Skip to main content

TradingAgents: Multi-agent LLM trading framework

A multi-agent framework where analyst agents debate and reach trading decisions, run on simulated money.

What TradingAgents does

TradingAgents simulates a trading firm with LLM agents. Analysts research fundamentals, sentiment and technicals, researchers debate the case, and a trader agent makes the call with risk checks along the way. It's built for research and simulated trading.

Why it matters for marketing

The useful part for marketing is the architecture: specialist agents with different roles debating before a decision. The same pattern works for campaign planning, creative review or budget allocation.

How to use TradingAgents

  • Study multi-agent debate as a decision pattern
  • Prototype role-based agent teams for planning
  • Paper trade to explore how agents reason

What to watch out for

  • Simulated results don't carry over to real markets
  • You'd be competing against professional trading desks with far better tools

TradingAgents FAQ

What is TradingAgents?

TradingAgents simulates a trading firm with LLM agents. Analysts research fundamentals, sentiment and technicals, researchers debate the case, and a trader agent makes the call with risk checks along the way. It's built for research and simulated trading.

What is TradingAgents used for?

Study multi-agent debate as a decision pattern. Prototype role-based agent teams for planning. Paper trade to explore how agents reason.

Is TradingAgents free and open source?

Yes. The code is public on GitHub at TauricResearch/TradingAgents under the Apache-2.0 license.

Who makes TradingAgents?

TradingAgents is published on GitHub by TauricResearch. It is written mainly in Python.

What tools are similar to TradingAgents?

Other repos in the Research and data category include Sherlock, Daily Stock Analysis, Auto Ontology.

More in Research and data

More AI repos to explore

  • Marketing Skills

    60.7k stars

    50+ agent skills for CRO, copy, SEO, analytics and growth

    Corey Haines's library of marketing skills for coding agents, covering conversion optimization, copywriting, SEO, AI search, analytics, pricing, launches and more. The most complete marketing skill pack on GitHub.

    NewUpdated this weekEditor's pick ·
    Read the review →
  • Maker Skills

    917 stars

    Agent skills for founders and solo operators

    25 skills for the operator side of running a business: decisions, deep research, second brain, content rotation, scenario modeling, finance cadence and slide decks.

    NewUpdated this weekEditor's pick ·
    Read the review →
  • Open-source forms scored on revenue, not submissions

    A form builder that judges forms and split tests by closed pipeline instead of completion rate, and tags every submission as human, agent or unverified.

    NewUpdated this weekEditor's pick ·
    Read the review →