ai-agent

FinRL‑Trading: Build AI‑driven trading strategies fast

Name: FinRL‑Trading: Build AI‑driven trading strategies fast
Author: AI4Finance-Foundation

FinRL‑Trading lets founders prototype and deploy reinforcement‑learning stock‑trading bots in Python, ideal for quant‑focused startups. 3.8k+ GitHub stars.

From the repo · “FinRL-X: An AI-Native Modular Infrastructure for Quantitative Trading”

3,846 stars+27★ this week1,123 forksPythonGuide quality 9/10 · reviewed Oct 7Updated 9/18/2026100% free · open source

What it does

FinRL-Trading is an AI-native modular infrastructure for quantitative trading that allows users to develop, test, and deploy trading strategies using deep reinforcement learning and other machine learning techniques.

When to use it

•You need to automate trading decisions based on complex market data analysis.
•You want to develop and test custom trading strategies using machine learning algorithms.
•You require a scalable and modular infrastructure for backtesting and deploying trading models.

Ready-to-paste prompt

python train.py --env DowJones --agent sac --net_dim 64 --batch_size 32 --episode_length 10

Heads up: Make sure you have the required dependencies installed, including `stable-baselines3` and `pandas`, and that your Python version is compatible with the FinRL-Trading library (Python 3.7 or later).

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/finrl-trading && curl -fsSL https://workflowstacks.com/api/skills/finrl-trading/claude-skill -o ~/.claude/skills/finrl-trading/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 FinRL‑Trading: Build AI‑driven trading strategies fast works

Codeflow

Free to inspect

FinRL‑Trading: Build AI‑driven trading strategies fast is a large Python project (~23k lines across 53 code files). Setup is light: runs with Docker — add your API keys to .env. Last commit this month, Apache-2.0 license, no tests found.

Size

Large codebase

~23k lines · 53 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 98%Shell 2%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
src/main.py
Where the program starts running
3
requirements.txt
Dependencies and the commands it exposes
4
.env.example
The API keys and settings you must provide
5
src/__init__.py
Inside src/ — the main logic begins here

What's in each folder

src/Core code — the actual logic53 files

examples/Examples you can copy7 files

docs/Documentation1 files

figs/Folder5 files

data/Data files3 files

READMENo tests foundDocumentedNo CIDocker readyExamples includedApache-2.0 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/finrl-trading && curl -fsSL https://workflowstacks.com/api/skills/finrl-trading/claude-skill -o ~/.claude/skills/finrl-trading/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

AI4Finance-Foundation

Language

Python