithms to gauge short-term market mood.\n- News Analyst: Monitors global news and macroeconomic indicators, interpreting the impact of events on market conditions.\n- Technical Analyst: Utilizes technical indicators (like MACD and RSI) to detect trading patterns and forecast price movements.\n\n\n \n
\n\n### Researcher Team\n- Comprises both bullish and bearish researchers who critically assess the insights provided by the Analyst Team. Through structured debates, they balance potential gains against inherent risks.\n\n\n \n
\n\n### Trader Agent\n- Composes reports from the analysts and researchers to make informed trading decisions. It determines the timing and magnitude of trades based on comprehensive market insights.\n\n\n \n
\n\n### Risk Management and Portfolio Manager\n- Continuously evaluates portfolio risk by assessing market volatility, liquidity, and other risk factors. The risk management team evaluates and adjusts trading strategies, providing assessment reports to the Portfolio Manager for final decision.\n- The Portfolio Manager approves/rejects the transaction proposal. If approved, the order will be sent to the simulated exchange and executed.\n\n\n \n
\n\n## Installation and CLI\n\n### Installation\n\nClone TradingAgents:\n```bash\ngit clone https://github.com/TauricResearch/TradingAgents.git\ncd TradingAgents\n```\n\nCreate a virtual environment in any of your favorite environment managers:\n```bash\nconda create -n tradingagents python=3.13\nconda activate tradingagents\n```\n\nInstall the package and its dependencies:\n```bash\npip install .\n```\n\n### Required APIs\n\nTradingAgents supports multiple LLM providers. Set the API key for your chosen provider:\n\n```bash\nexport OPENAI_API_KEY=... # OpenAI (GPT)\nexport GOOGLE_API_KEY=... # Google (Gemini)\nexport ANTHROPIC_API_KEY=... # Anthropic (Claude)\nexport XAI_API_KEY=... # xAI (Grok)\nexport OPENROUTER_API_KEY=... # OpenRouter\nexport ALPHA_VANTAGE_API_KEY=... # Alpha Vantage\n```\n\nFor local models, configure Ollama with `llm_provider: \"ollama\"` in your config.\n\nAlternatively, copy `.env.example` to `.env` and fill in your keys:\n```bash\ncp .env.example .env\n```\n\n### CLI Usage\n\nLaunch the interactive CLI:\n```bash\ntradingagents # installed command\npython -m cli.main # alternative: run directly from source\n```\nYou will see a screen where you can select your desired tickers, analysis date, LLM provider, research depth, and more.\n\n\n \n
\n\nAn interface will appear showing results as they load, letting you track the agent's progress as it runs.\n\n\n \n
\n\n\n \n
\n\n## TradingAgents Package\n\n### Implementation Details\n\nWe built TradingAgents with LangGraph to ensure flexibility and modularity. The framework supports multiple LLM providers: OpenAI, Google, Anthropic, xAI, OpenRouter, and Ollama.\n\n### Python Usage\n\nTo use TradingAgents inside your code, you can import the `tradingagents` module and initialize a `TradingAgentsGraph()` object. The `.propagate()` function will return a decision. You can run `main.py`, here's also a quick example:\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2026-01-15\")\nprint(decision)\n```\n\nYou can also adjust the default configuration to set your own choice of LLMs, debate rounds, etc.\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"llm_provider\"] = \"openai\" # openai, google, anthropic, xai, openrouter, ollama\nconfig[\"deep_think_llm\"] = \"gpt-5.4\" # Model for complex reasoning\nconfig[\"quick_think_llm\"] = \"gpt-5.4-mini\" # Model for quick tasks\nconfig[\"max_debate_rounds\"] = 2\n\nta = TradingAgentsGraph(debug=True, config=config)\n_, decision = ta.propagate(\"NVDA\", \"2026-01-15\")\nprint(decision)\n```\n\nSee `tradingagents/default_config.py` for all configuration options.\n\n## Contributing\n\nWe welcome contributions from the community! Whether it's fixing a bug, improving documentation, or suggesting a new feature, your input helps make this project better. If you are interested in this line of research, please consider joining our open-source financial AI research community [Tauric Research](https://tauric.ai/).\n\n## Citation\n\nPlease reference our work if you find *TradingAgents* provides you with some help :)\n\n```\n@misc{xiao2025tradingagentsmultiagentsllmfinancial,\n title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, \n author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang},\n year={2025},\n eprint={2412.20138},\n archivePrefix={arXiv},\n primaryClass={q-fin.TR},\n url={https://arxiv.org/abs/2412.20138}, \n}\n```\n"}, "589b351f2ab55a8a37d846848479cebc810a5a36": {"t": 1785766195.3629029, "n": 10582, "h": "996be7c9a4715864", "c": "\n \n
\n\n\n\n\n\n---\n\n# TradingAgents: Multi-Agents LLM Financial Trading Framework\n\n## News\n- [2026-03] **TradingAgents v0.2.2** released with GPT-5.4/Gemini 3.1/Claude 4.6 model coverage, five-tier rating scale, OpenAI Responses API, Anthropic effort control, and cross-platform stability.\n- [2026-02] **TradingAgents v0.2.0** released with multi-provider LLM support (GPT-5.x, Gemini 3.x, Claude 4.x, Grok 4.x) and improved system architecture.\n- [2026-01] **Trading-R1** [Technical Report](https://arxiv.org/abs/2509.11420) released, with [Terminal](https://github.com/TauricResearch/Trading-R1) expected to land soon.\n\n\n\n> 🎉 **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.\n>\n> So we decided to fully open-source the framework. Looking forward to building impactful projects with you!\n\n\n\n🚀 [TradingAgents](#tradingagents-framework) | ⚡ [Installation & CLI](#installation-and-cli) | 🎬 [Demo](https://www.youtube.com/watch?v=90gr5lwjIho) | 📦 [Package Usage](#tradingagents-package) | 🤝 [Contributing](#contributing) | 📄 [Citation](#citation)\n\n
\n\n## TradingAgents Framework\n\nTradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively evaluates market conditions and informs trading decisions. Moreover, these agents engage in dynamic discussions to pinpoint the optimal strategy.\n\n\n \n
\n\n> TradingAgents framework is designed for research purposes. Trading performance may vary based on many factors, including the chosen backbone language models, model temperature, trading periods, the quality of data, and other non-deterministic factors. [It is not intended as financial, investment, or trading advice.](https://tauric.ai/disclaimer/)\n\nOur framework decomposes complex trading tasks into specialized roles. This ensures the system achieves a robust, scalable approach to market analysis and decision-making.\n\n### Analyst Team\n- Fundamentals Analyst: Evaluates company financials and performance metrics, identifying intrinsic values and potential red flags.\n- Sentiment Analyst: Analyzes social media and public sentiment using sentiment scoring algorithms to gauge short-term market mood.\n- News Analyst: Monitors global news and macroeconomic indicators, interpreting the impact of events on market conditions.\n- Technical Analyst: Utilizes technical indicators (like MACD and RSI) to detect trading patterns and forecast price movements.\n\n\n \n
\n\n### Researcher Team\n- Comprises both bullish and bearish researchers who critically assess the insights provided by the Analyst Team. Through structured debates, they balance potential gains against inherent risks.\n\n\n \n
\n\n### Trader Agent\n- Composes reports from the analysts and researchers to make informed trading decisions. It determines the timing and magnitude of trades based on comprehensive market insights.\n\n\n \n
\n\n### Risk Management and Portfolio Manager\n- Continuously evaluates portfolio risk by assessing market volatility, liquidity, and other risk factors. The risk management team evaluates and adjusts trading strategies, providing assessment reports to the Portfolio Manager for final decision.\n- The Portfolio Manager approves/rejects the transaction proposal. If approved, the order will be sent to the simulated exchange and executed.\n\n\n \n
\n\n## Installation and CLI\n\n### Installation\n\nClone TradingAgents:\n```bash\ngit clone https://github.com/TauricResearch/TradingAgents.git\ncd TradingAgents\n```\n\nCreate a virtual environment in any of your favorite environment managers:\n```bash\nconda create -n tradingagents python=3.13\nconda activate tradingagents\n```\n\nInstall the package and its dependencies:\n```bash\npip install .\n```\n\n### Required APIs\n\nTradingAgents supports multiple LLM providers. Set the API key for your chosen provider:\n\n```bash\nexport OPENAI_API_KEY=... # OpenAI (GPT)\nexport GOOGLE_API_KEY=... # Google (Gemini)\nexport ANTHROPIC_API_KEY=... # Anthropic (Claude)\nexport XAI_API_KEY=... # xAI (Grok)\nexport OPENROUTER_API_KEY=... # OpenRouter\nexport ALPHA_VANTAGE_API_KEY=... # Alpha Vantage\n```\n\nFor local models, configure Ollama with `llm_provider: \"ollama\"` in your config.\n\nAlternatively, copy `.env.example` to `.env` and fill in your keys:\n```bash\ncp .env.example .env\n```\n\n### CLI Usage\n\nLaunch the interactive CLI:\n```bash\ntradingagents # installed command\npython -m cli.main # alternative: run directly from source\n```\nYou will see a screen where you can select your desired tickers, analysis date, LLM provider, research depth, and more.\n\n\n \n
\n\nAn interface will appear showing results as they load, letting you track the agent's progress as it runs.\n\n\n \n
\n\n\n \n
\n\n## TradingAgents Package\n\n### Implementation Details\n\nWe built TradingAgents with LangGraph to ensure flexibility and modularity. The framework supports multiple LLM providers: OpenAI, Google, Anthropic, xAI, OpenRouter, and Ollama.\n\n### Python Usage\n\nTo use TradingAgents inside your code, you can import the `tradingagents` module and initialize a `TradingAgentsGraph()` object. The `.propagate()` function will return a decision. You can run `main.py`, here's also a quick example:\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2026-01-15\")\nprint(decision)\n```\n\nYou can also adjust the default configuration to set your own choice of LLMs, debate rounds, etc.\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"llm_provider\"] = \"openai\" # openai, google, anthropic, xai, openrouter, ollama\nconfig[\"deep_think_llm\"] = \"gpt-5.2\" # Model for complex reasoning\nconfig[\"quick_think_llm\"] = \"gpt-5-mini\" # Model for quick tasks\nconfig[\"max_debate_rounds\"] = 2\n\nta = TradingAgentsGraph(debug=True, config=config)\n_, decision = ta.propagate(\"NVDA\", \"2026-01-15\")\nprint(decision)\n```\n\nSee `tradingagents/default_config.py` for all configuration options.\n\n## Contributing\n\nWe welcome contributions from the community! Whether it's fixing a bug, improving documentation, or suggesting a new feature, your input helps make this project better. If you are interested in this line of research, please consider joining our open-source financial AI research community [Tauric Research](https://tauric.ai/).\n\n## Citation\n\nPlease reference our work if you find *TradingAgents* provides you with some help :)\n\n```\n@misc{xiao2025tradingagentsmultiagentsllmfinancial,\n title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, \n author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang},\n year={2025},\n eprint={2412.20138},\n archivePrefix={arXiv},\n primaryClass={q-fin.TR},\n url={https://arxiv.org/abs/2412.20138}, \n}\n```\n"}, "77755f0431b284690ddc835ee66684dab25fbb33": {"t": 1785766197.41289, "n": 10512, "h": "898bafd4ee2b6e8f", "c": "\n \n
\n\n\n\n\n\n---\n\n# TradingAgents: Multi-Agents LLM Financial Trading Framework\n\n## News\n- [2026-03] **TradingAgents v0.2.1** released with GPT-5.4, Gemini 3.1, Claude 4.6 model coverage and improved system stability.\n- [2026-02] **TradingAgents v0.2.0** released with multi-provider LLM support (GPT-5.x, Gemini 3.x, Claude 4.x, Grok 4.x) and improved system architecture.\n- [2026-01] **Trading-R1** [Technical Report](https://arxiv.org/abs/2509.11420) released, with [Terminal](https://github.com/TauricResearch/Trading-R1) expected to land soon.\n\n\n\n> 🎉 **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.\n>\n> So we decided to fully open-source the framework. Looking forward to building impactful projects with you!\n\n\n\n🚀 [TradingAgents](#tradingagents-framework) | ⚡ [Installation & CLI](#installation-and-cli) | 🎬 [Demo](https://www.youtube.com/watch?v=90gr5lwjIho) | 📦 [Package Usage](#tradingagents-package) | 🤝 [Contributing](#contributing) | 📄 [Citation](#citation)\n\n
\n\n## TradingAgents Framework\n\nTradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively evaluates market conditions and informs trading decisions. Moreover, these agents engage in dynamic discussions to pinpoint the optimal strategy.\n\n\n \n
\n\n> TradingAgents framework is designed for research purposes. Trading performance may vary based on many factors, including the chosen backbone language models, model temperature, trading periods, the quality of data, and other non-deterministic factors. [It is not intended as financial, investment, or trading advice.](https://tauric.ai/disclaimer/)\n\nOur framework decomposes complex trading tasks into specialized roles. This ensures the system achieves a robust, scalable approach to market analysis and decision-making.\n\n### Analyst Team\n- Fundamentals Analyst: Evaluates company financials and performance metrics, identifying intrinsic values and potential red flags.\n- Sentiment Analyst: Analyzes social media and public sentiment using sentiment scoring algorithms to gauge short-term market mood.\n- News Analyst: Monitors global news and macroeconomic indicators, interpreting the impact of events on market conditions.\n- Technical Analyst: Utilizes technical indicators (like MACD and RSI) to detect trading patterns and forecast price movements.\n\n\n \n
\n\n### Researcher Team\n- Comprises both bullish and bearish researchers who critically assess the insights provided by the Analyst Team. Through structured debates, they balance potential gains against inherent risks.\n\n\n \n
\n\n### Trader Agent\n- Composes reports from the analysts and researchers to make informed trading decisions. It determines the timing and magnitude of trades based on comprehensive market insights.\n\n\n \n
\n\n### Risk Management and Portfolio Manager\n- Continuously evaluates portfolio risk by assessing market volatility, liquidity, and other risk factors. The risk management team evaluates and adjusts trading strategies, providing assessment reports to the Portfolio Manager for final decision.\n- The Portfolio Manager approves/rejects the transaction proposal. If approved, the order will be sent to the simulated exchange and executed.\n\n\n \n
\n\n## Installation and CLI\n\n### Installation\n\nClone TradingAgents:\n```bash\ngit clone https://github.com/TauricResearch/TradingAgents.git\ncd TradingAgents\n```\n\nCreate a virtual environment in any of your favorite environment managers:\n```bash\nconda create -n tradingagents python=3.13\nconda activate tradingagents\n```\n\nInstall the package and its dependencies:\n```bash\npip install .\n```\n\n### Required APIs\n\nTradingAgents supports multiple LLM providers. Set the API key for your chosen provider:\n\n```bash\nexport OPENAI_API_KEY=... # OpenAI (GPT)\nexport GOOGLE_API_KEY=... # Google (Gemini)\nexport ANTHROPIC_API_KEY=... # Anthropic (Claude)\nexport XAI_API_KEY=... # xAI (Grok)\nexport OPENROUTER_API_KEY=... # OpenRouter\nexport ALPHA_VANTAGE_API_KEY=... # Alpha Vantage\n```\n\nFor local models, configure Ollama with `llm_provider: \"ollama\"` in your config.\n\nAlternatively, copy `.env.example` to `.env` and fill in your keys:\n```bash\ncp .env.example .env\n```\n\n### CLI Usage\n\nLaunch the interactive CLI:\n```bash\ntradingagents # installed command\npython -m cli.main # alternative: run directly from source\n```\nYou will see a screen where you can select your desired tickers, analysis date, LLM provider, research depth, and more.\n\n\n \n
\n\nAn interface will appear showing results as they load, letting you track the agent's progress as it runs.\n\n\n \n
\n\n\n \n
\n\n## TradingAgents Package\n\n### Implementation Details\n\nWe built TradingAgents with LangGraph to ensure flexibility and modularity. The framework supports multiple LLM providers: OpenAI, Google, Anthropic, xAI, OpenRouter, and Ollama.\n\n### Python Usage\n\nTo use TradingAgents inside your code, you can import the `tradingagents` module and initialize a `TradingAgentsGraph()` object. The `.propagate()` function will return a decision. You can run `main.py`, here's also a quick example:\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2026-01-15\")\nprint(decision)\n```\n\nYou can also adjust the default configuration to set your own choice of LLMs, debate rounds, etc.\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"llm_provider\"] = \"openai\" # openai, google, anthropic, xai, openrouter, ollama\nconfig[\"deep_think_llm\"] = \"gpt-5.2\" # Model for complex reasoning\nconfig[\"quick_think_llm\"] = \"gpt-5-mini\" # Model for quick tasks\nconfig[\"max_debate_rounds\"] = 2\n\nta = TradingAgentsGraph(debug=True, config=config)\n_, decision = ta.propagate(\"NVDA\", \"2026-01-15\")\nprint(decision)\n```\n\nSee `tradingagents/default_config.py` for all configuration options.\n\n## Contributing\n\nWe welcome contributions from the community! Whether it's fixing a bug, improving documentation, or suggesting a new feature, your input helps make this project better. If you are interested in this line of research, please consider joining our open-source financial AI research community [Tauric Research](https://tauric.ai/).\n\n## Citation\n\nPlease reference our work if you find *TradingAgents* provides you with some help :)\n\n```\n@misc{xiao2025tradingagentsmultiagentsllmfinancial,\n title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, \n author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang},\n year={2025},\n eprint={2412.20138},\n archivePrefix={arXiv},\n primaryClass={q-fin.TR},\n url={https://arxiv.org/abs/2412.20138}, \n}\n```\n"}, "b19c5c18fb24b4b7a78310f905f619a856cdf2f3": {"t": 1785766198.9050696, "n": 10423, "h": "dce1c29f477dc0b7", "c": "\n \n
