Skip to content
Clawdemy

References: Why split one AI into many

For education only. Not investment, financial, or trading advice.

Source material

Section titled “Source material”
Primary source (open-source, Apache-2.0):
- TradingAgents, an open-source multi-agent LLM framework
  Authors: Yijia Xiao, Edward Sun, Di Luo, Wei Wang
  Organization: TauricResearch
  Repository: https://github.com/TauricResearch/TradingAgents
  Paper: "TradingAgents: Multi-Agents LLM Financial Trading Framework",
         arXiv:2412.20138 (https://arxiv.org/abs/2412.20138)
  License: Apache-2.0
  Pinned snapshot for this course: 7e9e7b8 (the framework as of 2026-05-01)


This course studies the framework's architecture as a worked example, with
attribution, under the Apache-2.0 license. Clawdemy's lesson prose is original;
we cite and credit the framework as a companion to study, not as our own work.
We teach the architecture only; we make no investment, financial, or trading
claims, and we report no performance results.

How to open it (no account or Git needed)

Section titled “How to open it (no account or Git needed)”

The framework is public and free to read. You do not need a GitHub account, the tool called Git, or any programming knowledge: open the link below in your browser and read the files like ordinary web pages.

Why we pin a snapshot

Section titled “Why we pin a snapshot”

The framework keeps evolving. To keep this course accurate, every lesson is anchored to one frozen snapshot (7e9e7b8). The link above already points to it, so what you read here matches what you see on screen; later changes upstream are the project’s own evolution, not part of what we teach. You do not need to do anything special: just use the link above.

Read this next

Section titled “Read this next”
  • TradingAgents repository (TauricResearch). The full source, at the pinned snapshot. Later lessons walk you to specific parts of it; for now, browsing the folders to get a feel for the project is plenty.
  • TradingAgents paper (arXiv:2412.20138) by Yijia Xiao, Edward Sun, Di Luo, and Wei Wang. The framework’s own description of its multi-agent design. Read it for the architecture and the rationale.

Adjacent topics

Section titled “Adjacent topics”

Where this leads inside this track.

  • How an agent fetches its own data. The next lesson, and the first time we open the project together. The analysts you met here are not handed data; they fetch it themselves with tools, deciding what to pull and when to stop.
  • Multi-agent systems (foundational agent track). The conceptual predecessor: when splitting work across agents helps and when one generalist wins. This track is that question answered by a real system.