TradingAgents Agent工作流

Required APIs

TradingAgents supports multiple LLM providers. Set the API key for your chosen provider:

export OPENAI_API_KEY=...          # OpenAI (GPT)
export GOOGLE_API_KEY=...          # Google (Gemini)
export ANTHROPIC_API_KEY=...       # Anthropic (Claude)
export XAI_API_KEY=...             # xAI (Grok)
export DEEPSEEK_API_KEY=...        # DeepSeek
export DASHSCOPE_API_KEY=...       # Qwen — International (dashscope-intl.aliyuncs.com)
export DASHSCOPE_CN_API_KEY=...    # Qwen — China (dashscope.aliyuncs.com)
export ZHIPU_API_KEY=...           # GLM via Z.AI (international)
export ZHIPU_CN_API_KEY=...        # GLM via BigModel (China, open.bigmodel.cn)
export MINIMAX_API_KEY=...         # MiniMax — Global (api.minimax.io)
export MINIMAX_CN_API_KEY=...      # MiniMax — China (api.minimaxi.com)
export OPENROUTER_API_KEY=...      # OpenRouter
export ALPHA_VANTAGE_API_KEY=...   # Alpha Vantage

For Azure OpenAI, copy .env.enterprise.example to .env.enterprise and fill in your credentials.

For AWS Bedrock, install the extra with pip install ".[bedrock]", set llm_provider: "bedrock", configure AWS credentials (environment variables, ~/.aws/credentials, or an IAM role) and AWS_DEFAULT_REGION, and use a Bedrock model ID, e.g. us.anthropic.claude-opus-4-8-v1:0.

For local models, configure Ollama with llm_provider: "ollama". The default endpoint is http://localhost:11434/v1; set OLLAMA_BASE_URL to point at a remote ollama-serve. Pull models with ollama pull <name>, and pick "Custom model ID" in the CLI for any model not listed by default.

For any other OpenAI-compatible server (vLLM, LM Studio, llama.cpp, or a custom relay), use llm_provider: "openai_compatible" and set the endpoint via backend_url (or TRADINGAGENTS_LLM_BACKEND_URL), e.g. http://localhost:8000/v1 for vLLM or http://localhost:1234/v1 for LM Studio. The model is whatever your server serves. No key is needed for local servers; set OPENAI_COMPATIBLE_API_KEY when the endpoint requires one.

Alternatively, copy .env.example to .env and fill in your keys:

cp .env.example .env

Installation and CLI

Installation

Clone TradingAgents:

git clone https://github.com/TauricResearch/TradingAgents.git
cd TradingAgents

Create a virtual environment in any of your favorite environment managers:

conda create -n tradingagents python=3.12
conda activate tradingagents

Install the package and its dependencies:

pip install .

Docker

Alternatively, run with Docker:

cp .env.example .env  # add your API keys
docker compose run --rm tradingagents

For local models with Ollama:

docker compose --profile ollama run --rm tradingagents-ollama

CLI Usage

Launch the interactive CLI:

tradingagents          # installed command
python -m cli.main     # alternative: run directly from source

Python Usage

To 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:

```python from tradingagents.graph.trading_graph import TradingAgentsGraph from tradingagents.default_config import DEFAULT_CONFIG

ta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())

non-reasoning deep/quick model explicitly (e.g. via the Custom model ID option).

```

What does not vary anymore: the analyzed company identity is resolved deterministically from the ticker before any agent runs, and the market analyst grounds exact price and indicator claims in a verified data snapshot. Earlier reports of "different companies" or fabricated price levels across runs are addressed by these two mechanisms.

Backtest results are not guaranteed to match any published figure. Returns depend on the model, the temperature, the date range, data quality, and the sampling above. Treat the framework as a research scaffold for studying multi-agent analysis, not as a strategy with a fixed, replicable return.

TradingAgents Package