#28 · Primary category: Financial Data & Analytics Platforms
TradingAgents-astock
A-share multi-agent investment research framework — 7 AI analysts, bull/bear debate, risk assessment。
Project last updated:08/19/26
GitHub Stars
3.1K
Forks
806
Contributors
9
License
Apache-2.0
Why we included this project
Stock-analysis agents are almost always built around US market assumptions, which leaves anyone working with China's A-shares to adapt them by hand. This fork takes TradingAgents' multi-agent debate setup and reworks it for mainland China: seven analysts argue bull and bear cases and weigh risk, and three of the roles are specific to this market, covering policy, hot-money flows, and share lockups. They pull free Chinese data from mootdx, East Money, Sina, and Tonghuashun instead of Yahoo Finance, and the framework enforces A-share rules like T+1 settlement, daily price limits, lot-size requirements, and ST-flag handling, so the reports reflect how the market actually trades. Output is in Chinese, while internal debate stays in English to keep reasoning quality. It's a research and teaching implementation, not a trading service, and the pip-install setup with zero external service dependencies makes it a practical base for building or studying A-share research pipelines.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
OpenBB
Open Data Platform for analysts, quants and AI agents.
daily_stock_analysis
LLM-powered multi-market stock analysis system with multi-source market data, real-time news, decision dashboard, automated notifications, and cost-free scheduled runs.
ai-hedge-fund
An AI Hedge Fund Team
qlib
AI-oriented quant investment platform supporting diverse ML paradigms and automated R&D for quantitative research and production.
nautilus_trader
Production-grade Rust-native trading engine with deterministic event-driven architecture