\n\n\n\n\n\n---\n\n# TradingAgents: Multi-Agents LLM Financial Trading Framework\n\n## News\n- [2026-03] **TradingAgents v0.2.1** released with GPT-5.4, Gemini 3.1, Claude 4.6 model coverage and improved system stability.\n- [2026-02] **TradingAgents v0.2.0** released with multi-provider LLM support (GPT-5.x, Gemini 3.x, Claude 4.x, Grok 4.x) and improved system architecture.\n- [2026-01] **Trading-R1** [Technical Report](https://arxiv.org/abs/2509.11420) released, with [Terminal](https://github.com/TauricResearch/Trading-R1) expected to land soon.\n\n\n\n> 🎉 **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.\n>\n> So we decided to fully open-source the framework. Looking forward to building impactful projects with you!\n\n\n\n🚀 [TradingAgents](#tradingagents-framework) | ⚡ [Installation & CLI](#installation-and-cli) | 🎬 [Demo](https://www.youtube.com/watch?v=90gr5lwjIho) | 📦 [Package Usage](#tradingagents-package) | 🤝 [Contributing](#contributing) | 📄 [Citation](#citation)\n\n
\n\n## TradingAgents Framework\n\nTradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively evaluates market conditions and informs trading decisions. Moreover, these agents engage in dynamic discussions to pinpoint the optimal strategy.\n\n\n \n
\n\n> TradingAgents framework is designed for research purposes. Trading performance may vary based on many factors, including the chosen backbone language models, model temperature, trading periods, the quality of data, and other non-deterministic factors. [It is not intended as financial, investment, or trading advice.](https://tauric.ai/disclaimer/)\n\nOur framework decomposes complex trading tasks into specialized roles. This ensures the system achieves a robust, scalable approach to market analysis and decision-making.\n\n### Analyst Team\n- Fundamentals Analyst: Evaluates company financials and performance metrics, identifying intrinsic values and potential red flags.\n- Sentiment Analyst: Analyzes social media and public sentiment using sentiment scoring algorithms to gauge short-term market mood.\n- News Analyst: Monitors global news and macroeconomic indicators, interpreting the impact of events on market conditions.\n- Technical Analyst: Utilizes technical indicators (like MACD and RSI) to detect trading patterns and forecast price movements.\n\n\n \n
\n\n### Researcher Team\n- Comprises both bullish and bearish researchers who critically assess the insights provided by the Analyst Team. Through structured debates, they balance potential gains against inherent risks.\n\n\n \n
\n\n### Trader Agent\n- Composes reports from the analysts and researchers to make informed trading decisions. It determines the timing and magnitude of trades based on comprehensive market insights.\n\n\n \n
\n\n### Risk Management and Portfolio Manager\n- Continuously evaluates portfolio risk by assessing market volatility, liquidity, and other risk factors. The risk management team evaluates and adjusts trading strategies, providing assessment reports to the Portfolio Manager for final decision.\n- The Portfolio Manager approves/rejects the transaction proposal. If approved, the order will be sent to the simulated exchange and executed.\n\n\n \n
\n\n## Installation and CLI\n\n### Installation\n\nClone TradingAgents:\n```bash\ngit clone https://github.com/TauricResearch/TradingAgents.git\ncd TradingAgents\n```\n\nCreate a virtual environment in any of your favorite environment managers:\n```bash\nconda create -n tradingagents python=3.13\nconda activate tradingagents\n```\n\nInstall dependencies:\n```bash\npip install -r requirements.txt\n```\n\n### Required APIs\n\nTradingAgents supports multiple LLM providers. Set the API key for your chosen provider:\n\n```bash\nexport OPENAI_API_KEY=... # OpenAI (GPT)\nexport GOOGLE_API_KEY=... # Google (Gemini)\nexport ANTHROPIC_API_KEY=... # Anthropic (Claude)\nexport XAI_API_KEY=... # xAI (Grok)\nexport OPENROUTER_API_KEY=... # OpenRouter\nexport ALPHA_VANTAGE_API_KEY=... # Alpha Vantage\n```\n\nFor local models, configure Ollama with `llm_provider: \"ollama\"` in your config.\n\nAlternatively, copy `.env.example` to `.env` and fill in your keys:\n```bash\ncp .env.example .env\n```\n\n### CLI Usage\n\nYou can also try out the CLI directly by running:\n```bash\npython -m cli.main\n```\nYou will see a screen where you can select your desired tickers, date, LLMs, research depth, etc.\n\n\n \n
\n\nAn interface will appear showing results as they load, letting you track the agent's progress as it runs.\n\n\n \n
\n\n\n \n
\n\n## TradingAgents Package\n\n### Implementation Details\n\nWe built TradingAgents with LangGraph to ensure flexibility and modularity. The framework supports multiple LLM providers: OpenAI, Google, Anthropic, xAI, OpenRouter, and Ollama.\n\n### Python Usage\n\nTo use TradingAgents inside your code, you can import the `tradingagents` module and initialize a `TradingAgentsGraph()` object. The `.propagate()` function will return a decision. You can run `main.py`, here's also a quick example:\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2026-01-15\")\nprint(decision)\n```\n\nYou can also adjust the default configuration to set your own choice of LLMs, debate rounds, etc.\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"llm_provider\"] = \"openai\" # openai, google, anthropic, xai, openrouter, ollama\nconfig[\"deep_think_llm\"] = \"gpt-5.2\" # Model for complex reasoning\nconfig[\"quick_think_llm\"] = \"gpt-5-mini\" # Model for quick tasks\nconfig[\"max_debate_rounds\"] = 2\n\nta = TradingAgentsGraph(debug=True, config=config)\n_, decision = ta.propagate(\"NVDA\", \"2026-01-15\")\nprint(decision)\n```\n\nSee `tradingagents/default_config.py` for all configuration options.\n\n## Contributing\n\nWe welcome contributions from the community! Whether it's fixing a bug, improving documentation, or suggesting a new feature, your input helps make this project better. If you are interested in this line of research, please consider joining our open-source financial AI research community [Tauric Research](https://tauric.ai/).\n\n## Citation\n\nPlease reference our work if you find *TradingAgents* provides you with some help :)\n\n```\n@misc{xiao2025tradingagentsmultiagentsllmfinancial,\n title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, \n author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang},\n year={2025},\n eprint={2412.20138},\n archivePrefix={arXiv},\n primaryClass={q-fin.TR},\n url={https://arxiv.org/abs/2412.20138}, \n}\n```\n"}, "80aab35119f1ca08008fc3d4df6ddb074c532c8d": {"t": 1785766200.6190448, "n": 10294, "h": "37740f574d433c8e", "c": "\n \n
\n\n\n\n\n\n---\n\n# TradingAgents: Multi-Agents LLM Financial Trading Framework\n\n## News\n- [2026-02] **TradingAgents v0.2.0** released with multi-provider LLM support (GPT-5.x, Gemini 3.x, Claude 4.x, Grok 4.x) and improved system architecture.\n- [2026-01] **Trading-R1** [Technical Report](https://arxiv.org/abs/2509.11420) released, with [Terminal](https://github.com/TauricResearch/Trading-R1) expected to land soon.\n\n\n\n> 🎉 **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.\n>\n> So we decided to fully open-source the framework. Looking forward to building impactful projects with you!\n\n\n\n🚀 [TradingAgents](#tradingagents-framework) | ⚡ [Installation & CLI](#installation-and-cli) | 🎬 [Demo](https://www.youtube.com/watch?v=90gr5lwjIho) | 📦 [Package Usage](#tradingagents-package) | 🤝 [Contributing](#contributing) | 📄 [Citation](#citation)\n\n
\n\n## TradingAgents Framework\n\nTradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively evaluates market conditions and informs trading decisions. Moreover, these agents engage in dynamic discussions to pinpoint the optimal strategy.\n\n\n \n
\n\n> TradingAgents framework is designed for research purposes. Trading performance may vary based on many factors, including the chosen backbone language models, model temperature, trading periods, the quality of data, and other non-deterministic factors. [It is not intended as financial, investment, or trading advice.](https://tauric.ai/disclaimer/)\n\nOur framework decomposes complex trading tasks into specialized roles. This ensures the system achieves a robust, scalable approach to market analysis and decision-making.\n\n### Analyst Team\n- Fundamentals Analyst: Evaluates company financials and performance metrics, identifying intrinsic values and potential red flags.\n- Sentiment Analyst: Analyzes social media and public sentiment using sentiment scoring algorithms to gauge short-term market mood.\n- News Analyst: Monitors global news and macroeconomic indicators, interpreting the impact of events on market conditions.\n- Technical Analyst: Utilizes technical indicators (like MACD and RSI) to detect trading patterns and forecast price movements.\n\n\n \n
\n\n### Researcher Team\n- Comprises both bullish and bearish researchers who critically assess the insights provided by the Analyst Team. Through structured debates, they balance potential gains against inherent risks.\n\n\n \n
\n\n### Trader Agent\n- Composes reports from the analysts and researchers to make informed trading decisions. It determines the timing and magnitude of trades based on comprehensive market insights.\n\n\n \n
\n\n### Risk Management and Portfolio Manager\n- Continuously evaluates portfolio risk by assessing market volatility, liquidity, and other risk factors. The risk management team evaluates and adjusts trading strategies, providing assessment reports to the Portfolio Manager for final decision.\n- The Portfolio Manager approves/rejects the transaction proposal. If approved, the order will be sent to the simulated exchange and executed.\n\n\n \n
\n\n## Installation and CLI\n\n### Installation\n\nClone TradingAgents:\n```bash\ngit clone https://github.com/TauricResearch/TradingAgents.git\ncd TradingAgents\n```\n\nCreate a virtual environment in any of your favorite environment managers:\n```bash\nconda create -n tradingagents python=3.13\nconda activate tradingagents\n```\n\nInstall dependencies:\n```bash\npip install -r requirements.txt\n```\n\n### Required APIs\n\nTradingAgents supports multiple LLM providers. Set the API key for your chosen provider:\n\n```bash\nexport OPENAI_API_KEY=... # OpenAI (GPT)\nexport GOOGLE_API_KEY=... # Google (Gemini)\nexport ANTHROPIC_API_KEY=... # Anthropic (Claude)\nexport XAI_API_KEY=... # xAI (Grok)\nexport OPENROUTER_API_KEY=... # OpenRouter\nexport ALPHA_VANTAGE_API_KEY=... # Alpha Vantage\n```\n\nFor local models, configure Ollama with `llm_provider: \"ollama\"` in your config.\n\nAlternatively, copy `.env.example` to `.env` and fill in your keys:\n```bash\ncp .env.example .env\n```\n\n### CLI Usage\n\nYou can also try out the CLI directly by running:\n```bash\npython -m cli.main\n```\nYou will see a screen where you can select your desired tickers, date, LLMs, research depth, etc.\n\n\n \n
\n\nAn interface will appear showing results as they load, letting you track the agent's progress as it runs.\n\n\n \n
\n\n\n \n
\n\n## TradingAgents Package\n\n### Implementation Details\n\nWe built TradingAgents with LangGraph to ensure flexibility and modularity. The framework supports multiple LLM providers: OpenAI, Google, Anthropic, xAI, OpenRouter, and Ollama.\n\n### Python Usage\n\nTo use TradingAgents inside your code, you can import the `tradingagents` module and initialize a `TradingAgentsGraph()` object. The `.propagate()` function will return a decision. You can run `main.py`, here's also a quick example:\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2026-01-15\")\nprint(decision)\n```\n\nYou can also adjust the default configuration to set your own choice of LLMs, debate rounds, etc.\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"llm_provider\"] = \"openai\" # openai, google, anthropic, xai, openrouter, ollama\nconfig[\"deep_think_llm\"] = \"gpt-5.2\" # Model for complex reasoning\nconfig[\"quick_think_llm\"] = \"gpt-5-mini\" # Model for quick tasks\nconfig[\"max_debate_rounds\"] = 2\n\nta = TradingAgentsGraph(debug=True, config=config)\n_, decision = ta.propagate(\"NVDA\", \"2026-01-15\")\nprint(decision)\n```\n\nSee `tradingagents/default_config.py` for all configuration options.\n\n## Contributing\n\nWe welcome contributions from the community! Whether it's fixing a bug, improving documentation, or suggesting a new feature, your input helps make this project better. If you are interested in this line of research, please consider joining our open-source financial AI research community [Tauric Research](https://tauric.ai/).\n\n## Citation\n\nPlease reference our work if you find *TradingAgents* provides you with some help :)\n\n```\n@misc{xiao2025tradingagentsmultiagentsllmfinancial,\n title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, \n author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang},\n year={2025},\n eprint={2412.20138},\n archivePrefix={arXiv},\n primaryClass={q-fin.TR},\n url={https://arxiv.org/abs/2412.20138}, \n}\n```\n"}, "102b026d23991e522fd5ab7c172293a2466c82d3": {"t": 1785766202.086487, "n": 9891, "h": "bc169066de164b81", "c": "\n \n
\n\n\n\n\n\n---\n\n# TradingAgents: Multi-Agents LLM Financial Trading Framework \n\n> 🎉 **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.\n>\n> So we decided to fully open-source the framework. Looking forward to building impactful projects with you!\n\n\n\n\n\n🚀 [TradingAgents](#tradingagents-framework) | ⚡ [Installation & CLI](#installation-and-cli) | 🎬 [Demo](https://www.youtube.com/watch?v=90gr5lwjIho) | 📦 [Package Usage](#tradingagents-package) | 🤝 [Contributing](#contributing) | 📄 [Citation](#citation)\n\n
\n\n## TradingAgents Framework\n\nTradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively evaluates market conditions and informs trading decisions. Moreover, these agents engage in dynamic discussions to pinpoint the optimal strategy.\n\n\n \n
\n\n> TradingAgents framework is designed for research purposes. Trading performance may vary based on many factors, including the chosen backbone language models, model temperature, trading periods, the quality of data, and other non-deterministic factors. [It is not intended as financial, investment, or trading advice.](https://tauric.ai/disclaimer/)\n\nOur framework decomposes complex trading tasks into specialized roles. This ensures the system achieves a robust, scalable approach to market analysis and decision-making.\n\n### Analyst Team\n- Fundamentals Analyst: Evaluates company financials and performance metrics, identifying intrinsic values and potential red flags.\n- Sentiment Analyst: Analyzes social media and public sentiment using sentiment scoring algorithms to gauge short-term market mood.\n- News Analyst: Monitors global news and macroeconomic indicators, interpreting the impact of events on market conditions.\n- Technical Analyst: Utilizes technical indicators (like MACD and RSI) to detect trading patterns and forecast price movements.\n\n\n \n
\n\n### Researcher Team\n- Comprises both bullish and bearish researchers who critically assess the insights provided by the Analyst Team. Through structured debates, they balance potential gains against inherent risks.\n\n\n \n
\n\n### Trader Agent\n- Composes reports from the analysts and researchers to make informed trading decisions. It determines the timing and magnitude of trades based on comprehensive market insights.\n\n\n \n
\n\n### Risk Management and Portfolio Manager\n- Continuously evaluates portfolio risk by assessing market volatility, liquidity, and other risk factors. The risk management team evaluates and adjusts trading strategies, providing assessment reports to the Portfolio Manager for final decision.\n- The Portfolio Manager approves/rejects the transaction proposal. If approved, the order will be sent to the simulated exchange and executed.\n\n\n \n
\n\n## Installation and CLI\n\n### Installation\n\nClone TradingAgents:\n```bash\ngit clone https://github.com/TauricResearch/TradingAgents.git\ncd TradingAgents\n```\n\nCreate a virtual environment in any of your favorite environment managers:\n```bash\nconda create -n tradingagents python=3.13\nconda activate tradingagents\n```\n\nInstall dependencies:\n```bash\npip install -r requirements.txt\n```\n\n### Required APIs\n\nTradingAgents supports multiple LLM providers. Set the API key for your chosen provider:\n\n```bash\nexport OPENAI_API_KEY=... # OpenAI\nexport GOOGLE_API_KEY=... # Google (Gemini)\nexport ANTHROPIC_API_KEY=... # Anthropic (Claude)\nexport OPENROUTER_API_KEY=... # OpenRouter\nexport ALPHA_VANTAGE_API_KEY=... # Alpha Vantage\n```\n\nFor local models, configure Ollama with `llm_provider: \"ollama\"` in your config.\n\nAlternatively, copy `.env.example` to `.env` and fill in your keys:\n```bash\ncp .env.example .env\n```\n\n### CLI Usage\n\nYou can also try out the CLI directly by running:\n```bash\npython -m cli.main\n```\nYou will see a screen where you can select your desired tickers, date, LLMs, research depth, etc.\n\n\n \n
\n\nAn interface will appear showing results as they load, letting you track the agent's progress as it runs.\n\n\n \n
\n\n\n \n
\n\n## TradingAgents Package\n\n### Implementation Details\n\nWe built TradingAgents with LangGraph to ensure flexibility and modularity. The framework supports multiple LLM providers: OpenAI, Google, Anthropic, OpenRouter, and Ollama.\n\n### Python Usage\n\nTo use TradingAgents inside your code, you can import the `tradingagents` module and initialize a `TradingAgentsGraph()` object. The `.propagate()` function will return a decision. You can run `main.py`, here's also a quick example:\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2026-01-15\")\nprint(decision)\n```\n\nYou can also adjust the default configuration to set your own choice of LLMs, debate rounds, etc.\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"llm_provider\"] = \"openai\" # openai, google, anthropic, openrouter, ollama\nconfig[\"deep_think_llm\"] = \"gpt-5.2\" # Model for complex reasoning\nconfig[\"quick_think_llm\"] = \"gpt-5-mini\" # Model for quick tasks\nconfig[\"max_debate_rounds\"] = 2\n\nta = TradingAgentsGraph(debug=True, config=config)\n_, decision = ta.propagate(\"NVDA\", \"2026-01-15\")\nprint(decision)\n```\n\nSee `tradingagents/default_config.py` for all configuration options.\n\n## Contributing\n\nWe welcome contributions from the community! Whether it's fixing a bug, improving documentation, or suggesting a new feature, your input helps make this project better. If you are interested in this line of research, please consider joining our open-source financial AI research community [Tauric Research](https://tauric.ai/).\n\n## Citation\n\nPlease reference our work if you find *TradingAgents* provides you with some help :)\n\n```\n@misc{xiao2025tradingagentsmultiagentsllmfinancial,\n title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, \n author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang},\n year={2025},\n eprint={2412.20138},\n archivePrefix={arXiv},\n primaryClass={q-fin.TR},\n url={https://arxiv.org/abs/2412.20138}, \n}\n```\n"}, "b2ef960da7b82152b043a99e9de25277eb3a5b0e": {"t": 1785766203.376364, "n": 11624, "h": "1db80e77bab6a808", "c": "\n \n
