TradingAgents
FrameworkTauricResearch/TradingAgents
Multi-agent LLM framework for financial trading.
Overview
TradingAgents is a multi-agent trading framework that mirrors real-world trading firms. It deploys specialized LLM-powered agents (analysts, researchers, trader, risk management) to collaboratively evaluate markets and make trading decisions. The framework supports multiple LLM providers and is designed for research.
README Preview
\n \n\n\n\n \n \n \n \n \n \n\n\n\n \n Deutsch | \n Español | \n français | \n 日本語 | \n 한국어 | \n Português | \n Русский | \n 中文\n\n\n---\n\n# TradingAgents: Multi-Agents LLM Financial Trading Framework\n\n## News\n- [2026-04] **TradingAgents v0.2.4** released with structured-output agents (Research Manager, Trader, Portfolio Manager), LangGraph checkpoint resume, persistent decision log, DeepSeek/Qwen/GLM/Azure provider support, Docker, and a Windows UTF-8 encoding fix. See [CHANGELOG.md](CHANGELOG.md) for the full list.\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 \n \n \n \n \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-po
FAQ (5)
TroubleshootingWhy does TradingAgents fail with 'model not found' for 'glm-4.7-flash-30b:latest'?
The default model name was incorrect; TradingAgents now uses 'glm-4.7-flash:latest'. Update to the latest main branch. As a temporary workaround, create an alias model: ollama create glm-4.7-flash-30b -f Modelfile with FROM glm-4.7-flash:latest in the Modelfile.
TroubleshootingWhy does TradingAgents show alpha vs SPY for non-US stocks like RELIANCE.NS?
This was a known bug where the reflection layer hardcoded SPY as the benchmark. It is fixed in the latest main branch. The framework now auto-selects a regional index based on the ticker’s exchange suffix (e.g., ^NSEI for .NS). You can also manually set benchmark_ticker in the config. Update your installation or pull the latest code to get the fix.
TroubleshootingHow to skip interactive CLI selection steps when environment variables are set?
Set specific TRADINGAGENTS_* environment variables before running the CLI. For example, TRADINGAGENTS_OUTPUT_LANGUAGE skips Step 3 (Output Language), TRADINGAGENTS_LLM_PROVIDER skips Step 6 (LLM Provider), and TRADINGAGENTS_DEEP_THINK_LLM / TRADINGAGENTS_QUICK_THINK_LLM skip Step 7 (Thinking Agents). The values will be used directly. This feature was implemented in commit 2e67782.
TroubleshootingWhy does tradingagents still prompt for LLM provider even though I set custom .env variables?
This was a bug where the CLI did not honor environment variables pointing to an OpenAI-compatible endpoint. Ensure you are on a version that includes the fix (commit 2e67782 or later). Set the required environment variables: TRADINGAGENTS_LLM_PROVIDER=openai, TRADINGAGENTS_LLM_BACKEND_URL=https://opencode.ai/zen/go/v1, TRADINGAGENTS_DEEP_THINK_LLM=<model>, TRADINGAGENTS_QUICK_THINK_LLM=<model>. The provider prompt will then be skipped automatically.
TroubleshootingWhy does TradingAgents show an incorrect gold price for symbol XAUUSD+?
This was a symbol resolution bug fixed in a recent commit (1ff3f07). Update to the latest TradingAgents version. It now properly maps common symbols like XAUUSD+ to Yahoo Finance instruments (GC=F for gold). If issues persist, try using 'GC=F' directly or verify you are on the latest build.