使用 Python、LangGraph 和 Obsidian 构建一个“记忆”AI 交易代理

Source: Dev.to

Hello DEV community!

I’m excited to share an open‑source project I’ve been working on: TradingAgents‑Dashboard. It remembers your insights forever using a local knowledge base (RAG).

Most AI trading bots today are stateless: they run an analysis, give you a result, and then forget everything the moment you close the terminal.

“Wait, didn’t we decide last week that inflation correlates with this stock?”
“Where is that news link I saw yesterday?”

As a developer and trader, I wanted an agent that grows smarter over time, just like a human analyst. I built a dashboard that wraps the TradingAgents framework and adds a persistent memory layer using Obsidian.

GitHub Repo: jiwoomap/TradingAgents‑Dashboard

Overview

• Analyze: Agents (Bull, Bear, Risk Manager) debate market conditions using LangGraph.
• Persist: All insights and debates are auto‑saved to your local Obsidian vault as Markdown files.
• Recall (RAG): Before making a new decision, the agents search your vault (via ChromaDB) to retrieve past lessons and context.

Features

• Interactive Debate UI – Watch the Bull and Bear agents argue in real‑time.
• Fact Checker – Prevents hallucinations by validating news URLs (200 OK checks).
• Dockerized – Get started in 1 minute with docker‑compose up.
• Data Sovereignty – Your financial data and strategies live on your disk, not in a cloud database.

Tech Stack

Getting Started

# Clone the repository
git clone https://github.com/jiwoomap/TradingAgents-Dashboard.git
cd TradingAgents-Dashboard

# Start the application (Docker Compose)
docker compose up

The dashboard will be available at http://localhost:8501 (default Streamlit port).

Feel free to explore, experiment, and provide feedback—especially if you’re interested in AI agents or FinTech!