\n\n\n\n\n\n---\n\n# TradingAgents: Multi-Agents LLM Financial Trading Framework \n\n> 🎉 **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.\n>\n> So we decided to fully open-source the framework. Looking forward to building impactful projects with you!\n\n\n\n\n\n🚀 [TradingAgents](#tradingagents-framework) | ⚡ [Installation & CLI](#installation-and-cli) | 🎬 [Demo](https://www.youtube.com/watch?v=90gr5lwjIho) | 📦 [Package Usage](#tradingagents-package) | 🤝 [Contributing](#contributing) | 📄 [Citation](#citation)\n\n
\n\n## TradingAgents Framework\n\nTradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively evaluates market conditions and informs trading decisions. Moreover, these agents engage in dynamic discussions to pinpoint the optimal strategy.\n\n\n \n
\n\n> TradingAgents framework is designed for research purposes. Trading performance may vary based on many factors, including the chosen backbone language models, model temperature, trading periods, the quality of data, and other non-deterministic factors. [It is not intended as financial, investment, or trading advice.](https://tauric.ai/disclaimer/)\n\nOur framework decomposes complex trading tasks into specialized roles. This ensures the system achieves a robust, scalable approach to market analysis and decision-making.\n\n### Analyst Team\n- Fundamentals Analyst: Evaluates company financials and performance metrics, identifying intrinsic values and potential red flags.\n- Sentiment Analyst: Analyzes social media and public sentiment using sentiment scoring algorithms to gauge short-term market mood.\n- News Analyst: Monitors global news and macroeconomic indicators, interpreting the impact of events on market conditions.\n- Technical Analyst: Utilizes technical indicators (like MACD and RSI) to detect trading patterns and forecast price movements.\n\n\n \n
\n\n### Researcher Team\n- Comprises both bullish and bearish researchers who critically assess the insights provided by the Analyst Team. Through structured debates, they balance potential gains against inherent risks.\n\n\n \n
\n\n### Trader Agent\n- Composes reports from the analysts and researchers to make informed trading decisions. It determines the timing and magnitude of trades based on comprehensive market insights.\n\n\n \n
\n\n### Risk Management and Portfolio Manager\n- Continuously evaluates portfolio risk by assessing market volatility, liquidity, and other risk factors. The risk management team evaluates and adjusts trading strategies, providing assessment reports to the Portfolio Manager for final decision.\n- The Portfolio Manager approves/rejects the transaction proposal. If approved, the order will be sent to the simulated exchange and executed.\n\n\n \n
\n\n## Installation and CLI\n\n### Installation\n\nClone TradingAgents:\n```bash\ngit clone https://github.com/TauricResearch/TradingAgents.git\ncd TradingAgents\n```\n\nCreate a virtual environment in any of your favorite environment managers:\n```bash\nconda create -n tradingagents python=3.13\nconda activate tradingagents\n```\n\nInstall dependencies:\n```bash\npip install -r requirements.txt\n```\n\n### Required APIs\n\nYou will need the OpenAI API for all the agents, and [Alpha Vantage API](https://www.alphavantage.co/support/#api-key) for fundamental and news data (default configuration).\n\n```bash\nexport OPENAI_API_KEY=$YOUR_OPENAI_API_KEY\nexport ALPHA_VANTAGE_API_KEY=$YOUR_ALPHA_VANTAGE_API_KEY\n```\n\nAlternatively, you can create a `.env` file in the project root with your API keys (see `.env.example` for reference):\n```bash\ncp .env.example .env\n# Edit .env with your actual API keys\n```\n\n**Note:** We are happy to partner with Alpha Vantage to provide robust API support for TradingAgents. You can get a free AlphaVantage API [here](https://www.alphavantage.co/support/#api-key), TradingAgents-sourced requests also have increased rate limits to 60 requests per minute with no daily limits. Typically the quota is sufficient for performing complex tasks with TradingAgents thanks to Alpha Vantage’s open-source support program. If you prefer to use OpenAI for these data sources instead, you can modify the data vendor settings in `tradingagents/default_config.py`.\n\n### CLI Usage\n\nYou can also try out the CLI directly by running:\n```bash\npython -m cli.main\n```\nYou will see a screen where you can select your desired tickers, date, LLMs, research depth, etc.\n\n\n \n
\n\nAn interface will appear showing results as they load, letting you track the agent's progress as it runs.\n\n\n \n
\n\n\n \n
\n\n## TradingAgents Package\n\n### Implementation Details\n\nWe built TradingAgents with LangGraph to ensure flexibility and modularity. We utilize `o1-preview` and `gpt-4o` as our deep thinking and fast thinking LLMs for our experiments. However, for testing purposes, we recommend you use `o4-mini` and `gpt-4.1-mini` to save on costs as our framework makes **lots of** API calls.\n\n### Python Usage\n\nTo use TradingAgents inside your code, you can import the `tradingagents` module and initialize a `TradingAgentsGraph()` object. The `.propagate()` function will return a decision. You can run `main.py`, here's also a quick example:\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\nYou can also adjust the default configuration to set your own choice of LLMs, debate rounds, etc.\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\n# Create a custom config\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"deep_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"quick_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"max_debate_rounds\"] = 1 # Increase debate rounds\n\n# Configure data vendors (default uses yfinance and Alpha Vantage)\nconfig[\"data_vendors\"] = {\n \"core_stock_apis\": \"yfinance\", # Options: yfinance, alpha_vantage, local\n \"technical_indicators\": \"yfinance\", # Options: yfinance, alpha_vantage, local\n \"fundamental_data\": \"alpha_vantage\", # Options: openai, alpha_vantage, local\n \"news_data\": \"alpha_vantage\", # Options: openai, alpha_vantage, google, local\n}\n\n# Initialize with custom config\nta = TradingAgentsGraph(debug=True, config=config)\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\n> The default configuration uses yfinance for stock price and technical data, and Alpha Vantage for fundamental and news data. For production use or if you encounter rate limits, consider upgrading to [Alpha Vantage Premium](https://www.alphavantage.co/premium/) for more stable and reliable data access. For offline experimentation, there's a local data vendor option that uses our **Tauric TradingDB**, a curated dataset for backtesting, though this is still in development. We're currently refining this dataset and plan to release it soon alongside our upcoming projects. Stay tuned!\n\nYou can view the full list of configurations in `tradingagents/default_config.py`.\n\n## Contributing\n\nWe welcome contributions from the community! Whether it's fixing a bug, improving documentation, or suggesting a new feature, your input helps make this project better. If you are interested in this line of research, please consider joining our open-source financial AI research community [Tauric Research](https://tauric.ai/).\n\n## Citation\n\nPlease reference our work if you find *TradingAgents* provides you with some help :)\n\n```\n@misc{xiao2025tradingagentsmultiagentsllmfinancial,\n title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, \n author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang},\n year={2025},\n eprint={2412.20138},\n archivePrefix={arXiv},\n primaryClass={q-fin.TR},\n url={https://arxiv.org/abs/2412.20138}, \n}\n```\n"}, "a5dcc7da452e2840fedea4a4beede3175c8ccd62": {"t": 1785766205.135366, "n": 11513, "h": "3003636a0f4c3728", "c": "\n \n
\n\n\n\n\n\n---\n\n# TradingAgents: Multi-Agents LLM Financial Trading Framework \n\n> 🎉 **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.\n>\n> So we decided to fully open-source the framework. Looking forward to building impactful projects with you!\n\n\n\n\n\n🚀 [TradingAgents](#tradingagents-framework) | ⚡ [Installation & CLI](#installation-and-cli) | 🎬 [Demo](https://www.youtube.com/watch?v=90gr5lwjIho) | 📦 [Package Usage](#tradingagents-package) | 🤝 [Contributing](#contributing) | 📄 [Citation](#citation)\n\n
\n\n## TradingAgents Framework\n\nTradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively evaluates market conditions and informs trading decisions. Moreover, these agents engage in dynamic discussions to pinpoint the optimal strategy.\n\n\n \n
\n\n> TradingAgents framework is designed for research purposes. Trading performance may vary based on many factors, including the chosen backbone language models, model temperature, trading periods, the quality of data, and other non-deterministic factors. [It is not intended as financial, investment, or trading advice.](https://tauric.ai/disclaimer/)\n\nOur framework decomposes complex trading tasks into specialized roles. This ensures the system achieves a robust, scalable approach to market analysis and decision-making.\n\n### Analyst Team\n- Fundamentals Analyst: Evaluates company financials and performance metrics, identifying intrinsic values and potential red flags.\n- Sentiment Analyst: Analyzes social media and public sentiment using sentiment scoring algorithms to gauge short-term market mood.\n- News Analyst: Monitors global news and macroeconomic indicators, interpreting the impact of events on market conditions.\n- Technical Analyst: Utilizes technical indicators (like MACD and RSI) to detect trading patterns and forecast price movements.\n\n\n \n
\n\n### Researcher Team\n- Comprises both bullish and bearish researchers who critically assess the insights provided by the Analyst Team. Through structured debates, they balance potential gains against inherent risks.\n\n\n \n
\n\n### Trader Agent\n- Composes reports from the analysts and researchers to make informed trading decisions. It determines the timing and magnitude of trades based on comprehensive market insights.\n\n\n \n
\n\n### Risk Management and Portfolio Manager\n- Continuously evaluates portfolio risk by assessing market volatility, liquidity, and other risk factors. The risk management team evaluates and adjusts trading strategies, providing assessment reports to the Portfolio Manager for final decision.\n- The Portfolio Manager approves/rejects the transaction proposal. If approved, the order will be sent to the simulated exchange and executed.\n\n\n \n
\n\n## Installation and CLI\n\n### Installation\n\nClone TradingAgents:\n```bash\ngit clone https://github.com/TauricResearch/TradingAgents.git\ncd TradingAgents\n```\n\nCreate a virtual environment in any of your favorite environment managers:\n```bash\nconda create -n tradingagents python=3.13\nconda activate tradingagents\n```\n\nInstall dependencies:\n```bash\npip install -r requirements.txt\n```\n\n### Required APIs\n\nYou will need the OpenAI API for all the agents, and [Alpha Vantage API](https://www.alphavantage.co/support/#api-key) for fundamental and news data (default configuration).\n\n```bash\nexport OPENAI_API_KEY=$YOUR_OPENAI_API_KEY\nexport ALPHA_VANTAGE_API_KEY=$YOUR_ALPHA_VANTAGE_API_KEY\n```\n\nAlternatively, you can create a `.env` file in the project root with your API keys (see `.env.example` for reference):\n```bash\ncp .env.example .env\n# Edit .env with your actual API keys\n```\n\n**Note:** We are happy to partner with Alpha Vantage to provide robust API support for TradingAgents. You can get a free AlphaVantage API [here](https://www.alphavantage.co/support/#api-key). Typically the quota is sufficient for performing complex tasks with TradingAgents thanks to Alpha Vantage’s open-source support program. If you prefer to use OpenAI for these data sources instead, you can modify the data vendor settings in `tradingagents/default_config.py`.\n\n### CLI Usage\n\nYou can also try out the CLI directly by running:\n```bash\npython -m cli.main\n```\nYou will see a screen where you can select your desired tickers, date, LLMs, research depth, etc.\n\n\n \n
\n\nAn interface will appear showing results as they load, letting you track the agent's progress as it runs.\n\n\n \n
\n\n\n \n
\n\n## TradingAgents Package\n\n### Implementation Details\n\nWe built TradingAgents with LangGraph to ensure flexibility and modularity. We utilize `o1-preview` and `gpt-4o` as our deep thinking and fast thinking LLMs for our experiments. However, for testing purposes, we recommend you use `o4-mini` and `gpt-4.1-mini` to save on costs as our framework makes **lots of** API calls.\n\n### Python Usage\n\nTo use TradingAgents inside your code, you can import the `tradingagents` module and initialize a `TradingAgentsGraph()` object. The `.propagate()` function will return a decision. You can run `main.py`, here's also a quick example:\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\nYou can also adjust the default configuration to set your own choice of LLMs, debate rounds, etc.\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\n# Create a custom config\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"deep_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"quick_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"max_debate_rounds\"] = 1 # Increase debate rounds\n\n# Configure data vendors (default uses yfinance and Alpha Vantage)\nconfig[\"data_vendors\"] = {\n \"core_stock_apis\": \"yfinance\", # Options: yfinance, alpha_vantage, local\n \"technical_indicators\": \"yfinance\", # Options: yfinance, alpha_vantage, local\n \"fundamental_data\": \"alpha_vantage\", # Options: openai, alpha_vantage, local\n \"news_data\": \"alpha_vantage\", # Options: openai, alpha_vantage, google, local\n}\n\n# Initialize with custom config\nta = TradingAgentsGraph(debug=True, config=config)\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\n> The default configuration uses yfinance for stock price and technical data, and Alpha Vantage for fundamental and news data. For production use or if you encounter rate limits, consider upgrading to [Alpha Vantage Premium](https://www.alphavantage.co/premium/) for more stable and reliable data access. For offline experimentation, there's a local data vendor option that uses our **Tauric TradingDB**, a curated dataset for backtesting, though this is still in development. We're currently refining this dataset and plan to release it soon alongside our upcoming projects. Stay tuned!\n\nYou can view the full list of configurations in `tradingagents/default_config.py`.\n\n## Contributing\n\nWe welcome contributions from the community! Whether it's fixing a bug, improving documentation, or suggesting a new feature, your input helps make this project better. If you are interested in this line of research, please consider joining our open-source financial AI research community [Tauric Research](https://tauric.ai/).\n\n## Citation\n\nPlease reference our work if you find *TradingAgents* provides you with some help :)\n\n```\n@misc{xiao2025tradingagentsmultiagentsllmfinancial,\n title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, \n author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang},\n year={2025},\n eprint={2412.20138},\n archivePrefix={arXiv},\n primaryClass={q-fin.TR},\n url={https://arxiv.org/abs/2412.20138}, \n}\n```\n"}, "b01051b9f478fb054f4c6e93598322df74bd8a46": {"t": 1785766206.4083114, "n": 11472, "h": "746922091dcdb919", "c": "\n \n
\n\n\n\n\n\n---\n\n# TradingAgents: Multi-Agents LLM Financial Trading Framework \n\n> 🎉 **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.\n>\n> So we decided to fully open-source the framework. Looking forward to building impactful projects with you!\n\n\n\n\n\n🚀 [TradingAgents](#tradingagents-framework) | ⚡ [Installation & CLI](#installation-and-cli) | 🎬 [Demo](https://www.youtube.com/watch?v=90gr5lwjIho) | 📦 [Package Usage](#tradingagents-package) | 🤝 [Contributing](#contributing) | 📄 [Citation](#citation)\n\n
\n\n## TradingAgents Framework\n\nTradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively evaluates market conditions and informs trading decisions. Moreover, these agents engage in dynamic discussions to pinpoint the optimal strategy.\n\n\n \n
\n\n> TradingAgents framework is designed for research purposes. Trading performance may vary based on many factors, including the chosen backbone language models, model temperature, trading periods, the quality of data, and other non-deterministic factors. [It is not intended as financial, investment, or trading advice.](https://tauric.ai/disclaimer/)\n\nOur framework decomposes complex trading tasks into specialized roles. This ensures the system achieves a robust, scalable approach to market analysis and decision-making.\n\n### Analyst Team\n- Fundamentals Analyst: Evaluates company financials and performance metrics, identifying intrinsic values and potential red flags.\n- Sentiment Analyst: Analyzes social media and public sentiment using sentiment scoring algorithms to gauge short-term market mood.\n- News Analyst: Monitors global news and macroeconomic indicators, interpreting the impact of events on market conditions.\n- Technical Analyst: Utilizes technical indicators (like MACD and RSI) to detect trading patterns and forecast price movements.\n\n\n \n
\n\n### Researcher Team\n- Comprises both bullish and bearish researchers who critically assess the insights provided by the Analyst Team. Through structured debates, they balance potential gains against inherent risks.\n\n\n \n
\n\n### Trader Agent\n- Composes reports from the analysts and researchers to make informed trading decisions. It determines the timing and magnitude of trades based on comprehensive market insights.\n\n\n \n
