Why this exists.
Trading Agents Lab is a carefully built analysis tool, made purely for educational purposes. We do not force user adoption and we do not provide trading tools. We provide a free resource for analysis and learning.
The codebase is a fork of Tauric Research's TradingAgents with substantial extensions for desktop use, cost discipline, paper-trading-only data adapters, and outbound webhooks.
Positioning, analysis, not execution.
If you read one sentence on this page, make it this one:
Trading Agents Lab is an analysis tool, not an execution platform.
The product empowers users with multi-agent LLM analysis to make their own trading decisions. It does not execute trades on a user's behalf, not via paper-trading suites that look like real trading apps, not via a hidden feature flag, not via a future patch.
- No live-trading execution code, ever. Not in the engine, not in the UI, not in distribution builds.
- No full trading suite. No stop-loss management, no sell-order workflow, no order routing.
- Defence in depth via endpoint hard-coding. Where the app connects to Alpaca, it connects only to paper-trading and data endpoints. Live keys for the live endpoint simply have nowhere to go in our code.
- External brokerage via webhooks, on your terms. When a debate finishes, the result can be pushed to your own endpoint, which you wire to your own broker on your own authorised account.
This is a regulatory firewall, not a temporary scope cut. When execution code does not exist in our repository, there is structurally nothing to regulate as a trading platform.
A teaching artifact for Clawdemy.
Trading Agents Lab doubles as a practical case study for Clawdemy.org, a free, open AI-education platform. Students can read the source to learn how to design real multi-agent LLM systems that ship.
That case study is now a full course. Clawdemy's Track 25, Anatomy of an AI Agent Team, is dedicated to the TradingAgents framework this app is built on. Eight lessons walk the system role by role: why one AI becomes many, how an analyst fetches its own data, the bull and the bear, the trader, the risk gate, orchestration, and memory. The capstone puts you inside a real run in Trading Agents Lab itself. If you want to understand what happens under the hood before or after you download, start there.
We optimise for readable code over clever code. Decisions that surprise a reader carry a comment explaining the why, not just the what. The whole system is meant to be understood, forked, and improved on.
If you're a student, researcher, or educator using this as a teaching reference, we'd love to hear from you. File an issue on GitHub and tell us what you're building.
Business model: free, no monetisation.
Free. Open source. AGPL-3.0. No subscription, no paywall, no premium tier, no enterprise upsell.
We collect no personal data because we don't have a business that requires it. The marketing site uses one cookieless visit counter and nothing else; the desktop app has no telemetry, no error-reporting services, no install pings, no accounts, and no email collection. Read the security posture →
If monetisation is ever considered in the future, the change in business model is itself the regulatory inflection point and we will engage securities counsel before shipping anything.
Family.
Trading Agents Lab has sibling products from the same company. See them all on the family page.
The company behind it.
RBJ Global LLC builds a family of independent products, and much of the work is for awareness and education. Trading Agents Lab is part of that: a working multi-agent system that anyone can download, read and learn from.
From the founder.
I learn by examining working systems, and Trading Agents Lab gives others that opportunity. Its agents provide a concrete way to study how multiple AI roles approach research and analysis. Readers can inspect the methods, question the outputs and make their own judgments.
AI is changing many kinds of work. I want people to have open examples that help them understand its strengths and limits. Trading Agents Lab is one way to explore those ideas in a market-research setting. Start small, study what happens, and keep learning.
Junaid (Jay) Siddiqi, Founder, RBJ Global LLC · LinkedIn