# AI use cases for Trading Agents (TauricResearch/TradingAgents) Repo: [TauricResearch/TradingAgents](https://github.com/TauricResearch/TradingAgents) | Use cases: 3 | Page: https://dedupedai.com/use-cases/tauricresearch-tradingagents/ TradingAgents is an open-source multi-agent trading research framework that mirrors a trading firm. LLM agents play fundamentals, sentiment, news and technical analysts, bullish and bearish researchers who debate, a trader, a risk management team and a portfolio manager who approves or rejects each proposal, which then runs on a simulated exchange. The README says it is built for research and is not financial, investment or trading advice. Not financial advice: paper trade first, and remember you can lose money. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Run a multi-agent research debate on one stock: https://dedupedai.com/use-cases/tauricresearch-tradingagents/run-a-multi-agent-analysis-of-one-stock/ - Run Trading Agents on local models with Ollama: https://dedupedai.com/use-cases/tauricresearch-tradingagents/run-tradingagents-on-local-models-with-ollama/ - Run Trading Agents on your ChatGPT Plus or Pro plan: https://dedupedai.com/use-cases/tauricresearch-tradingagents/run-tradingagents-on-your-chatgpt-plan/ ## How to run a multi-agent research debate on one stock with Trading Agents Repo: [TauricResearch/TradingAgents](https://github.com/TauricResearch/TradingAgents) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Pick a ticker and date in the CLI and watch analysts, researchers, a trader and a risk team argue before a decision. **Who it is for:** A developer or student who wants to see how LLM agents weigh fundamentals, news, sentiment and technicals for one stock. **The problem:** One chatbot answer about a stock hides its reasoning and never argues with itself. **The outcome:** A saved report with each analyst's findings, the bull and bear debate, the trader's proposal and the portfolio manager's approve or reject call. ### Steps 1. Clone the repo, create a Python 3.11 or later environment and run `pip install .` 2. Run `cp .env.example .env` and add the API key for your chosen LLM provider 3. Launch the interactive CLI with `tradingagents` 4. Select your tickers, analysis date, LLM provider and research depth on the setup screen 5. Read the analyst reports, the researcher debate and the final decision; reports are saved as one HTML page ### Prompt to paste into your agent ```text Install TauricResearch/TradingAgents, run the tradingagents CLI for on with , and give me the final decision plus the two strongest bull and bear arguments from the debate. Confirm the run only used data available on that date. ``` ### Caveat Results vary with the model, temperature, period and data quality, and orders only go to a simulated exchange. Not financial advice: paper trade first, and remember you can lose money. Risk, credentials: You store LLM and data API keys in .env, so keep that file out of version control. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/tauricresearch-tradingagents/run-a-multi-agent-analysis-of-one-stock/ ## How to run Trading Agents on local models with Ollama with Trading Agents Repo: [TauricResearch/TradingAgents](https://github.com/TauricResearch/TradingAgents) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Use the Docker Ollama profile or any OpenAI-compatible local server so no API key is needed. **Who it is for:** A tinkerer who wants to experiment with many runs without paying per token or sending prompts to a cloud provider. **The problem:** A multi-agent debate makes many model calls, which adds up fast on a paid API. **The outcome:** Trading Agents running end to end against local models on your own machine. ### Steps 1. Run `cp .env.example .env` in the cloned repo 2. Start the Ollama setup with `docker compose --profile ollama run --rm tradingagents-ollama` 3. Or without Docker, set `llm_provider: "ollama"` and point `OLLAMA_BASE_URL` at a remote ollama-serve if needed 4. For vLLM, LM Studio or llama.cpp, set `llm_provider: "openai_compatible"` and the endpoint in backend_url 5. Pick Custom model ID in the CLI for any model not listed by default ### Prompt to paste into your agent ```text Set up TauricResearch/TradingAgents to use through Ollama (or an OpenAI-compatible server at ), run one analysis of , and tell me how long it took and whether any agent step failed. ``` ### Caveat Small local models may reason worse than the hosted ones the project defaults to, so compare before trusting any output. Not financial advice: paper trade first, and remember you can lose money. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/tauricresearch-tradingagents/run-tradingagents-on-local-models-with-ollama/ ## How to run Trading Agents on your ChatGPT Plus or Pro plan with Trading Agents Repo: [TauricResearch/TradingAgents](https://github.com/TauricResearch/TradingAgents) | Difficulty: Beginner | Time: 20 minutes | Basis: From the README Sign in once with your ChatGPT plan instead of paying for a separate API key. **Who it is for:** Someone who already pays for ChatGPT Plus or Pro and wants to try the framework without new API billing. **The problem:** Setting up and funding a new API account is a hurdle just to try a research tool. **The outcome:** Trading Agents runs that count toward your ChatGPT plan's usage limits. ### Steps 1. Install the package with `pip install .` in the cloned repo 2. Sign in with `tradingagents login chatgpt` and open the address it prints in your browser 3. In the CLI provider menu choose Subscription, or set `llm_provider: "chatgpt"` 4. Run an analysis as usual; revoke access later with `tradingagents logout chatgpt` ### Prompt to paste into your agent ```text Configure TauricResearch/TradingAgents to use my ChatGPT plan with tradingagents login chatgpt, run one analysis of on , and tell me where the sign-in file is stored so I can revoke it later. ``` ### Caveat Runs use your plan's limits and the plan ignores temperature and max_tokens settings. Not financial advice: paper trade first, and remember you can lose money. Risk, credentials: The sign-in is kept in ~/.tradingagents/chatgpt-auth.json, so treat that file like a password and log out on shared machines. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/tauricresearch-tradingagents/run-tradingagents-on-your-chatgpt-plan/