\n\n### Risk Management and Portfolio Manager\n- Continuously evaluates portfolio risk by assessing market volatility, liquidity, and other risk factors. The risk management team evaluates and adjusts trading strategies, providing assessment reports to the Portfolio Manager for final decision.\n- The Portfolio Manager approves/rejects the transaction proposal. If approved, the order will be sent to the simulated exchange and executed.\n\n\n \n
\n\n## Installation and CLI\n\n### Installation\n\nClone TradingAgents:\n```bash\ngit clone https://github.com/TauricResearch/TradingAgents.git\ncd TradingAgents\n```\n\nCreate a virtual environment in any of your favorite environment managers:\n```bash\nconda create -n tradingagents python=3.13\nconda activate tradingagents\n```\n\nInstall dependencies:\n```bash\npip install -r requirements.txt\n```\n\n### Required APIs\n\nYou will need the OpenAI API for all the agents, and [Alpha Vantage API](https://www.alphavantage.co/support/#api-key) for fundamental and news data (default configuration).\n\n```bash\nexport OPENAI_API_KEY=$YOUR_OPENAI_API_KEY\nexport ALPHA_VANTAGE_API_KEY=$YOUR_ALPHA_VANTAGE_API_KEY\n```\n\nAlternatively, you can create a `.env` file in the project root with your API keys (see `.env.example` for reference):\n```bash\ncp .env.example .env\n# Edit .env with your actual API keys\n```\n\n**Note:** The default configuration uses [Alpha Vantage](https://www.alphavantage.co/) for fundamental and news data. You can get a free API key from their website, or upgrade to [Alpha Vantage Premium](https://www.alphavantage.co/premium/) for higher rate limits and more stable access. If you prefer to use OpenAI for these data sources instead, you can modify the data vendor settings in `tradingagents/default_config.py`.\n\n### CLI Usage\n\nYou can also try out the CLI directly by running:\n```bash\npython -m cli.main\n```\nYou will see a screen where you can select your desired tickers, date, LLMs, research depth, etc.\n\n\n \n
\n\nAn interface will appear showing results as they load, letting you track the agent's progress as it runs.\n\n\n \n
\n\n\n \n
\n\n## TradingAgents Package\n\n### Implementation Details\n\nWe built TradingAgents with LangGraph to ensure flexibility and modularity. We utilize `o1-preview` and `gpt-4o` as our deep thinking and fast thinking LLMs for our experiments. However, for testing purposes, we recommend you use `o4-mini` and `gpt-4.1-mini` to save on costs as our framework makes **lots of** API calls.\n\n### Python Usage\n\nTo use TradingAgents inside your code, you can import the `tradingagents` module and initialize a `TradingAgentsGraph()` object. The `.propagate()` function will return a decision. You can run `main.py`, here's also a quick example:\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\nYou can also adjust the default configuration to set your own choice of LLMs, debate rounds, etc.\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\n# Create a custom config\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"deep_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"quick_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"max_debate_rounds\"] = 1 # Increase debate rounds\n\n# Configure data vendors (default uses yfinance and Alpha Vantage)\nconfig[\"data_vendors\"] = {\n \"core_stock_apis\": \"yfinance\", # Options: yfinance, alpha_vantage, local\n \"technical_indicators\": \"yfinance\", # Options: yfinance, alpha_vantage, local\n \"fundamental_data\": \"alpha_vantage\", # Options: openai, alpha_vantage, local\n \"news_data\": \"alpha_vantage\", # Options: openai, alpha_vantage, google, local\n}\n\n# Initialize with custom config\nta = TradingAgentsGraph(debug=True, config=config)\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\n> The default configuration uses yfinance for stock price and technical data, and Alpha Vantage for fundamental and news data. For production use or if you encounter rate limits, consider upgrading to [Alpha Vantage Premium](https://www.alphavantage.co/premium/) for more stable and reliable data access. For offline experimentation, there's a local data vendor option that uses our **Tauric TradingDB**, a curated dataset for backtesting, though this is still in development. We're currently refining this dataset and plan to release it soon alongside our upcoming projects. Stay tuned!\n\nYou can view the full list of configurations in `tradingagents/default_config.py`.\n\n## Contributing\n\nWe welcome contributions from the community! Whether it's fixing a bug, improving documentation, or suggesting a new feature, your input helps make this project better. If you are interested in this line of research, please consider joining our open-source financial AI research community [Tauric Research](https://tauric.ai/).\n\n## Citation\n\nPlease reference our work if you find *TradingAgents* provides you with some help :)\n\n```\n@misc{xiao2025tradingagentsmultiagentsllmfinancial,\n title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, \n author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang},\n year={2025},\n eprint={2412.20138},\n archivePrefix={arXiv},\n primaryClass={q-fin.TR},\n url={https://arxiv.org/abs/2412.20138}, \n}\n```\n"}, "8fdbbcca3d9aabc7315e6e7659567ac39af9b337": {"t": 1785766207.919066, "n": 10926, "h": "5a5fe02ee9e22b2f", "c": "\n \n
\n\n\n\n\n\n---\n\n# TradingAgents: Multi-Agents LLM Financial Trading Framework \n\n> 🎉 **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.\n>\n> So we decided to fully open-source the framework. Looking forward to building impactful projects with you!\n\n\n\n\n\n🚀 [TradingAgents](#tradingagents-framework) | ⚡ [Installation & CLI](#installation-and-cli) | 🎬 [Demo](https://www.youtube.com/watch?v=90gr5lwjIho) | 📦 [Package Usage](#tradingagents-package) | 🤝 [Contributing](#contributing) | 📄 [Citation](#citation)\n\n
\n\n## TradingAgents Framework\n\nTradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively evaluates market conditions and informs trading decisions. Moreover, these agents engage in dynamic discussions to pinpoint the optimal strategy.\n\n\n \n
\n\n> TradingAgents framework is designed for research purposes. Trading performance may vary based on many factors, including the chosen backbone language models, model temperature, trading periods, the quality of data, and other non-deterministic factors. [It is not intended as financial, investment, or trading advice.](https://tauric.ai/disclaimer/)\n\nOur framework decomposes complex trading tasks into specialized roles. This ensures the system achieves a robust, scalable approach to market analysis and decision-making.\n\n### Analyst Team\n- Fundamentals Analyst: Evaluates company financials and performance metrics, identifying intrinsic values and potential red flags.\n- Sentiment Analyst: Analyzes social media and public sentiment using sentiment scoring algorithms to gauge short-term market mood.\n- News Analyst: Monitors global news and macroeconomic indicators, interpreting the impact of events on market conditions.\n- Technical Analyst: Utilizes technical indicators (like MACD and RSI) to detect trading patterns and forecast price movements.\n\n\n \n
\n\n### Researcher Team\n- Comprises both bullish and bearish researchers who critically assess the insights provided by the Analyst Team. Through structured debates, they balance potential gains against inherent risks.\n\n\n \n
\n\n### Trader Agent\n- Composes reports from the analysts and researchers to make informed trading decisions. It determines the timing and magnitude of trades based on comprehensive market insights.\n\n\n \n
\n\n### Risk Management and Portfolio Manager\n- Continuously evaluates portfolio risk by assessing market volatility, liquidity, and other risk factors. The risk management team evaluates and adjusts trading strategies, providing assessment reports to the Portfolio Manager for final decision.\n- The Portfolio Manager approves/rejects the transaction proposal. If approved, the order will be sent to the simulated exchange and executed.\n\n\n \n
\n\n## Installation and CLI\n\n### Installation\n\nClone TradingAgents:\n```bash\ngit clone https://github.com/TauricResearch/TradingAgents.git\ncd TradingAgents\n```\n\nCreate a virtual environment in any of your favorite environment managers:\n```bash\nconda create -n tradingagents python=3.13\nconda activate tradingagents\n```\n\nInstall dependencies:\n```bash\npip install -r requirements.txt\n```\n\n### Required APIs\n\nYou will also need the [Alpha Vantage API](https://www.alphavantage.co/support/#api-key) for financial data. The free tier supports 25 API calls per day.\n```bash\nexport ALPHA_VANTAGE_API_KEY=$YOUR_ALPHA_VANTAGE_API_KEY\n```\n\nYou will need the OpenAI API for all the agents.\n```bash\nexport OPENAI_API_KEY=$YOUR_OPENAI_API_KEY\n```\n\nAlternatively, you can create a `.env` file in the project root with your API keys (see `.env.example` for reference):\n```bash\ncp .env.example .env\n# Edit .env with your actual API keys\n```\n\n### CLI Usage\n\nYou can also try out the CLI directly by running:\n```bash\npython -m cli.main\n```\nYou will see a screen where you can select your desired tickers, date, LLMs, research depth, etc.\n\n\n \n
\n\nAn interface will appear showing results as they load, letting you track the agent's progress as it runs.\n\n\n \n
\n\n\n \n
\n\n## TradingAgents Package\n\n### Implementation Details\n\nWe built TradingAgents with LangGraph to ensure flexibility and modularity. We utilize `o1-preview` and `gpt-4o` as our deep thinking and fast thinking LLMs for our experiments. However, for testing purposes, we recommend you use `o4-mini` and `gpt-4.1-mini` to save on costs as our framework makes **lots of** API calls.\n\n### Python Usage\n\nTo use TradingAgents inside your code, you can import the `tradingagents` module and initialize a `TradingAgentsGraph()` object. The `.propagate()` function will return a decision. You can run `main.py`, here's also a quick example:\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\nYou can also adjust the default configuration to set your own choice of LLMs, debate rounds, etc.\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\n# Create a custom config\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"deep_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"quick_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"max_debate_rounds\"] = 1 # Increase debate rounds\n\n# Configure data vendors (default uses Alpha Vantage for real-time data)\nconfig[\"data_vendors\"] = {\n \"core_stock_apis\": \"alpha_vantage\", # Options: alpha_vantage, yahoo_finance, local\n \"technical_indicators\": \"alpha_vantage\", # Options: alpha_vantage, yahoo_finance, local\n \"fundamental_data\": \"alpha_vantage\", # Options: alpha_vantage, openai, local\n \"news_data\": \"alpha_vantage\", # Options: alpha_vantage, openai, google, local\n}\n\n# Initialize with custom config\nta = TradingAgentsGraph(debug=True, config=config)\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\n> The default configuration now uses Alpha Vantage as the primary data provider, which provides access to real-time market data. For offline experimentation, there's a local data vendor option that uses our **Tauric TradingDB**, a curated dataset for backtesting, though this is still in development. We're currently refining this dataset and plan to release it soon alongside our upcoming projects. Stay tuned!\n\nYou can view the full list of configurations in `tradingagents/default_config.py`.\n\n## Contributing\n\nWe welcome contributions from the community! Whether it's fixing a bug, improving documentation, or suggesting a new feature, your input helps make this project better. If you are interested in this line of research, please consider joining our open-source financial AI research community [Tauric Research](https://tauric.ai/).\n\n## Citation\n\nPlease reference our work if you find *TradingAgents* provides you with some help :)\n\n```\n@misc{xiao2025tradingagentsmultiagentsllmfinancial,\n title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, \n author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang},\n year={2025},\n eprint={2412.20138},\n archivePrefix={arXiv},\n primaryClass={q-fin.TR},\n url={https://arxiv.org/abs/2412.20138}, \n}\n```\n"}, "7fc9c28a94d177851c205d4958be88014d16eba6": {"t": 1785766209.7257135, "n": 10878, "h": "c93ec767a2e64d6d", "c": "\n \n
\n\n\n\n\n\n---\n\n# TradingAgents: Multi-Agents LLM Financial Trading Framework \n\n> 🎉 **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.\n>\n> So we decided to fully open-source the framework. Looking forward to building impactful projects with you!\n\n\n\n\n\n🚀 [TradingAgents](#tradingagents-framework) | ⚡ [Installation & CLI](#installation-and-cli) | 🎬 [Demo](https://www.youtube.com/watch?v=90gr5lwjIho) | 📦 [Package Usage](#tradingagents-package) | 🤝 [Contributing](#contributing) | 📄 [Citation](#citation)\n\n
\n\n## TradingAgents Framework\n\nTradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively evaluates market conditions and informs trading decisions. Moreover, these agents engage in dynamic discussions to pinpoint the optimal strategy.\n\n\n \n
\n\n> TradingAgents framework is designed for research purposes. Trading performance may vary based on many factors, including the chosen backbone language models, model temperature, trading periods, the quality of data, and other non-deterministic factors. [It is not intended as financial, investment, or trading advice.](https://tauric.ai/disclaimer/)\n\nOur framework decomposes complex trading tasks into specialized roles. This ensures the system achieves a robust, scalable approach to market analysis and decision-making.\n\n### Analyst Team\n- Fundamentals Analyst: Evaluates company financials and performance metrics, identifying intrinsic values and potential red flags.\n- Sentiment Analyst: Analyzes social media and public sentiment using sentiment scoring algorithms to gauge short-term market mood.\n- News Analyst: Monitors global news and macroeconomic indicators, interpreting the impact of events on market conditions.\n- Technical Analyst: Utilizes technical indicators (like MACD and RSI) to detect trading patterns and forecast price movements.\n\n\n \n
\n\n### Researcher Team\n- Comprises both bullish and bearish researchers who critically assess the insights provided by the Analyst Team. Through structured debates, they balance potential gains against inherent risks.\n\n\n \n
\n\n### Trader Agent\n- Composes reports from the analysts and researchers to make informed trading decisions. It determines the timing and magnitude of trades based on comprehensive market insights.\n\n\n \n
\n\n### Risk Management and Portfolio Manager\n- Continuously evaluates portfolio risk by assessing market volatility, liquidity, and other risk factors. The risk management team evaluates and adjusts trading strategies, providing assessment reports to the Portfolio Manager for final decision.\n- The Portfolio Manager approves/rejects the transaction proposal. If approved, the order will be sent to the simulated exchange and executed.\n\n\n \n
\n\n## Installation and CLI\n\n### Installation\n\nClone TradingAgents:\n```bash\ngit clone https://github.com/TauricResearch/TradingAgents.git\ncd TradingAgents\n```\n\nCreate a virtual environment in any of your favorite environment managers:\n```bash\nconda create -n tradingagents python=3.13\nconda activate tradingagents\n```\n\nInstall dependencies:\n```bash\npip install -r requirements.txt\n```\n\n### Required APIs\n\nYou will also need the Alpha Vantage API for financial data. The free tier supports 25 API calls per day.\n```bash\nexport ALPHA_VANTAGE_API_KEY=$YOUR_ALPHA_VANTAGE_API_KEY\n```\n\nYou will need the OpenAI API for all the agents.\n```bash\nexport OPENAI_API_KEY=$YOUR_OPENAI_API_KEY\n```\n\nAlternatively, you can create a `.env` file in the project root with your API keys (see `.env.example` for reference):\n```bash\ncp .env.example .env\n# Edit .env with your actual API keys\n```\n\n### CLI Usage\n\nYou can also try out the CLI directly by running:\n```bash\npython -m cli.main\n```\nYou will see a screen where you can select your desired tickers, date, LLMs, research depth, etc.\n\n\n \n
\n\nAn interface will appear showing results as they load, letting you track the agent's progress as it runs.\n\n\n \n
\n\n\n \n
\n\n## TradingAgents Package\n\n### Implementation Details\n\nWe built TradingAgents with LangGraph to ensure flexibility and modularity. We utilize `o1-preview` and `gpt-4o` as our deep thinking and fast thinking LLMs for our experiments. However, for testing purposes, we recommend you use `o4-mini` and `gpt-4.1-mini` to save on costs as our framework makes **lots of** API calls.\n\n### Python Usage\n\nTo use TradingAgents inside your code, you can import the `tradingagents` module and initialize a `TradingAgentsGraph()` object. The `.propagate()` function will return a decision. You can run `main.py`, here's also a quick example:\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\nYou can also adjust the default configuration to set your own choice of LLMs, debate rounds, etc.\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\n# Create a custom config\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"deep_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"quick_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"max_debate_rounds\"] = 1 # Increase debate rounds\n\n# Configure data vendors (default uses Alpha Vantage for real-time data)\nconfig[\"data_vendors\"] = {\n \"core_stock_apis\": \"alpha_vantage\", # Options: alpha_vantage, yahoo_finance, local\n \"technical_indicators\": \"alpha_vantage\", # Options: alpha_vantage, yahoo_finance, local\n \"fundamental_data\": \"alpha_vantage\", # Options: alpha_vantage, openai, local\n \"news_data\": \"alpha_vantage\", # Options: alpha_vantage, openai, google, local\n}\n\n# Initialize with custom config\nta = TradingAgentsGraph(debug=True, config=config)\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\n> The default configuration now uses Alpha Vantage as the primary data provider, which provides access to real-time market data. For offline experimentation, there's a local data vendor option that uses our **Tauric TradingDB**, a curated dataset for backtesting, though this is still in development. We're currently refining this dataset and plan to release it soon alongside our upcoming projects. Stay tuned!\n\nYou can view the full list of configurations in `tradingagents/default_config.py`.\n\n## Contributing\n\nWe welcome contributions from the community! Whether it's fixing a bug, improving documentation, or suggesting a new feature, your input helps make this project better. If you are interested in this line of research, please consider joining our open-source financial AI research community [Tauric Research](https://tauric.ai/).\n\n## Citation\n\nPlease reference our work if you find *TradingAgents* provides you with some help :)\n\n```\n@misc{xiao2025tradingagentsmultiagentsllmfinancial,\n title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, \n author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang},\n year={2025},\n eprint={2412.20138},\n archivePrefix={arXiv},\n primaryClass={q-fin.TR},\n url={https://arxiv.org/abs/2412.20138}, \n}\n```\n"}, "7bcc2cbd8aa4ccf05e3a86ea7afae74e1aa2b649": {"t": 1785766211.2755601, "n": 10687, "h": "a99398eaf2e2c591", "c": "\n \n
