ai-agent

TradingAgents‑AShare: Multi‑Agent AI for Real‑Time Stock Research

Simulate 15 AI agents collaborating and debating market moves, with full visual workflow and Docker one‑click setup—ideal for founders building AI‑driven finance tools.

From the repo · “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。”

875 stars+15★ this week242 forksPythonGuide quality 8/10 · reviewed Oct 11Updated 10/21/2026100% free · open source
What it does

TradingAgents-AShare is an AI-powered trading research system that simulates the collaboration and debate of 15 AI agents to provide intelligent investment insights

When to use it
  • •When you need to analyze and visualize the behavior of multiple AI agents in a trading scenario
  • •When you want to integrate AI-powered trading research with existing systems using OpenClaw or Claude Code
  • •When you need a scalable and deployable solution for trading research using Docker
Ready-to-paste prompt
docker run -it --rm -v $(pwd):/app kylinmountain/tradingagents-ashare:latest python app.py --mode train --agent-count 15 --episode-count 100
Heads up: Make sure you have Docker installed and configured on your system, as TradingAgents-AShare relies on Docker for deployment and runtime
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/tradingagents-ashare && curl -fsSL https://workflowstacks.com/api/skills/tradingagents-ashare/claude-skill -o ~/.claude/skills/tradingagents-ashare/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How TradingAgents‑AShare: Multi‑Agent AI for Real‑Time Stock Research works
Codeflow
Free to inspect

TradingAgents‑AShare: Multi‑Agent AI for Real‑Time Stock Research is a large Python project (~35k lines across 145 code files, plus 27 test files). Setup is light: installs like a normal app — add your API keys. Reading the code is optional. Last commit this month, Other license, has a test suite.

Size
Large codebase
~35k lines · 145 code files · ~5 h to skim
Setup
One-command install
Installs like a normal app — add your API keys. Reading the code is optional.
Runs on
Python · Docker
Needs API keys (.env)
Python 63%TypeScript 35%JavaScript 1%CSS 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    api/main.py
    Where the program starts running
  3. 3
    pyproject.toml
    Dependencies and the commands it exposes
  4. 4
    .env.example
    The API keys and settings you must provide
  5. 5
    skills/tradingagents-analysis/SKILL.md
    Inside skills/ — an example of what the AI is told to do
What's in each folder
skills/Prompts, skills & agent definitions2 files
frontend/Frontend / UI70 files
api/Backend / API22 files
guide/Documentation3 files
tradingagents/Folder71 files
scheduler/Folder2 files
tests/Tests — proof it works27 files
assets/Images & static assets14 files
READMEHas testsDocumentedCI checksDocker readyOther licenseUpdated this month
Quick Actions
Details
Creator
KylinMountain
Language
Python
Category
ai-agent
Published
3/2/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/tradingagents-ashare.svg)](https://workflowstacks.com/skills/tradingagents-ashare?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.