ai-agent

qlib: Accelerate Quant Research with AI‑Powered Modeling

Name: qlib: Accelerate Quant Research with AI‑Powered Modeling
Author: microsoft

Founder‑level quant teams use qlib to prototype, test, and deploy AI‑driven trading models—from supervised learning to RL—in minutes. Backed by 49k+ GitHub stars.

From the repo · “Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, including supervised learning, market dynamics modeling, and RL, and is now equipped with https://github.com/microsoft/RD-Agent to automate R&D process.”

49,590 stars+221★ this week7,828 forksPythonGuide quality 9/10 · reviewed Oct 5Install verified Sep 21Updated 10/14/2026100% free · open source

What it does

Qlib provides a platform for founders in finance and fintech to conduct AI-powered quant research and backtest trading strategies

When to use it

•When you need to backtest a trading strategy before deploying it in a live market
•When you want to analyze and compare the performance of different trading algorithms
•When you need to integrate machine learning models into your quantitative trading workflow

Ready-to-paste prompt

python scripts/backtest.py -c scripts/config_backend.yaml -m LSTM -d btc

Heads up: Qlib requires a specific version of Python (3.7 or later) and may not work correctly with earlier versions, so ensure you have the correct version installed before trying to use it

Saves to your device

Use with Claude

New

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

✅ Light setup✓ Install verified 9/21/2026

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/qlib && curl -fsSL https://workflowstacks.com/api/skills/qlib/claude-skill -o ~/.claude/skills/qlib/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 qlib: Accelerate Quant Research with AI‑Powered Modeling works

Codeflow

Free to inspect

Qlib: Accelerate Quant Research with AI‑Powered Modeling is a very large Python project (~67k lines across 298 code files, plus 40 test files). Setup is light: installs like a normal app. Reading the code is optional. Last commit a month ago, MIT license, has a test suite.

Size

Very large codebase

~67k lines · 298 code files · days to read — use, don't read

Setup

One-command install

Installs like a normal app. Reading the code is optional.

Runs on

Python · Docker

No API keys detected

Python 99%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
pyproject.toml
Dependencies and the commands it exposes
3
qlib/__init__.py
Inside qlib/ — the main logic begins here
4
examples/README.md
A worked example — copy this to get going

What's in each folder

qlib/Core code — the actual logic234 files

examples/Examples you can copy192 files

docs/Documentation77 files

scripts/Helper scripts43 files

tests/Tests — proof it works40 files

.github/CI / automation (GitHub Actions)13 files

READMEHas testsDocumentedCI checksDocker readyExamples includedMIT licenseUpdated this month

Use with Claude

New

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

✅ Light setup✓ Install verified 9/21/2026

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install

Claude Code

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

microsoft

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

Automate your meeting summaries

A private form takes any transcript (from Zoom, Meet, Otter, Fireflies) and emails you back a structured summary: a TL;DR, the decisions made, and action items with owners.