\n\n\n\n\n\n---\n\n# TradingAgents: Multi-Agents LLM Financial Trading Framework \n\n> 🎉 **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.\n>\n> So we decided to fully open-source the framework. Looking forward to building impactful projects with you!\n\n\n\n\n\n🚀 [TradingAgents](#tradingagents-framework) | ⚡ [Installation & CLI](#installation-and-cli) | 🎬 [Demo](https://www.youtube.com/watch?v=90gr5lwjIho) | 📦 [Package Usage](#tradingagents-package) | 🤝 [Contributing](#contributing) | 📄 [Citation](#citation)\n\n
\n\n## TradingAgents Framework\n\nTradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively evaluates market conditions and informs trading decisions. Moreover, these agents engage in dynamic discussions to pinpoint the optimal strategy.\n\n\n \n
\n\n> TradingAgents framework is designed for research purposes. Trading performance may vary based on many factors, including the chosen backbone language models, model temperature, trading periods, the quality of data, and other non-deterministic factors. [It is not intended as financial, investment, or trading advice.](https://tauric.ai/disclaimer/)\n\nOur framework decomposes complex trading tasks into specialized roles. This ensures the system achieves a robust, scalable approach to market analysis and decision-making.\n\n### Analyst Team\n- Fundamentals Analyst: Evaluates company financials and performance metrics, identifying intrinsic values and potential red flags.\n- Sentiment Analyst: Analyzes social media and public sentiment using sentiment scoring algorithms to gauge short-term market mood.\n- News Analyst: Monitors global news and macroeconomic indicators, interpreting the impact of events on market conditions.\n- Technical Analyst: Utilizes technical indicators (like MACD and RSI) to detect trading patterns and forecast price movements.\n\n\n \n
\n\n### Researcher Team\n- Comprises both bullish and bearish researchers who critically assess the insights provided by the Analyst Team. Through structured debates, they balance potential gains against inherent risks.\n\n\n \n
\n\n### Trader Agent\n- Composes reports from the analysts and researchers to make informed trading decisions. It determines the timing and magnitude of trades based on comprehensive market insights.\n\n\n \n
\n\n### Risk Management and Portfolio Manager\n- Continuously evaluates portfolio risk by assessing market volatility, liquidity, and other risk factors. The risk management team evaluates and adjusts trading strategies, providing assessment reports to the Portfolio Manager for final decision.\n- The Portfolio Manager approves/rejects the transaction proposal. If approved, the order will be sent to the simulated exchange and executed.\n\n\n \n
\n\n## Installation and CLI\n\n### Installation\n\nClone TradingAgents:\n```bash\ngit clone https://github.com/TauricResearch/TradingAgents.git\ncd TradingAgents\n```\n\nCreate a virtual environment in any of your favorite environment managers:\n```bash\nconda create -n tradingagents python=3.13\nconda activate tradingagents\n```\n\nInstall dependencies:\n```bash\npip install -r requirements.txt\n```\n\n### Required APIs\n\nYou will also need the Alpha Vantage API for financial data. The free tier supports 25 API calls per day.\n```bash\nexport ALPHA_VANTAGE_API_KEY=$YOUR_ALPHA_VANTAGE_API_KEY\n```\n\nYou will need the OpenAI API for all the agents.\n```bash\nexport OPENAI_API_KEY=$YOUR_OPENAI_API_KEY\n```\n\n### CLI Usage\n\nYou can also try out the CLI directly by running:\n```bash\npython -m cli.main\n```\nYou will see a screen where you can select your desired tickers, date, LLMs, research depth, etc.\n\n\n \n
\n\nAn interface will appear showing results as they load, letting you track the agent's progress as it runs.\n\n\n \n
\n\n\n \n
\n\n## TradingAgents Package\n\n### Implementation Details\n\nWe built TradingAgents with LangGraph to ensure flexibility and modularity. We utilize `o1-preview` and `gpt-4o` as our deep thinking and fast thinking LLMs for our experiments. However, for testing purposes, we recommend you use `o4-mini` and `gpt-4.1-mini` to save on costs as our framework makes **lots of** API calls.\n\n### Python Usage\n\nTo use TradingAgents inside your code, you can import the `tradingagents` module and initialize a `TradingAgentsGraph()` object. The `.propagate()` function will return a decision. You can run `main.py`, here's also a quick example:\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\nYou can also adjust the default configuration to set your own choice of LLMs, debate rounds, etc.\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\n# Create a custom config\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"deep_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"quick_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"max_debate_rounds\"] = 1 # Increase debate rounds\n\n# Configure data vendors (default uses Alpha Vantage for real-time data)\nconfig[\"data_vendors\"] = {\n \"core_stock_apis\": \"alpha_vantage\", # Options: alpha_vantage, yahoo_finance, local\n \"technical_indicators\": \"alpha_vantage\", # Options: alpha_vantage, yahoo_finance, local\n \"fundamental_data\": \"alpha_vantage\", # Options: alpha_vantage, openai, local\n \"news_data\": \"alpha_vantage\", # Options: alpha_vantage, openai, google, local\n}\n\n# Initialize with custom config\nta = TradingAgentsGraph(debug=True, config=config)\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\n> The default configuration now uses Alpha Vantage as the primary data provider, which provides access to real-time market data. For offline experimentation, there's a local data vendor option that uses our **Tauric TradingDB**, a curated dataset for backtesting, though this is still in development. We're currently refining this dataset and plan to release it soon alongside our upcoming projects. Stay tuned!\n\nYou can view the full list of configurations in `tradingagents/default_config.py`.\n\n## Contributing\n\nWe welcome contributions from the community! Whether it's fixing a bug, improving documentation, or suggesting a new feature, your input helps make this project better. If you are interested in this line of research, please consider joining our open-source financial AI research community [Tauric Research](https://tauric.ai/).\n\n## Citation\n\nPlease reference our work if you find *TradingAgents* provides you with some help :)\n\n```\n@misc{xiao2025tradingagentsmultiagentsllmfinancial,\n title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, \n author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang},\n year={2025},\n eprint={2412.20138},\n archivePrefix={arXiv},\n primaryClass={q-fin.TR},\n url={https://arxiv.org/abs/2412.20138}, \n}\n```\n"}, "0ab323c2c6575d474575a0a623654dec126c55ce": {"t": 1785766212.7399917, "n": 10154, "h": "26392877afbdc197", "c": "\n \n
\n\n\n\n\n\n---\n\n# TradingAgents: Multi-Agents LLM Financial Trading Framework \n\n> 🎉 **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.\n>\n> So we decided to fully open-source the framework. Looking forward to building impactful projects with you!\n\n\n\n\n\n🚀 [TradingAgents](#tradingagents-framework) | ⚡ [Installation & CLI](#installation-and-cli) | 🎬 [Demo](https://www.youtube.com/watch?v=90gr5lwjIho) | 📦 [Package Usage](#tradingagents-package) | 🤝 [Contributing](#contributing) | 📄 [Citation](#citation)\n\n
\n\n## TradingAgents Framework\n\nTradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively evaluates market conditions and informs trading decisions. Moreover, these agents engage in dynamic discussions to pinpoint the optimal strategy.\n\n\n \n
\n\n> TradingAgents framework is designed for research purposes. Trading performance may vary based on many factors, including the chosen backbone language models, model temperature, trading periods, the quality of data, and other non-deterministic factors. [It is not intended as financial, investment, or trading advice.](https://tauric.ai/disclaimer/)\n\nOur framework decomposes complex trading tasks into specialized roles. This ensures the system achieves a robust, scalable approach to market analysis and decision-making.\n\n### Analyst Team\n- Fundamentals Analyst: Evaluates company financials and performance metrics, identifying intrinsic values and potential red flags.\n- Sentiment Analyst: Analyzes social media and public sentiment using sentiment scoring algorithms to gauge short-term market mood.\n- News Analyst: Monitors global news and macroeconomic indicators, interpreting the impact of events on market conditions.\n- Technical Analyst: Utilizes technical indicators (like MACD and RSI) to detect trading patterns and forecast price movements.\n\n\n \n
\n\n### Researcher Team\n- Comprises both bullish and bearish researchers who critically assess the insights provided by the Analyst Team. Through structured debates, they balance potential gains against inherent risks.\n\n\n \n
\n\n### Trader Agent\n- Composes reports from the analysts and researchers to make informed trading decisions. It determines the timing and magnitude of trades based on comprehensive market insights.\n\n\n \n
\n\n### Risk Management and Portfolio Manager\n- Continuously evaluates portfolio risk by assessing market volatility, liquidity, and other risk factors. The risk management team evaluates and adjusts trading strategies, providing assessment reports to the Portfolio Manager for final decision.\n- The Portfolio Manager approves/rejects the transaction proposal. If approved, the order will be sent to the simulated exchange and executed.\n\n\n \n
\n\n## Installation and CLI\n\n### Installation\n\nClone TradingAgents:\n```bash\ngit clone https://github.com/TauricResearch/TradingAgents.git\ncd TradingAgents\n```\n\nCreate a virtual environment in any of your favorite environment managers:\n```bash\nconda create -n tradingagents python=3.13\nconda activate tradingagents\n```\n\nInstall dependencies:\n```bash\npip install -r requirements.txt\n```\n\n### Required APIs\n\nYou will also need the Alpha Vantage API for financial data. The free tier supports 25 API calls per day.\n```bash\nexport ALPHA_VANTAGE_API_KEY=$YOUR_ALPHA_VANTAGE_API_KEY\n```\n\nYou will need the OpenAI API for all the agents.\n```bash\nexport OPENAI_API_KEY=$YOUR_OPENAI_API_KEY\n```\n\n### CLI Usage\n\nYou can also try out the CLI directly by running:\n```bash\npython -m cli.main\n```\nYou will see a screen where you can select your desired tickers, date, LLMs, research depth, etc.\n\n\n \n
\n\nAn interface will appear showing results as they load, letting you track the agent's progress as it runs.\n\n\n \n
\n\n\n \n
\n\n## TradingAgents Package\n\n### Implementation Details\n\nWe built TradingAgents with LangGraph to ensure flexibility and modularity. We utilize `o1-preview` and `gpt-4o` as our deep thinking and fast thinking LLMs for our experiments. However, for testing purposes, we recommend you use `o4-mini` and `gpt-4.1-mini` to save on costs as our framework makes **lots of** API calls.\n\n### Python Usage\n\nTo use TradingAgents inside your code, you can import the `tradingagents` module and initialize a `TradingAgentsGraph()` object. The `.propagate()` function will return a decision. You can run `main.py`, here's also a quick example:\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\nYou can also adjust the default configuration to set your own choice of LLMs, debate rounds, etc.\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\n# Create a custom config\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"deep_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"quick_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"max_debate_rounds\"] = 1 # Increase debate rounds\n\n# Initialize with custom config\nta = TradingAgentsGraph(debug=True, config=config)\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\n> We recommend enabling them for experimentation, as they provide access to real-time data. The agents' offline tools rely on cached data from our **Tauric TradingDB**, a curated dataset we use for backtesting. We're currently in the process of refining this dataset, and we plan to release it soon alongside our upcoming projects. Stay tuned!\n\nYou can view the full list of configurations in `tradingagents/default_config.py`.\n\n## Contributing\n\nWe welcome contributions from the community! Whether it's fixing a bug, improving documentation, or suggesting a new feature, your input helps make this project better. If you are interested in this line of research, please consider joining our open-source financial AI research community [Tauric Research](https://tauric.ai/).\n\n## Citation\n\nPlease reference our work if you find *TradingAgents* provides you with some help :)\n\n```\n@misc{xiao2025tradingagentsmultiagentsllmfinancial,\n title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, \n author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang},\n year={2025},\n eprint={2412.20138},\n archivePrefix={arXiv},\n primaryClass={q-fin.TR},\n url={https://arxiv.org/abs/2412.20138}, \n}\n```\n"}, "a6734d71bcca0543296bc2f202a2c98dbf74612f": {"t": 1785766214.1716354, "n": 10142, "h": "f56d4121725ece46", "c": "\n \n
\n\n\n\n\n\n---\n\n# TradingAgents: Multi-Agents LLM Financial Trading Framework \n\n> 🎉 **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.\n>\n> So we decided to fully open-source the framework. Looking forward to building impactful projects with you!\n\n\n\n\n\n🚀 [TradingAgents](#tradingagents-framework) | ⚡ [Installation & CLI](#installation-and-cli) | 🎬 [Demo](https://www.youtube.com/watch?v=90gr5lwjIho) | 📦 [Package Usage](#tradingagents-package) | 🤝 [Contributing](#contributing) | 📄 [Citation](#citation)\n\n
\n\n## TradingAgents Framework\n\nTradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively evaluates market conditions and informs trading decisions. Moreover, these agents engage in dynamic discussions to pinpoint the optimal strategy.\n\n\n \n
\n\n> TradingAgents framework is designed for research purposes. Trading performance may vary based on many factors, including the chosen backbone language models, model temperature, trading periods, the quality of data, and other non-deterministic factors. [It is not intended as financial, investment, or trading advice.](https://tauric.ai/disclaimer/)\n\nOur framework decomposes complex trading tasks into specialized roles. This ensures the system achieves a robust, scalable approach to market analysis and decision-making.\n\n### Analyst Team\n- Fundamentals Analyst: Evaluates company financials and performance metrics, identifying intrinsic values and potential red flags.\n- Sentiment Analyst: Analyzes social media and public sentiment using sentiment scoring algorithms to gauge short-term market mood.\n- News Analyst: Monitors global news and macroeconomic indicators, interpreting the impact of events on market conditions.\n- Technical Analyst: Utilizes technical indicators (like MACD and RSI) to detect trading patterns and forecast price movements.\n\n\n \n
\n\n### Researcher Team\n- Comprises both bullish and bearish researchers who critically assess the insights provided by the Analyst Team. Through structured debates, they balance potential gains against inherent risks.\n\n\n \n
\n\n### Trader Agent\n- Composes reports from the analysts and researchers to make informed trading decisions. It determines the timing and magnitude of trades based on comprehensive market insights.\n\n\n \n
\n\n### Risk Management and Portfolio Manager\n- Continuously evaluates portfolio risk by assessing market volatility, liquidity, and other risk factors. The risk management team evaluates and adjusts trading strategies, providing assessment reports to the Portfolio Manager for final decision.\n- The Portfolio Manager approves/rejects the transaction proposal. If approved, the order will be sent to the simulated exchange and executed.\n\n\n \n
\n\n## Installation and CLI\n\n### Installation\n\nClone TradingAgents:\n```bash\ngit clone https://github.com/TauricResearch/TradingAgents.git\ncd TradingAgents\n```\n\nCreate a virtual environment in any of your favorite environment managers:\n```bash\nconda create -n tradingagents python=3.13\nconda activate tradingagents\n```\n\nInstall dependencies:\n```bash\npip install -r requirements.txt\n```\n\n### Required APIs\n\nYou will also need the FinnHub API for financial data. All of our code is implemented with the free tier.\n```bash\nexport FINNHUB_API_KEY=$YOUR_FINNHUB_API_KEY\n```\n\nYou will need the OpenAI API for all the agents.\n```bash\nexport OPENAI_API_KEY=$YOUR_OPENAI_API_KEY\n```\n\n### CLI Usage\n\nYou can also try out the CLI directly by running:\n```bash\npython -m cli.main\n```\nYou will see a screen where you can select your desired tickers, date, LLMs, research depth, etc.\n\n\n \n
\n\nAn interface will appear showing results as they load, letting you track the agent's progress as it runs.\n\n\n \n
\n\n\n \n
