DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to run Trading Agents on local models with Ollama with Trading Agents

Use the Docker Ollama profile or any OpenAI-compatible local server so no API key is needed.

Short answer: Run cp .env.example .env in the cloned repo; then start the Ollama setup with docker compose --profile ollama run --rm tradingagents-ollama; Or without Docker, set llm_provider: "ollama" and point OLLAMA_BASE_URL at a remote ollama-serve if needed. All steps.

  • Money
  • Intermediate
  • 45 minutes
  • From the README
  • Any agent

Who it is forA tinkerer who wants to experiment with many runs without paying per token or sending prompts to a cloud provider.

The problemA multi-agent debate makes many model calls, which adds up fast on a paid API.

The outcomeTrading Agents running end to end against local models on your own machine.

What you need first

  • Python 3.11 or later, or Docker
  • An API key for one supported LLM provider, a ChatGPT Plus or Pro plan, or local models through Ollama
  • Optional data keys such as Alpha Vantage and FRED (free)

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 for your agent

Set up TauricResearch/TradingAgents to use <local model> through Ollama (or an OpenAI-compatible server at <url>), run one analysis of <ticker>, 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.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for TauricResearch/TradingAgents and "Run Trading Agents on local models with Ollama"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer