ai-agent

AgentQuant: Build Code‑Free, AI‑Driven Trading Strategies Fast

Name: AgentQuant: Build Code‑Free, AI‑Driven Trading Strategies Fast
Author: OnePunchMonk

Turn any stock list into a fully backtested, quantitative trading model without writing code. Ideal for founders launching fintech or data‑driven products.

From the repo · “Autonomous quantitative trading research platform that transforms stock lists into fully backtested strategies using AI agents, real market data, and mathematical formulations, all without requiring any coding.”

217 stars+3★ this week47 forksPythonGuide quality 9/10 · reviewed Oct 10Updated 10/21/2026100% free · open source

What it does

AgentQuant transforms stock lists into fully backtested quantitative trading strategies using AI agents, real market data, and mathematical formulations without requiring any coding.

When to use it

•You have a list of stocks you want to evaluate for potential trading opportunities.
•You need to backtest trading strategies without extensive coding knowledge.
•You want to leverage AI and machine learning in your trading research.

Ready-to-paste prompt

python main.py --stock_list=my_stocks.csv --agent_type=mlp --start_date=2020-01-01 --end_date=2022-12-31

Heads up: Ensure you have Python installed and properly configured on your system, as AgentQuant relies on it to run, and be aware that accessing real-time market data may require API keys or subscriptions from financial data providers.

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/agentquant && curl -fsSL https://workflowstacks.com/api/skills/agentquant/claude-skill -o ~/.claude/skills/agentquant/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 AgentQuant: Build Code‑Free, AI‑Driven Trading Strategies Fast works

Codeflow

Free to inspect

AgentQuant: Build Code‑Free, AI‑Driven Trading Strategies Fast is a large Python project (~19k lines across 108 code files, plus 33 test files). Setup is light: runs with Docker — add your API keys to .env. Last commit this month, MIT license, has a test suite.

Size

Large codebase

~19k lines · 108 code files · ~3 h to skim

Setup

Light setup

Runs with Docker — add your API keys to .env.

Runs on

Python · Docker

Needs API keys (.env)

Python 99%Jupyter Notebook 1%

Where to start reading

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

What's in each folder

src/Core code — the actual logic86 files

docs/Documentation10 files

scripts/Helper scripts15 files

experiments/Research & notebooks14 files

screenshots/Folder8 files

results/Folder7 files

data_store/Folder6 files

harnesskit_spec/Folder2 files

READMEHas testsDocumentedCI checksDocker readyMIT licenseUpdated this month

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/agentquant && curl -fsSL https://workflowstacks.com/api/skills/agentquant/claude-skill -o ~/.claude/skills/agentquant/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.

Quick Actions

Details

Creator

OnePunchMonk

Language

Python

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.

Outcome guide

Score your leads by ideal-customer fit

You describe your ideal customer once and keep leads in a Google Sheet. The workflow scores each 1–5 for fit with a one-line reason, so you sort and work the best first.