\n\n## TradingAgents Package\n\n### Implementation Details\n\nWe built TradingAgents with LangGraph to ensure flexibility and modularity. We utilize `o1-preview` and `gpt-4o` as our deep thinking and fast thinking LLMs for our experiments. However, for testing purposes, we recommend you use `o4-mini` and `gpt-4.1-mini` to save on costs as our framework makes **lots of** API calls.\n\n### Python Usage\n\nTo use TradingAgents inside your code, you can import the `tradingagents` module and initialize a `TradingAgentsGraph()` object. The `.propagate()` function will return a decision. You can run `main.py`, here's also a quick example:\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\nYou can also adjust the default configuration to set your own choice of LLMs, debate rounds, etc.\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\n# Create a custom config\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"deep_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"quick_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"max_debate_rounds\"] = 1 # Increase debate rounds\n\n# Initialize with custom config\nta = TradingAgentsGraph(debug=True, config=config)\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\n> We recommend enabling them for experimentation, as they provide access to real-time data. The agents' offline tools rely on cached data from our **Tauric TradingDB**, a curated dataset we use for backtesting. We're currently in the process of refining this dataset, and we plan to release it soon alongside our upcoming projects. Stay tuned!\n\nYou can view the full list of configurations in `tradingagents/default_config.py`.\n\n## Contributing\n\nWe welcome contributions from the community! Whether it's fixing a bug, improving documentation, or suggesting a new feature, your input helps make this project better. If you are interested in this line of research, please consider joining our open-source financial AI research community [Tauric Research](https://tauric.ai/).\n\n## Citation\n\nPlease reference our work if you find *TradingAgents* provides you with some help :)\n\n```\n@misc{xiao2025tradingagentsmultiagentsllmfinancial,\n title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, \n author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang},\n year={2025},\n eprint={2412.20138},\n archivePrefix={arXiv},\n primaryClass={q-fin.TR},\n url={https://arxiv.org/abs/2412.20138}, \n}\n```\n"}, "26c5ba5a786e1da47c90b014faad889d759f6c76": {"t": 1785766215.5351756, "n": 10226, "h": "001c7603ca2e7bbf", "c": "\n \n
\n\n\n\n\n\n---\n\n# TradingAgents: Multi-Agents LLM Financial Trading Framework \n\n> 🎉 **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.\n>\n> So we decided to fully open-source the framework. Looking forward to building impactful projects with you!\n\n\n\n\n\n🚀 [TradingAgents](#tradingagents-framework) | ⚡ [Installation & CLI](#installation-and-cli) | 🎬 [Demo](https://www.youtube.com/watch?v=90gr5lwjIho) | 📦 [Package Usage](#tradingagents-package) | 🤝 [Contributing](#contributing) | 📄 [Citation](#citation)\n\n
\n\n## TradingAgents Framework\n\nTradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively evaluates market conditions and informs trading decisions. Moreover, these agents engage in dynamic discussions to pinpoint the optimal strategy.\n\n\n \n
\n\n> TradingAgents framework is designed for research purposes. Trading performance may vary based on many factors, including the chosen backbone language models, model temperature, trading periods, the quality of data, and other non-deterministic factors. [It is not intended as financial, investment, or trading advice.](https://tauric.ai/disclaimer/)\n\nOur framework decomposes complex trading tasks into specialized roles. This ensures the system achieves a robust, scalable approach to market analysis and decision-making.\n\n### Analyst Team\n- Fundamentals Analyst: Evaluates company financials and performance metrics, identifying intrinsic values and potential red flags.\n- Sentiment Analyst: Analyzes social media and public sentiment using sentiment scoring algorithms to gauge short-term market mood.\n- News Analyst: Monitors global news and macroeconomic indicators, interpreting the impact of events on market conditions.\n- Technical Analyst: Utilizes technical indicators (like MACD and RSI) to detect trading patterns and forecast price movements.\n\n\n \n
\n\n### Researcher Team\n- Comprises both bullish and bearish researchers who critically assess the insights provided by the Analyst Team. Through structured debates, they balance potential gains against inherent risks.\n\n\n \n
\n\n### Trader Agent\n- Composes reports from the analysts and researchers to make informed trading decisions. It determines the timing and magnitude of trades based on comprehensive market insights.\n\n\n \n
\n\n### Risk Management and Portfolio Manager\n- Continuously evaluates portfolio risk by assessing market volatility, liquidity, and other risk factors. The risk management team evaluates and adjusts trading strategies, providing assessment reports to the Portfolio Manager for final decision.\n- The Portfolio Manager approves/rejects the transaction proposal. If approved, the order will be sent to the simulated exchange and executed.\n\n\n \n
\n\n## Installation and CLI\n\n### Installation\n\nClone TradingAgents:\n```bash\ngit clone https://github.com/TauricResearch/TradingAgents.git\ncd TradingAgents\n```\n\nCreate a virtual environment in any of your favorite environment managers:\n```bash\nconda create -n tradingagents python=3.13\nconda activate tradingagents\n```\n\nInstall dependencies:\n```bash\npip install -r requirements.txt\n```\n\n### Required APIs\n\nYou will also need the FinnHub API for financial data. All of our code is implemented with the free tier.\n```bash\nexport FINNHUB_API_KEY=$YOUR_FINNHUB_API_KEY\n```\n\nYou will need the OpenAI API for all the agents.\n```bash\nexport OPENAI_API_KEY=$YOUR_OPENAI_API_KEY\n```\n\n### CLI Usage\n\nYou can also try out the CLI directly by running:\n```bash\npython -m cli.main\n```\nYou will see a screen where you can select your desired tickers, date, LLMs, research depth, etc.\n\n\n \n
\n\nAn interface will appear showing results as they load, letting you track the agent's progress as it runs.\n\n\n \n
\n\n\n \n
\n\n## TradingAgents Package\n\n### Implementation Details\n\nWe built TradingAgents with LangGraph to ensure flexibility and modularity. We utilize `o1-preview` and `gpt-4o` as our deep thinking and fast thinking LLMs for our experiments. However, for testing purposes, we recommend you use `o4-mini` and `gpt-4.1-mini` to save on costs as our framework makes **lots of** API calls.\n\n### Python Usage\n\nTo use TradingAgents inside your code, you can import the `tradingagents` module and initialize a `TradingAgentsGraph()` object. The `.propagate()` function will return a decision. You can run `main.py`, here's also a quick example:\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\nYou can also adjust the default configuration to set your own choice of LLMs, debate rounds, etc.\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\n# Create a custom config\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"deep_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"quick_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"max_debate_rounds\"] = 1 # Increase debate rounds\nconfig[\"online_tools\"] = True # Use online tools or cached data\n\n# Initialize with custom config\nta = TradingAgentsGraph(debug=True, config=config)\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\n> For `online_tools`, we recommend enabling them for experimentation, as they provide access to real-time data. The agents' offline tools rely on cached data from our **Tauric TradingDB**, a curated dataset we use for backtesting. We're currently in the process of refining this dataset, and we plan to release it soon alongside our upcoming projects. Stay tuned!\n\nYou can view the full list of configurations in `tradingagents/default_config.py`.\n\n## Contributing\n\nWe welcome contributions from the community! Whether it's fixing a bug, improving documentation, or suggesting a new feature, your input helps make this project better. If you are interested in this line of research, please consider joining our open-source financial AI research community [Tauric Research](https://tauric.ai/).\n\n## Citation\n\nPlease reference our work if you find *TradingAgents* provides you with some help :)\n\n```\n@misc{xiao2025tradingagentsmultiagentsllmfinancial,\n title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, \n author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang},\n year={2025},\n eprint={2412.20138},\n archivePrefix={arXiv},\n primaryClass={q-fin.TR},\n url={https://arxiv.org/abs/2412.20138}, \n}\n```\n"}, "78ea029a0bbe3ea23c0016c1f54d022bc8c28459": {"t": 1785766217.2023344, "n": 10323, "h": "78f2144f1b821be3", "c": "\n \n
\n\n\n\n\n\n---\n\n# TradingAgents: Multi-Agents LLM Financial Trading Framework \n\n> 🎉 **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.\n>\n> So we decided to fully open-source the framework. Looking forward to building impactful projects with you!\n\n\n\n\n\n🚀 [TradingAgents](#tradingagents-framework) | ⚡ [Installation & CLI](#installation-and-cli) | 🎬 [Demo](https://www.youtube.com/watch?v=90gr5lwjIho) | 📦 [Package Usage](#tradingagents-package) | 🤝 [Contributing](#contributing) | 📄 [Citation](#citation)\n\n
\n\n## TradingAgents Framework\n\nTradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively evaluates market conditions and informs trading decisions. Moreover, these agents engage in dynamic discussions to pinpoint the optimal strategy.\n\n\n \n
\n\n> TradingAgents framework is designed for research purposes. Trading performance may vary based on many factors, including the chosen backbone language models, model temperature, trading periods, the quality of data, and other non-deterministic factors. [It is not intended as financial, investment, or trading advice.](https://tauric.ai/disclaimer/)\n\nOur framework decomposes complex trading tasks into specialized roles. This ensures the system achieves a robust, scalable approach to market analysis and decision-making.\n\n### Analyst Team\n- Fundamentals Analyst: Evaluates company financials and performance metrics, identifying intrinsic values and potential red flags.\n- Sentiment Analyst: Analyzes social media and public sentiment using sentiment scoring algorithms to gauge short-term market mood.\n- News Analyst: Monitors global news and macroeconomic indicators, interpreting the impact of events on market conditions.\n- Technical Analyst: Utilizes technical indicators (like MACD and RSI) to detect trading patterns and forecast price movements.\n\n\n \n
\n\n### Researcher Team\n- Comprises both bullish and bearish researchers who critically assess the insights provided by the Analyst Team. Through structured debates, they balance potential gains against inherent risks.\n\n\n \n
\n\n### Trader Agent\n- Composes reports from the analysts and researchers to make informed trading decisions. It determines the timing and magnitude of trades based on comprehensive market insights.\n\n\n \n
\n\n### Risk Management and Portfolio Manager\n- Continuously evaluates portfolio risk by assessing market volatility, liquidity, and other risk factors. The risk management team evaluates and adjusts trading strategies, providing assessment reports to the Portfolio Manager for final decision.\n- The Portfolio Manager approves/rejects the transaction proposal. If approved, the order will be sent to the simulated exchange and executed.\n\n\n \n
\n\n## Installation and CLI\n\n### Installation\n\nClone TradingAgents:\n```bash\ngit clone https://github.com/TauricResearch/TradingAgents.git\ncd TradingAgents\n```\n\nCreate a virtual environment in any of your favorite environment managers:\n```bash\nconda create -n tradingagents python=3.13\nconda activate tradingagents\n```\n\nInstall dependencies:\n```bash\npip install -r requirements.txt\n```\n\n### Required APIs\n\nYou will also need the FinnHub API for financial data. All of our code is implemented with the free tier.\n```bash\nexport FINNHUB_API_KEY=$YOUR_FINNHUB_API_KEY\n```\n\nYou will need the OpenAI API for all the agents.\n```bash\nexport OPENAI_API_KEY=$YOUR_OPENAI_API_KEY\n```\n\n### CLI Usage\n\nYou can also try out the CLI directly by running:\n```bash\npython -m cli.main\n```\nYou will see a screen where you can select your desired tickers, date, LLMs, research depth, etc.\n\n\n \n
\n\nAn interface will appear showing results as they load, letting you track the agent's progress as it runs.\n\n\n \n
\n\n\n \n
\n\n## TradingAgents Package\n\n### Implementation Details\n\nWe built TradingAgents with LangGraph to ensure flexibility and modularity. We utilize `o1-preview` and `gpt-4o` as our deep thinking and fast thinking LLMs for our experiments. However, for testing purposes, we recommend you use `o4-mini` and `gpt-4.1-mini` to save on costs as our framework makes **lots of** API calls.\n\n### Python Usage\n\nTo use TradingAgents inside your code, you can import the `tradingagents` module and initialize a `TradingAgentsGraph()` object. The `.propagate()` function will return a decision. You can run `main.py`, here's also a quick example:\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\nYou can also adjust the default configuration to set your own choice of LLMs, debate rounds, etc.\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\n# Create a custom config\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"deep_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"quick_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"max_debate_rounds\"] = 1 # Increase debate rounds\nconfig[\"online_tools\"] = True # Use online tools or cached data\n\n# Initialize with custom config\nta = TradingAgentsGraph(debug=True, config=config)\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\n> For `online_tools`, we recommend enabling them for experimentation, as they provide access to real-time data. The agents' offline tools rely on cached data from our **Tauric TradingDB**, a curated dataset we use for backtesting. We're currently in the process of refining this dataset, and we plan to release it soon alongside our upcoming projects. Stay tuned!\n\nYou can view the full list of configurations in `tradingagents/default_config.py`.\n\n## Docker usage and local ollama tests ##\n\nSee [Docker Readme](./Docker-readme.md) for details.\n\n## Contributing\n\nWe welcome contributions from the community! Whether it's fixing a bug, improving documentation, or suggesting a new feature, your input helps make this project better. If you are interested in this line of research, please consider joining our open-source financial AI research community [Tauric Research](https://tauric.ai/).\n\n## Citation\n\nPlease reference our work if you find *TradingAgents* provides you with some help :)\n\n```\n@misc{xiao2025tradingagentsmultiagentsllmfinancial,\n title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, \n author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang},\n year={2025},\n eprint={2412.20138},\n archivePrefix={arXiv},\n primaryClass={q-fin.TR},\n url={https://arxiv.org/abs/2412.20138}, \n}\n```\n"}, "383deb72aac77d898c11e9bbbf5bfd17790a5371": {"t": 1785766218.5347402, "n": 10226, "h": "001c7603ca2e7bbf", "c": "\n \n
\n\n\n\n\n\n---\n\n# TradingAgents: Multi-Agents LLM Financial Trading Framework \n\n> 🎉 **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.\n>\n> So we decided to fully open-source the framework. Looking forward to building impactful projects with you!\n\n\n\n\n\n🚀 [TradingAgents](#tradingagents-framework) | ⚡ [Installation & CLI](#installation-and-cli) | 🎬 [Demo](https://www.youtube.com/watch?v=90gr5lwjIho) | 📦 [Package Usage](#tradingagents-package) | 🤝 [Contributing](#contributing) | 📄 [Citation](#citation)\n\n
\n\n## TradingAgents Framework\n\nTradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively evaluates market conditions and informs trading decisions. Moreover, these agents engage in dynamic discussions to pinpoint the optimal strategy.\n\n\n \n
\n\n> TradingAgents framework is designed for research purposes. Trading performance may vary based on many factors, including the chosen backbone language models, model temperature, trading periods, the quality of data, and other non-deterministic factors. [It is not intended as financial, investment, or trading advice.](https://tauric.ai/disclaimer/)\n\nOur framework decomposes complex trading tasks into specialized roles. This ensures the system achieves a robust, scalable approach to market analysis and decision-making.\n\n### Analyst Team\n- Fundamentals Analyst: Evaluates company financials and performance metrics, identifying intrinsic values and potential red flags.\n- Sentiment Analyst: Analyzes social media and public sentiment using sentiment scoring algorithms to gauge short-term market mood.\n- News Analyst: Monitors global news and macroeconomic indicators, interpreting the impact of events on market conditions.\n- Technical Analyst: Utilizes technical indicators (like MACD and RSI) to detect trading patterns and forecast price movements.\n\n\n \n
\n\n### Researcher Team\n- Comprises both bullish and bearish researchers who critically assess the insights provided by the Analyst Team. Through structured debates, they balance potential gains against inherent risks.\n\n\n \n
\n\n### Trader Agent\n- Composes reports from the analysts and researchers to make informed trading decisions. It determines the timing and magnitude of trades based on comprehensive market insights.\n\n\n \n
\n\n### Risk Management and Portfolio Manager\n- Continuously evaluates portfolio risk by assessing market volatility, liquidity, and other risk factors. The risk management team evaluates and adjusts trading strategies, providing assessment reports to the Portfolio Manager for final decision.\n- The Portfolio Manager approves/rejects the transaction proposal. If approved, the order will be sent to the simulated exchange and executed.\n\n\n \n
