Home / LLM agents & research
simonlin1212/TradingAgents-astock
LLM multi-agent investment research framework specialized for A-shares
What it is
A multi-agent investment research framework that adapts the open-source TradingAgents architecture to China's A-share market. Seven LLM analyst roles — including A-share-specific policy, hot-money (longhubang), and share-unlock analysts — feed reports into a bull/bear research debate and a risk debate, producing Chinese reports. It pulls data from free sources such as mootdx, Eastmoney, Sina, and Tencent, with no API keys or external services, and enforces A-share rules like T+1, price limits, and lot sizes. It is an Apache 2.0 research and teaching implementation of the TradingAgents paper, not investment advice, and covers only the A-share market.
At a glance
Worth watchingOur rating, based on popularity, maintenance and how ready it is for real use.
| Best for | Developers |
|---|---|
| Used for | Strategy research, AI agents |
| Markets | China A-shares |
| Stack | Python |
| Learning curve | Moderate learning curve |
| Practical value | High practical value |
| Cost | Free and open source |
| Hardware | No GPU needed |
| Maintenance | Commits today |
GitHub stars, last 30 days
Daily snapshots since 2026-09-12 (up to 30 days): +395 over the period, now 3,659. Gaps mean no snapshot was taken that day.
A股多Agent投研框架 — 适配A股数据源(龙虎榜/游资/解禁等)，7位分析师基于A股规则的辩论决策，基于TradingAgents深度改造，适配大A。A-share multi-agent investment research framework — 7 AI analysts, bull/bear debate, risk assessment。