automation

WyckoffTradingAgent: Automate Trading

Name: WyckoffTradingAgent: Automate Trading
Author: YoungCan-Wang

Founder's AI trading agent for volume-price analysis and A-share screening. Use WyckoffTradingAgent for efficient trading workflows.

From the repo · “Open-source Wyckoff trading agent and AI stock screener for volume-price analysis, A-share screening, CLI workflows, and MCP tools.灵感来自秋生trader @Hoyooyoo”

754 stars+6★ this week215 forksPythonGuide quality 8/10 · reviewed Jul 4Updated 10/21/2026100% free · open source

What it does

WyckoffTradingAgent is an AI-powered trading agent that analyzes volume and price data for A-share screening and automates trading workflows using Python

When to use it

•You need to screen a large number of A-shares based on volume and price analysis
•You want to automate your trading workflow using a rule-based approach
•You are looking for a customizable and open-source trading agent

Ready-to-paste prompt

python cli.py --screen --volume=100000 --price=10.0

Heads up: Make sure you have Python 3.8 or later installed, as the tool is not compatible with earlier versions

Saves to your device

Use with Claude

New

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

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/wyckofftradingagent && curl -fsSL https://workflowstacks.com/api/skills/wyckofftradingagent/claude-skill -o ~/.claude/skills/wyckofftradingagent/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 WyckoffTradingAgent: Automate Trading works

Codeflow

Free to inspect

WyckoffTradingAgent: Automate Trading is a very large Python project (~205k lines across 843 code files, plus 552 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, AGPL-3.0 license, has a test suite.

Size

Very large codebase

~205k lines · 843 code files · days to read — use, don't read

Setup

Developer setup

A real software project. Use it via its install path; don't expect to read it all.

Runs on

Python

Needs API keys (.env)

Python 80%TypeScript 15%JavaScript 4%CSS 1%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
AGENTS.md
The instructions the AI actually follows
3
cli/__main__.py
Where the program starts running
4
pyproject.toml
Dependencies and the commands it exposes
5
.env.example
The API keys and settings you must provide

What's in each folder

core/Core code — the actual logic120 files

agents/Prompts, skills & agent definitions24 files

web/Frontend / UI269 files

workflows/Workflows / pipelines136 files

cli/Command-line entry points85 files

integrations/Sub-packages / plugins63 files

docs/Documentation26 files

desktop/Folder126 files

READMEHas testsDocumentedCI checksAGPL-3.0 licenseUpdated this month