\n\n## Installation and CLI\n\n### Installation\n\nClone TradingAgents:\n```bash\ngit clone https://github.com/TauricResearch/TradingAgents.git\ncd TradingAgents\n```\n\nCreate a virtual environment in any of your favorite environment managers:\n```bash\nconda create -n tradingagents python=3.13\nconda activate tradingagents\n```\n\nInstall dependencies:\n```bash\npip install -r requirements.txt\n```\n\n### Required APIs\n\nYou will also need the FinnHub API for financial data. All of our code is implemented with the free tier.\n```bash\nexport FINNHUB_API_KEY=$YOUR_FINNHUB_API_KEY\n```\n\nYou will need the OpenAI API for all the agents.\n```bash\nexport OPENAI_API_KEY=$YOUR_OPENAI_API_KEY\n```\n\n### CLI Usage\n\nYou can also try out the CLI directly by running:\n```bash\npython -m cli.main\n```\nYou will see a screen where you can select your desired tickers, date, LLMs, research depth, etc.\n\n\n \n
\n\nAn interface will appear showing results as they load, letting you track the agent's progress as it runs.\n\n\n \n
\n\n\n \n
\n\n## TradingAgents Package\n\n### Implementation Details\n\nWe built TradingAgents with LangGraph to ensure flexibility and modularity. We utilize `o1-preview` and `gpt-4o` as our deep thinking and fast thinking LLMs for our experiments. However, for testing purposes, we recommend you use `o4-mini` and `gpt-4.1-mini` to save on costs as our framework makes **lots of** API calls.\n\n### Python Usage\n\nTo use TradingAgents inside your code, you can import the `tradingagents` module and initialize a `TradingAgentsGraph()` object. The `.propagate()` function will return a decision. You can run `main.py`, here's also a quick example:\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\nYou can also adjust the default configuration to set your own choice of LLMs, debate rounds, etc.\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\n# Create a custom config\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"deep_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"quick_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"max_debate_rounds\"] = 1 # Increase debate rounds\nconfig[\"online_tools\"] = True # Use online tools or cached data\n\n# Initialize with custom config\nta = TradingAgentsGraph(debug=True, config=config)\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\n> For `online_tools`, we recommend enabling them for experimentation, as they provide access to real-time data. The agents' offline tools rely on cached data from our **Tauric TradingDB**, a curated dataset we use for backtesting. We're currently in the process of refining this dataset, and we plan to release it soon alongside our upcoming projects. Stay tuned!\n\nYou can view the full list of configurations in `tradingagents/default_config.py`.\n\n## Contributing\n\nWe welcome contributions from the community! Whether it's fixing a bug, improving documentation, or suggesting a new feature, your input helps make this project better. If you are interested in this line of research, please consider joining our open-source financial AI research community [Tauric Research](https://tauric.ai/).\n\n## Citation\n\nPlease reference our work if you find *TradingAgents* provides you with some help :)\n\n```\n@misc{xiao2025tradingagentsmultiagentsllmfinancial,\n title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, \n author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang},\n year={2025},\n eprint={2412.20138},\n archivePrefix={arXiv},\n primaryClass={q-fin.TR},\n url={https://arxiv.org/abs/2412.20138}, \n}\n```\n"}, "a87986839632535a61bdd1383e8c9f81dd3a87da": {"t": 1785766220.098545, "n": 10226, "h": "8837e7f41734382b", "c": "\n \n
\n\n\n\n\n\n---\n\n# TradingAgents: Multi-Agents LLM Financial Trading Framework \n\n> 🎉 **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.\n>\n> So we decided to fully open-source the framework. Looking forward to building impactful projects with you!\n\n\n\n\n\n🚀 [TradingAgents](#tradingagents-framework) | ⚡ [Installation & CLI](#installation-and-cli) | 🎬 [Demo](https://www.youtube.com/watch?v=90gr5lwjIho) | 📦 [Package Usage](#tradingagents-package) | 🤝 [Contributing](#contributing) | 📄 [Citation](#citation)\n\n
\n\n## TradingAgents Framework\n\nTradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively evaluates market conditions and informs trading decisions. Moreover, these agents engage in dynamic discussions to pinpoint the optimal strategy.\n\n\n \n
\n\n> TradingAgents framework is designed for research purposes. Trading performance may vary based on many factors, including the chosen backbone language models, model temperature, trading periods, the quality of data, and other non-deterministic factors. [It is not intended as financial, investment, or trading advice.](https://tauric.ai/disclaimer/)\n\nOur framework decomposes complex trading tasks into specialized roles. This ensures the system achieves a robust, scalable approach to market analysis and decision-making.\n\n### Analyst Team\n- Fundamentals Analyst: Evaluates company financials and performance metrics, identifying intrinsic values and potential red flags.\n- Sentiment Analyst: Analyzes social media and public sentiment using sentiment scoring algorithms to gauge short-term market mood.\n- News Analyst: Monitors global news and macroeconomic indicators, interpreting the impact of events on market conditions.\n- Technical Analyst: Utilizes technical indicators (like MACD and RSI) to detect trading patterns and forecast price movements.\n\n\n \n
\n\n### Researcher Team\n- Comprises both bullish and bearish researchers who critically assess the insights provided by the Analyst Team. Through structured debates, they balance potential gains against inherent risks.\n\n\n \n
\n\n### Trader Agent\n- Composes reports from the analysts and researchers to make informed trading decisions. It determines the timing and magnitude of trades based on comprehensive market insights.\n\n\n \n
\n\n### Risk Management and Portfolio Manager\n- Continuously evaluates portfolio risk by assessing market volatility, liquidity, and other risk factors. The risk management team evaluates and adjusts trading strategies, providing assessment reports to the Portfolio Manager for final decision.\n- The Portfolio Manager approves/rejects the transaction proposal. If approved, the order will be sent to the simulated exchange and executed.\n\n\n \n
\n\n## Installation and CLI\n\n### Installation\n\nClone TradingAgents:\n```bash\ngit clone https://github.com/TauricResearch/TradingAgents.git\ncd TradingAgents\n```\n\nCreate a virtual environment in any of your favorite environment managers:\n```bash\nconda create -n tradingagents python=3.13\nconda activate tradingagents\n```\n\nInstall dependencies:\n```bash\npip install -r requirements.txt\n```\n\n### Required APIs\n\nYou will also need the FinnHub API for financial data. All of our code is implemented with the free tier.\n```bash\nexport FINNHUB_API_KEY=$YOUR_FINNHUB_API_KEY\n```\n\nYou will need the OpenAI API for all the agents.\n```bash\nexport OPENAI_API_KEY=$YOUR_OPENAI_API_KEY\n```\n\n### CLI Usage\n\nYou can also try out the CLI directly by running:\n```bash\npython -m cli.main\n```\nYou will see a screen where you can select your desired tickers, date, LLMs, research depth, etc.\n\n\n \n
\n\nAn interface will appear showing results as they load, letting you track the agent's progress as it runs.\n\n\n \n
\n\n\n \n
\n\n## TradingAgents Package\n\n### Implementation Details\n\nWe built TradingAgents with LangGraph to ensure flexibility and modularity. We utilize `o1-preview` and `gpt-4o` as our deep thinking and fast thinking LLMs for our experiments. However, for testing purposes, we recommend you use `o4-mini` and `gpt-4.1-mini` to save on costs as our framework makes **lots of** API calls.\n\n### Python Usage\n\nTo use TradingAgents inside your code, you can import the `tradingagents` module and initialize a `TradingAgentsGraph()` object. The `.propagate()` function will return a decision. You can run `main.py`, here's also a quick example:\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\nYou can also adjust the default configuration to set your own choice of LLMs, debate rounds, etc.\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\n# Create a custom config\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"deep_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"quick_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"max_debate_rounds\"] = 1 # Increase debate rounds\nconfig[\"online_tools\"] = True # Use online tools or cached data\n\n# Initialize with custom config\nta = TradingAgentsGraph(debug=True, config=config)\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\n> For `online_tools`, we recommend enabling them for experimentation, as they provide access to real-time data. The agents' offline tools rely on cached data from our **Tauric TradingDB**, a curated dataset we use for backtesting. We're currently in the process of refining this dataset, and we plan to release it soon alongside our upcoming projects. Stay tuned!\n\nYou can view the full list of configurations in `tradingagents/default_config.py`.\n\n## Contributing\n\nWe welcome contributions from the community! Whether it's fixing a bug, improving documentation, or suggesting a new feature, your input helps make this project better. If you are interested in this line of research, please consider joining our open-source financial AI research community [Tauric Research](https://tauric.ai/).\n\n## Citation\n\nPlease reference our work if you find *TradingAgents* provides you with some help :)\n\n```\n@misc{xiao2025tradingagentsmultiagentsllmfinancial,\n title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, \n author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang},\n year={2025},\n eprint={2412.20138},\n archivePrefix={arXiv},\n primaryClass={q-fin.TR},\n url={https://arxiv.org/abs/2412.20138}, \n}\n```\n"}, "0013415378dc83f45f7cf56d3457f6bcef381b90": {"t": 1785766221.309299, "n": 9389, "h": "f6abba2404220012", "c": "\n \n
\n\n\n\n---\n\n# TradingAgents: Multi-Agents LLM Financial Trading Framework \n\n> 🎉 **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.\n>\n> So we decided to fully open-source the framework. Looking forward to building impactful projects with you!\n\n\n\n\n\n🚀 [TradingAgents](#tradingagents-framework) | ⚡ [Installation & CLI](#installation-and-cli) | 🎬 [Demo](https://www.youtube.com/watch?v=90gr5lwjIho) | 📦 [Package Usage](#tradingagents-package) | 🤝 [Contributing](#contributing) | 📄 [Citation](#citation)\n\n
\n\n## TradingAgents Framework\n\nTradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively evaluates market conditions and informs trading decisions. Moreover, these agents engage in dynamic discussions to pinpoint the optimal strategy.\n\n\n \n
\n\n> TradingAgents framework is designed for research purposes. Trading performance may vary based on many factors, including the chosen backbone language models, model temperature, trading periods, the quality of data, and other non-deterministic factors. [It is not intended as financial, investment, or trading advice.](https://tauric.ai/disclaimer/)\n\nOur framework decomposes complex trading tasks into specialized roles. This ensures the system achieves a robust, scalable approach to market analysis and decision-making.\n\n### Analyst Team\n- Fundamentals Analyst: Evaluates company financials and performance metrics, identifying intrinsic values and potential red flags.\n- Sentiment Analyst: Analyzes social media and public sentiment using sentiment scoring algorithms to gauge short-term market mood.\n- News Analyst: Monitors global news and macroeconomic indicators, interpreting the impact of events on market conditions.\n- Technical Analyst: Utilizes technical indicators (like MACD and RSI) to detect trading patterns and forecast price movements.\n\n\n \n
\n\n### Researcher Team\n- Comprises both bullish and bearish researchers who critically assess the insights provided by the Analyst Team. Through structured debates, they balance potential gains against inherent risks.\n\n\n \n
\n\n### Trader Agent\n- Composes reports from the analysts and researchers to make informed trading decisions. It determines the timing and magnitude of trades based on comprehensive market insights.\n\n\n \n
\n\n### Risk Management and Portfolio Manager\n- Continuously evaluates portfolio risk by assessing market volatility, liquidity, and other risk factors. The risk management team evaluates and adjusts trading strategies, providing assessment reports to the Portfolio Manager for final decision.\n- The Portfolio Manager approves/rejects the transaction proposal. If approved, the order will be sent to the simulated exchange and executed.\n\n\n \n
\n\n## Installation and CLI\n\n### Installation\n\nClone TradingAgents:\n```bash\ngit clone https://github.com/TauricResearch/TradingAgents.git\ncd TradingAgents\n```\n\nCreate a virtual environment in any of your favorite environment managers:\n```bash\nconda create -n tradingagents python=3.13\nconda activate tradingagents\n```\n\nInstall dependencies:\n```bash\npip install -r requirements.txt\n```\n\n### Required APIs\n\nYou will also need the FinnHub API for financial data. All of our code is implemented with the free tier.\n```bash\nexport FINNHUB_API_KEY=$YOUR_FINNHUB_API_KEY\n```\n\nYou will need the OpenAI API for all the agents.\n```bash\nexport OPENAI_API_KEY=$YOUR_OPENAI_API_KEY\n```\n\n### CLI Usage\n\nYou can also try out the CLI directly by running:\n```bash\npython -m cli.main\n```\nYou will see a screen where you can select your desired tickers, date, LLMs, research depth, etc.\n\n\n \n
\n\nAn interface will appear showing results as they load, letting you track the agent's progress as it runs.\n\n\n \n
\n\n\n \n
\n\n## TradingAgents Package\n\n### Implementation Details\n\nWe built TradingAgents with LangGraph to ensure flexibility and modularity. We utilize `o1-preview` and `gpt-4o` as our deep thinking and fast thinking LLMs for our experiments. However, for testing purposes, we recommend you use `o4-mini` and `gpt-4.1-mini` to save on costs as our framework makes **lots of** API calls.\n\n### Python Usage\n\nTo use TradingAgents inside your code, you can import the `tradingagents` module and initialize a `TradingAgentsGraph()` object. The `.propagate()` function will return a decision. You can run `main.py`, here's also a quick example:\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\nYou can also adjust the default configuration to set your own choice of LLMs, debate rounds, etc.\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\n# Create a custom config\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"deep_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"quick_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"max_debate_rounds\"] = 1 # Increase debate rounds\nconfig[\"online_tools\"] = True # Use online tools or cached data\n\n# Initialize with custom config\nta = TradingAgentsGraph(debug=True, config=config)\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\n> For `online_tools`, we recommend enabling them for experimentation, as they provide access to real-time data. The agents' offline tools rely on cached data from our **Tauric TradingDB**, a curated dataset we use for backtesting. We're currently in the process of refining this dataset, and we plan to release it soon alongside our upcoming projects. Stay tuned!\n\nYou can view the full list of configurations in `tradingagents/default_config.py`.\n\n## Contributing\n\nWe welcome contributions from the community! Whether it's fixing a bug, improving documentation, or suggesting a new feature, your input helps make this project better. If you are interested in this line of research, please consider joining our open-source financial AI research community [Tauric Research](https://tauric.ai/).\n\n## Citation\n\nPlease reference our work if you find *TradingAgents* provides you with some help :)\n\n```\n@misc{xiao2025tradingagentsmultiagentsllmfinancial,\n title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, \n author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang},\n year={2025},\n eprint={2412.20138},\n archivePrefix={arXiv},\n primaryClass={q-fin.TR},\n url={https://arxiv.org/abs/2412.20138}, \n}\n```\n"}, "0fdfd3586784193d7dc69bfa7bc0b4f2002caca2": {"t": 1785766223.3014958, "n": 8807, "h": "dbe9feedfe257ad3", "c": "\n \n
\n\n\n\n---\n\n# TradingAgents: Multi-Agents LLM Financial Trading Framework \n\n> 🎉 **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.\n>\n> So we decided to fully open-source the framework. Looking forward to building impactful projects with you!\n\n\n\n🚀 [TradingAgents](#tradingagents-framework) | ⚡ [Installation & CLI](#installation-and-cli) | 🎬 [Demo](https://www.youtube.com/watch?v=90gr5lwjIho) | 📦 [Package Usage](#tradingagents-package) | 🤝 [Contributing](#contributing) | 📄 [Citation](#citation)\n\n
\n\n## TradingAgents Framework\n\nTradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively evaluates market conditions and informs trading decisions. Moreover, these agents engage in dynamic discussions to pinpoint the optimal strategy.\n\n\n \n
\n\n> TradingAgents framework is designed for research purposes. Trading performance may vary based on many factors, including the chosen backbone language models, model temperature, trading periods, the quality of data, and other non-deterministic factors. [It is not intended as financial, investment, or trading advice.](https://tauric.ai/disclaimer/)\n\nOur framework decomposes complex trading tasks into specialized roles. This ensures the system achieves a robust, scalable approach to market analysis and decision-making.\n\n### Analyst Team\n- Fundamentals Analyst: Evaluates company financials and performance metrics, identifying intrinsic values and potential red flags.\n- Sentiment Analyst: Analyzes social media and public sentiment using sentiment scoring algorithms to gauge short-term market mood.\n- News Analyst: Monitors global news and macroeconomic indicators, interpreting the impact of events on market conditions.\n- Technical Analyst: Utilizes technical indicators (like MACD and RSI) to detect trading patterns and forecast price movements.\n\n\n \n
\n\n### Researcher Team\n- Comprises both bullish and bearish researchers who critically assess the insights provided by the Analyst Team. Through structured debates, they balance potential gains against inherent risks.\n\n\n \n
