References: The capstone

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)

The commands and outputs shown in this lesson are representative of the
framework at the pinned snapshot above, used 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 to read it: open the link below in your browser and read the files like ordinary web pages. To run it yourself (optional) you do need Python and your own AI provider key.

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

What the capstone runs

At the pinned snapshot:

• cli/main.py: the command-line entry point (the tradingagents command) that runs the interactive questionnaire and the live status board.
• tradingagents/graph/setup.py: the graph that wires the agents into the pipeline you watched run.
• tradingagents/graph/signal_processing.py: the final step that turns the decision into one of the five written stances (Buy, Overweight, Hold, Underweight, Sell).
• The run writes its seven reports to a folder under your home directory, one markdown file per stage.

Try it in a browser instead (optional)

• tradingagentslab.ai: a free desktop application that lets you watch a multi-agent run in a polished interface. Honest caveat (from the lesson): the desktop app uses a deliberately simplified engine for cost and user experience, while this capstone runs the real open-source library you studied. Both are for education and research only.

Read this next

• TradingAgents repository (TauricResearch). The full source, at the pinned snapshot.
• TradingAgents paper (arXiv:2412.20138) by Yijia Xiao, Edward Sun, Di Luo, and Wei Wang. The framework’s own description of its design.

Adjacent topics

Where this sits inside this track.

• Memory and reflection. The previous lesson: the last piece of the architecture before you run the whole thing.
• Why split one AI into many. Lesson 1: the opening idea, worth rereading now that you have seen the whole system run.