Home / LLM agents & research
KylinMountain/TradingAgents-AShare
Multi-agent LLM research system for China A-shares
What it is
A multi-agent research system for China's A-share market built on the TradingAgents architecture. Fifteen AI agents play the roles of institutional analysts, collaborate and debate each other, and the whole research flow is visualised; it also integrates with OpenClaw and Claude Code and ships with a Docker setup. Developers and individual investors who want LLM help with A-share research are the target users. The focus is mainland China equities, and the project is documented mainly in Chinese.
At a glance
Worth watchingOur rating, based on popularity, maintenance and how ready it is for real use.
| Best for | Professional quants |
|---|---|
| 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 | Last commit 6 days ago |
GitHub stars, last 30 days
Daily snapshots since 2026-09-28 (up to 30 days): +34 over the period, now 879. Gaps mean no snapshot was taken that day.
A 股多智能体智能投研系统 — 基于 TradingAgents 架构，15 名 AI Agent 模拟机构协作与实时辩论对抗，全流程可视化，支持 OpenClaw / Claude Code 集成，Docker 一键部署。
Similar tools
LLM multi-agent investment research framework specialized for A-shares
LLM trading research agent with multi-market backtesting
Multi-agent LLM research assistant for Chinese A-shares
Open-source LLM harness for agentic trading
Multi-agent stock analysis system using MCP tools
Multi-agent LLM system for trading research