\n\n### Trader Agent\n- Composes reports from the analysts and researchers to make informed trading decisions. It determines the timing and magnitude of trades based on comprehensive market insights.\n\n\n \n
\n\n### Risk Management and Portfolio Manager\n- Continuously evaluates portfolio risk by assessing market volatility, liquidity, and other risk factors. The risk management team evaluates and adjusts trading strategies, providing assessment reports to the Portfolio Manager for final decision.\n- The Portfolio Manager approves/rejects the transaction proposal. If approved, the order will be sent to the simulated exchange and executed.\n\n\n \n
\n\n## Installation and CLI\n\n### Installation\n\nClone TradingAgents:\n```bash\ngit clone https://github.com/TauricResearch/TradingAgents.git\ncd TradingAgents\n```\n\nCreate a virtual environment in any of your favorite environment managers:\n```bash\nconda create -n tradingagents python=3.13\nconda activate tradingagents\n```\n\nInstall dependencies:\n```bash\npip install -r requirements.txt\n```\n\n### Required APIs\n\nYou will also need the FinnHub API for financial data. All of our code is implemented with the free tier.\n```bash\nexport FINNHUB_API_KEY=$YOUR_FINNHUB_API_KEY\n```\n\nYou will need the OpenAI API for all the agents.\n```bash\nexport OPENAI_API_KEY=$YOUR_OPENAI_API_KEY\n```\n\n### CLI Usage\n\nYou can also try out the CLI directly by running:\n```bash\npython -m cli.main\n```\nYou will see a screen where you can select your desired tickers, date, LLMs, research depth, etc.\n\n\n \n
\n\nAn interface will appear showing results as they load, letting you track the agent's progress as it runs.\n\n\n \n
\n\n\n \n
\n\n## TradingAgents Package\n\n### Implementation Details\n\nWe built TradingAgents with LangGraph to ensure flexibility and modularity. We utilize `o1-preview` and `gpt-4o` as our deep thinking and fast thinking LLMs for our experiments. However, for testing purposes, we recommend you use `o4-mini` and `gpt-4.1-mini` to save on costs as our framework makes **lots of** API calls.\n\n### Python Usage\n\nTo use TradingAgents inside your code, you can import the `tradingagents` module and initialize a `TradingAgentsGraph()` object. The `.propagate()` function will return a decision. You can run `main.py`, here's also a quick example:\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\nYou can also adjust the default configuration to set your own choice of LLMs, debate rounds, etc.\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\n# Create a custom config\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"deep_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"quick_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"max_debate_rounds\"] = 1 # Increase debate rounds\nconfig[\"online_tools\"] = True # Use online tools or cached data\n\n# Initialize with custom config\nta = TradingAgentsGraph(debug=True, config=config)\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\n> For `online_tools`, we recommend enabling them for experimentation, as they provide access to real-time data. The agents' offline tools rely on cached data from our **Tauric TradingDB**, a curated dataset we use for backtesting. We're currently in the process of refining this dataset, and we plan to release it soon alongside our upcoming projects. Stay tuned!\n\nYou can view the full list of configurations in `tradingagents/default_config.py`.\n\n## Contributing\n\nWe welcome contributions from the community! Whether it's fixing a bug, improving documentation, or suggesting a new feature, your input helps make this project better. If you are interested in this line of research, please consider joining our open-source financial AI research community [Tauric Research](https://tauric.ai/).\n\n## Citation\n\nPlease reference our work if you find *TradingAgents* provides you with some help :)\n\n```\n@misc{xiao2025tradingagentsmultiagentsllmfinancial,\n title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, \n author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang},\n year={2025},\n eprint={2412.20138},\n archivePrefix={arXiv},\n primaryClass={q-fin.TR},\n url={https://arxiv.org/abs/2412.20138}, \n}\n```\n"}, "e994e56c23889f4e223659c2d0017f8d1714597d": {"t": 1785766225.1904638, "n": 8736, "h": "11ab460f40aa22fc", "c": "\n \n
\n\n\n\n---\n\n# TradingAgents: Multi-Agents LLM Financial Trading Framework \n\n> 🎉 **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.\n>\n> So we decided to fully open-source the framework. Looking forward to building impactful projects with you!\n\n\n\n🚀 [TradingAgents](#tradingagents-framework) | ⚡ [Installation & CLI](#installation-and-cli) | 🎬 [Demo](https://www.youtube.com/watch?v=90gr5lwjIho) | 📦 [Package Usage](#tradingagents-package) | 🤝 [Contributing](#contributing) | 📄 [Citation](#citation)\n\n
\n\n## TradingAgents Framework\n\nTradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively evaluates market conditions and informs trading decisions. Moreover, these agents engage in dynamic discussions to pinpoint the optimal strategy.\n\n\n \n
\n\n> TradingAgents framework is designed for research purposes. Trading performance may vary based on many factors, including the chosen backbone language models, model temperature, trading periods, the quality of data, and other non-deterministic factors. [It is not intended as financial, investment, or trading advice.](https://tauric.ai/disclaimer/)\n\nOur framework decomposes complex trading tasks into specialized roles. This ensures the system achieves a robust, scalable approach to market analysis and decision-making.\n\n### Analyst Team\n- Fundamentals Analyst: Evaluates company financials and performance metrics, identifying intrinsic values and potential red flags.\n- Sentiment Analyst: Analyzes social media and public sentiment using sentiment scoring algorithms to gauge short-term market mood.\n- News Analyst: Monitors global news and macroeconomic indicators, interpreting the impact of events on market conditions.\n- Technical Analyst: Utilizes technical indicators (like MACD and RSI) to detect trading patterns and forecast price movements.\n\n\n \n
\n\n### Researcher Team\n- Comprises both bullish and bearish researchers who critically assess the insights provided by the Analyst Team. Through structured debates, they balance potential gains against inherent risks.\n\n\n \n
\n\n### Trader Agent\n- Composes reports from the analysts and researchers to make informed trading decisions. It determines the timing and magnitude of trades based on comprehensive market insights.\n\n\n \n
\n\n### Risk Management and Portfolio Manager\n- Continuously evaluates portfolio risk by assessing market volatility, liquidity, and other risk factors. The risk management team evaluates and adjusts trading strategies, providing assessment reports to the Portfolio Manager for final decision.\n- The Portfolio Manager approves/rejects the transaction proposal. If approved, the order will be sent to the simulated exchange and executed.\n\n\n \n
\n\n## Installation and CLI\n\n### Installation\n\nClone TradingAgents:\n```bash\ngit clone https://github.com/TauricResearch/TradingAgents.git\ncd TradingAgents\n```\n\nCreate a virtual environment in any of your favorite environment managers:\n```bash\nconda create -n tradingagents python=3.13\nconda activate tradingagents\n```\n\nInstall dependencies:\n```bash\npip install -r requirements.txt\n```\n\n### Required APIs\n\nYou will also need the FinnHub API for financial data. All of our code is implemented with the free tier.\n```bash\nexport FINNHUB_API_KEY=$YOUR_FINNHUB_API_KEY\n```\n\nYou will need the OpenAI API for all the agents.\n```bash\nexport OPENAI_API_KEY=$YOUR_OPENAI_API_KEY\n```\n\n### CLI Usage\n\nYou can also try out the CLI directly by running:\n```bash\npython -m cli.main\n```\nYou will see a screen where you can select your desired tickers, date, LLMs, research depth, etc.\n\n\n \n
\n\nAn interface will appear showing results as they load, letting you track the agent's progress as it runs.\n\n\n \n
\n\n\n \n
\n\n## TradingAgents Package\n\n### Implementation Details\n\nWe built TradingAgents with LangGraph to ensure flexibility and modularity. We utilize `o1-preview` and `gpt-4o` as our deep thinking and fast thinking LLMs for our experiments. However, for testing purposes, we recommend you use `o4-mini` and `gpt-4.1-mini` to save on costs as our framework makes **lots of** API calls.\n\n### Python Usage\n\nTo use TradingAgents inside your code, you can import the `tradingagents` module and initialize a `TradingAgentsGraph()` object. The `.propagate()` function will return a decision. You can run `main.py`, here's also a quick example:\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\n\nta = TradingAgentsGraph(debug=True, config=config)\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\nYou can also adjust the default configuration to set your own choice of LLMs, debate rounds, etc.\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\n# Create a custom config\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"deep_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"quick_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"max_debate_rounds\"] = 1 # Increase debate rounds\nconfig[\"online_tools\"] = True # Use online tools or cached data\n\n# Initialize with custom config\nta = TradingAgentsGraph(debug=True, config=config)\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\n> For `online_tools`, we recommend enabling them for experimentation, as they provide access to real-time data. The agents' offline tools rely on cached data from our **Tauric TradingDB**, a curated dataset we use for backtesting. We're currently in the process of refining this dataset, and we plan to release it soon alongside our upcoming projects. Stay tuned!\n\nYou can view the full list of configurations in `tradingagents/default_config.py`.\n\n## Contributing\n\nWe welcome contributions from the community! Whether it's fixing a bug, improving documentation, or suggesting a new feature, your input helps make this project better. If you are interested in this line of research, please consider joining our open-source financial AI research community [Tauric Research](https://tauric.ai/).\n\n## Citation\n\nPlease reference our work if you find *TradingAgents* provides you with some help :)\n\n```\n@misc{xiao2025tradingagentsmultiagentsllmfinancial,\n title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, \n author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang},\n year={2025},\n eprint={2412.20138},\n archivePrefix={arXiv},\n primaryClass={q-fin.TR},\n url={https://arxiv.org/abs/2412.20138}, \n}\n```\n"}, "cc97cb6d5deb10eac370db0c6678e2796a62eba8": {"t": 1785766226.7445476, "n": 8750, "h": "9929c3e5a61c8710", "c": "\n \n
\n\n\n\n---\n\n# TradingAgents: Multi-Agents LLM Financial Trading Framework \n\n> 🎉 **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.\n>\n> So we decided to fully open-source the framework. Looking forward to building impactful projects with you!\n\n\n\n🚀 [TradingAgents](#tradingagents-framework) | ⚡ [Installation & CLI](#installation-and-cli) | 🎬 [Demo](https://www.youtube.com/watch?v=90gr5lwjIho) | 📦 [Package Usage](#tradingagents-package) | 🤝 [Contributing](#contributing) | 📄 [Citation](#citation)\n\n
\n\n## TradingAgents Framework\n\nTradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively evaluates market conditions and informs trading decisions. Moreover, these agents engage in dynamic discussions to pinpoint the optimal strategy.\n\n\n \n
\n\n> TradingAgents framework is designed for research purposes. Trading performance may vary based on many factors, including the chosen backbone language models, model temperature, trading periods, the quality of data, and other non-deterministic factors. [It is not intended as financial, investment, or trading advice.](https://tauric.ai/disclaimer/)\n\nOur framework decomposes complex trading tasks into specialized roles. This ensures the system achieves a robust, scalable approach to market analysis and decision-making.\n\n### Analyst Team\n- Fundamentals Analyst: Evaluates company financials and performance metrics, identifying intrinsic values and potential red flags.\n- Sentiment Analyst: Analyzes social media and public sentiment using sentiment scoring algorithms to gauge short-term market mood.\n- News Analyst: Monitors global news and macroeconomic indicators, interpreting the impact of events on market conditions.\n- Technical Analyst: Utilizes technical indicators (like MACD and RSI) to detect trading patterns and forecast price movements.\n\n\n \n
\n\n### Researcher Team\n- Comprises both bullish and bearish researchers who critically assess the insights provided by the Analyst Team. Through structured debates, they balance potential gains against inherent risks.\n\n\n \n
\n\n### Trader Agent\n- Composes reports from the analysts and researchers to make informed trading decisions. It determines the timing and magnitude of trades based on comprehensive market insights.\n\n\n \n
\n\n### Risk Management and Portfolio Manager\n- Continuously evaluates portfolio risk by assessing market volatility, liquidity, and other risk factors. The risk management team evaluates and adjusts trading strategies, providing assessment reports to the Portfolio Manager for final decision.\n- The Portfolio Manager approves/rejects the transaction proposal. If approved, the order will be sent to the simulated exchange and executed.\n\n\n \n
\n\n## Installation and CLI\n\n### Installation\n\nClone TradingAgents:\n```bash\ngit clone https://github.com/TauricResearch/TradingAgents.git\ncd TradingAgents\n```\n\nCreate a virtual environment in any of your favorite environment managers:\n```bash\nconda create -n tradingagents python=3.13\nconda activate tradingagents\n```\n\nInstall dependencies:\n```bash\npip install -r requirements.txt\n```\n\n### Required APIs\n\nYou will also need the FinnHub API and EODHD API for financial data. All of our code is implemented with the free tier.\n```bash\nexport FINNHUB_API_KEY=$YOUR_FINNHUB_API_KEY\n```\n\nYou will need the OpenAI API for all the agents.\n```bash\nexport OPENAI_API_KEY=$YOUR_OPENAI_API_KEY\n```\n\n### CLI Usage\n\nYou can also try out the CLI directly by running:\n```bash\npython -m cli.main\n```\nYou will see a screen where you can select your desired tickers, date, LLMs, research depth, etc.\n\n\n \n
\n\nAn interface will appear showing results as they load, letting you track the agent's progress as it runs.\n\n\n \n
\n\n\n \n
\n\n## TradingAgents Package\n\n### Implementation Details\n\nWe built TradingAgents with LangGraph to ensure flexibility and modularity. We utilize `o1-preview` and `gpt-4o` as our deep thinking and fast thinking LLMs for our experiments. However, for testing purposes, we recommend you use `o4-mini` and `gpt-4.1-mini` to save on costs as our framework makes **lots of** API calls.\n\n### Python Usage\n\nTo use TradingAgents inside your code, you can import the `tradingagents` module and initialize a `TradingAgentsGraph()` object. The `.propagate()` function will return a decision. You can run `main.py`, here's also a quick example:\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\n\nta = TradingAgentsGraph(debug=True, config=config)\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\nYou can also adjust the default configuration to set your own choice of LLMs, debate rounds, etc.\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\n# Create a custom config\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"deep_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"quick_think_llm\"] = \"gpt-4.1-nano\" # Use a different model\nconfig[\"max_debate_rounds\"] = 1 # Increase debate rounds\nconfig[\"online_tools\"] = True # Use online tools or cached data\n\n# Initialize with custom config\nta = TradingAgentsGraph(debug=True, config=config)\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2024-05-10\")\nprint(decision)\n```\n\n> For `online_tools`, we recommend enabling them for experimentation, as they provide access to real-time data. The agents' offline tools rely on cached data from our **Tauric TradingDB**, a curated dataset we use for backtesting. We're currently in the process of refining this dataset, and we plan to release it soon alongside our upcoming projects. Stay tuned!\n\nYou can view the full list of configurations in `tradingagents/default_config.py`.\n\n## Contributing\n\nWe welcome contributions from the community! Whether it's fixing a bug, improving documentation, or suggesting a new feature, your input helps make this project better. If you are interested in this line of research, please consider joining our open-source financial AI research community [Tauric Research](https://tauric.ai/).\n\n## Citation\n\nPlease reference our work if you find *TradingAgents* provides you with some help :)\n\n```\n@misc{xiao2025tradingagentsmultiagentsllmfinancial,\n title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, \n author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang},\n year={2025},\n eprint={2412.20138},\n archivePrefix={arXiv},\n primaryClass={q-fin.TR},\n url={https://arxiv.org/abs/2412.20138}, \n}\n```\n"}}, ".env.example": {"289ac184bee091ce7e80fbb89aeaaf856b21f2cd": {"t": 1786067294.62697, "n": 473, "h": "fccd38f804ea1854", "c": "# LLM Providers (set the one you use)\nOPENAI_API_KEY=\nGOOGLE_API_KEY=\nANTHROPIC_API_KEY=\nXAI_API_KEY=\nDEEPSEEK_API_KEY=\nDASHSCOPE_API_KEY=\nZHIPU_API_KEY=\nOPENROUTER_API_KEY=\n\n# Search backends for News/Sentiment/Fundamental analysts (auto-fallback chain)\n# Priority: Tavily > Anthropic web_search > Claude CLI > Gemini CLI\n# Tavily: free 1000 searches/month at https://tavily.com (recommended)\nTAVILY_API_KEY=\n# Optional: Alpha Vantage news fallback\nALPHA_VANTAGE_API_KEY=\n"}}}}![\"arXiv\"](\"https://img.shields.io/badge/arXiv-2412.20138-B31B1B?logo=arxiv\"/){kind=icon}
\n ![\"Discord\"](\"https://img.shields.io/badge/Discord-TradingResearch-7289da?logo=discord&logoColor=white&color=7289da\"/){kind=icon}
\n ![\"WeChat\"](\"./assets/wechat.png\")
\n ![\"X](\"https://img.shields.io/badge/X-TauricResearch-white?logo=x&logoColor=white\"/){kind=icon}
\n ![\"Community\"](\"https://img.shields.io/badge/Join_GitHub_Community-TauricResearch-14C290?logo=discourse\"/){kind=icon}
\n