#5454th of 80 in Agent platformsFor finance and business, trading, stocks and crypto, finance and accounting
tradingagents-cn
Multi-agent LLM research assistant for Chinese A-share stocks
- Stars
- 32.9k
- License
- custom license
- Last commit
- Sep 2026
- Language
- Python
23,923 on 20 Apr 202632,883 on 9 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Runs LLM analyst agents (market, sector, fundamentals, news, optimistic and cautious researchers) that debate a stock and produce a research report. It also offers natural-language screening over 6000+ A-shares, a web-search assistant with memory, paper trading and study courses. Backend is FastAPI with a Vue 3 frontend, MongoDB and Redis. Research aid only, not investment advice.
Who it is for: Chinese-reading developers studying multi-agent LLM research on A-shares
Strengths
- Debate-style analysis with five depth levels and distinct analyst and researcher roles
- Natural-language stock screening and paper trading in one app
- Pulls data from public sources: Tushare, AKShare, BaoStock
- Core agent library, CLI and docs are Apache-2.0
Weaknesses
- App and frontend are source-available only: no redistribution or commercial use
- Batch and scheduled analysis, PDF/Word export and custom agents are Pro-only
- MongoDB and Redis must be installed and secured separately; no compose file
- A-share market only; UI and docs are mainly Chinese
What it needs
- no GPU
- Needs MongoDB 7.0+, Redis 6+, Node.js 18+, Python 3.11, Tushare/AKShare/BaoStock data access
- Models: OpenAI, DeepSeek, Qwen
- port 3000
Quick answers
Is tradingagents-cn open source?
Its code is public on GitHub under its own license terms; read them before you use it at work.
Can you run tradingagents-cn with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does tradingagents-cn need a GPU?
No, it runs without one.
Also in Agent platforms
See all 80| Rank | Project | Score |
|---|---|---|
| 1 | AutoGPTRole-based AI agents coordinated by one lead agent, plus a visual workflow builder | 95 out of 100 |
| 2 | daily_stock_analysisLLM-driven daily analysis of watchlist stocks across six markets, pushed to chat apps | 95 out of 100 |
| 3 | LangflowVisual builder for AI agents and workflows, exposed as API or MCP server | 94 out of 100 |
| #4 | deer-flowAgent harness running sub-agents, memory and sandboxes with pluggable skills | 93 out of 100 |
| #5 | DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs | 92 out of 100 |