References: Memory and reflection

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/memory.py: the append-only logbook. It records a decision as a pending entry (no model), and later resolves it with the reflection.
• tradingagents/graph/reflection.py: the reflection step, built with the cheaper model. Given a past decision and its outcome, it writes a few plain sentences of lessons learned.
• tradingagents/graph/trading_graph.py: the loop that ties it together. At the start of a run it resolves earlier pending entries for the same company and injects the past context; at the end it records the new decision.

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.

Adjacent topics

Where this sits inside this track.

• Orchestration and shared state. The previous lesson: the shared state that the memory log is read into and written back from.
• The risk gate. The portfolio manager introduced there is the one agent that reads the accumulated memory when it makes the final call.
• The capstone. The final lesson: run the whole system yourself in a safe simulation, with your own AI provider key.