References: Orchestration and shared state

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

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)

All code shown in this lesson is quoted from the framework at the pinned
snapshot above, under the Apache-2.0 license, with attribution. Clawdemy's
lesson prose is original. 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)

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.

• github.com/TauricResearch/TradingAgents (pinned snapshot). This link points to one frozen version of the project, marked by the short code 7e9e7b8.

The files this lesson reads

At the pinned snapshot:

• tradingagents/agents/utils/agent_states.py: the shared state, the one structured workspace every agent reads from and writes to.
• tradingagents/graph/setup.py: where the graph is built, one node per agent, with the fixed and conditional arrows wired between them.
• tradingagents/graph/conditional_logic.py: the small decision functions (the “should we continue” checks) that the conditional arrows run.

Read this next

• TradingAgents repository (TauricResearch). The full source, at the pinned snapshot. The files above are the ones this lesson quotes.
• TradingAgents paper (arXiv:2412.20138) by Yijia Xiao, Edward Sun, Di Luo, and Wei Wang. The framework’s own description of its design, including the agent graph.

Adjacent topics

Where this sits inside this track.

• The risk gate. The previous lesson: the last role in the flow, whose handoffs this lesson explains as reads and writes of the shared state.
• Memory and reflection. The next lesson: how the system records its past decisions and learns from how they turned out.
• How an agent fetches its own data. Lesson 2 introduced the analyst’s tool loop; this lesson shows that loop as a conditional edge of the graph.