hsliuping/TradingAgents-CN

基于多智能体LLM的中文金融交易框架 - TradingAgents中文增强版

What it solves

TradingAgents-CN is a multi-agent stock analysis platform designed for Chinese users. It solves the problem of conducting systematic, AI-driven stock research and strategy experimentation without providing real-time trading instructions, focusing instead on educational and research purposes.

How it works

The platform utilizes a multi-agent framework to simulate professional analysts. It integrates multiple LLM providers (including native OpenAI, Google AI, and VolcEngine Ark) and synchronizes data from sources like Tushare, AkShare, and BaoStock. The system uses a FastAPI backend and a Vue 3 frontend to provide a web-based interface for managing configurations, tracking analysis progress in real-time, and exporting professional reports in Markdown, Word, or PDF formats.

Who it’s for

It is intended for researchers, students, and individuals interested in learning how to use multi-agent AI frameworks for compliant stock market analysis across A-shares, Hong Kong stocks, and US stocks.

Highlights

  • Multi-LLM Integration: Supports a wide range of providers including domestic Chinese LLMs and reasoning models with optimized reasoning_effort passing.
  • Chinese Market Support: Full support for A-shares and localized Chinese interfaces.
  • Enterprise-grade Infrastructure: Features a MongoDB and Redis dual-database architecture, user permission management, and Docker multi-architecture support (amd64 and arm64).
  • Advanced Analysis Tools: Includes intelligent news analysis, multi-level news filtering, a simulated trading system for strategy validation, and a stock screening system based on multi-dimensional indicators.

Related

  • Project
    oficcejo/aiagents-stock

    An AI-powered multi-agent stock analysis system that simulates a professional analyst team to provide technical, fundamental, and capital-flow insights for global markets.

  • Project
    KylinMountain/TradingAgents-AShare

    A multi-agent AI system that simulates a professional investment research institution to provide deep analysis and trading suggestions for the A-share market.

  • Project
    x-pai/AlphaBot

    An AI-powered stock analysis assistant that combines LLMs, machine learning, and real-time market data to help traders make data-driven investment decisions.

  • Project
    TauricResearch/TradingAgents

    A multi-agent LLM framework that simulates a professional trading firm, using specialized agents for analysis, research, and risk management to inform financial trading decisions.

  • Project
    simonlin1212/TradingAgents-astock

    TradingAgents‑Astock is an Apache‑2.0, pip‑installable fork of the TradingAgents research framework, re‑engineered for China’s A‑share market. It adds three new analyst roles (policy, hot‑money, lockup), uses free Chinese data sources (mootdx, East‑money, Sina, etc.), and enforces A‑share trading rules (T+1, price limits, lot sizes). The pipeline runs 7 analysts → bull/bear debate → research manager → trader → risk debate → portfolio manager, with two tiers of LLMs (quick and deep). Users configure any LLM provider (MiniMax, DeepSeek, OpenAI, Anthropic, etc.) via a .env file, then run analyses via a CLI or a Streamlit UI, receiving Chinese markdown/PDF reports and optional performance statistics. It is a research/teaching tool, not an investment advisory or back‑testing system.