workflowstacks
ai-agent

SkyRL: Accelerate LLM Training with a 2.4k‑Star Modular RL Library

SkyRL lets founders plug‑in reinforcement learning to their large language models fast, using a flexible Python stack designed for rapid experimentation.

From the repo · “SkyRL: A Modular Full-stack RL Library for LLMs”

2,443 stars+21★ this week466 forksPythonGuide quality 8/10 · reviewed Oct 10Updated 10/21/2026100% free · open source
What it does

SkyRL allows startup founders to build and deploy full-stack reinforcement learning models with ease, using a modular library designed for large language models

When to use it
  • •You need to train an AI agent to interact with a complex environment
  • •You want to integrate reinforcement learning with your existing large language model
  • •You need a modular and flexible library to build custom RL models
Ready-to-paste prompt
python examples/cartpole.py --policy dqn --episodes 100 --render
Heads up: Make sure you have the `gym` library installed, as it is required by SkyRL for environment simulations, you can install it by running `pip install gym`
Saves to your device
Use with Claude
New

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

✅ Light setup

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/skyrl && curl -fsSL https://workflowstacks.com/api/skills/skyrl/claude-skill -o ~/.claude/skills/skyrl/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 SkyRL: Accelerate LLM Training with a 2.4k‑Star Modular RL Library works
Codeflow
Free to inspect

SkyRL: Accelerate LLM Training with a 2.4k‑Star Modular RL Library is a very large Python project (~167k lines across 717 code files, plus 376 test files). Setup is light: installs like a normal app. Reading the code is optional. Last commit this month, Apache-2.0 license, has a test suite.

Size
Very large codebase
~167k lines · 717 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%Shell 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    pyproject.toml
    Dependencies and the commands it exposes
  4. 4
    skyrl/__init__.py
    Inside skyrl/ — the main logic begins here
  5. 5
    examples/model_checks/README.md
    A worked example — copy this to get going
What's in each folder
skyrl/Core code — the actual logic250 files
integrations/Sub-packages / plugins16 files
examples/Examples you can copy330 files
docs/Documentation134 files
skyrl-agent/Folder123 files
skycap/Folder48 files
skyrl-gym/Folder38 files
ci/Folder26 files
READMEHas testsDocumentedCI checksDocker readyExamples includedApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
NovaSky-AI
Language
Python
Category
ai-agent
Published
4/22/2025

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/skyrl.svg)](https://workflowstacks.com/skills/skyrl?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.

Related skills

More ai-agent tools founders pair with this one.

ai-agent★ 303,577
superpowers
An agentic skills framework & software development methodology that works.
ai-agent★ 277,154
Track GitHub Stars with 996.ICU
Get a popular GitHub star counter for your startup, backed by 276k+ GitHub stars, ideal for founders.
ai-agent★ 253,161
Linux – 251k+ GitHub stars for building custom kernel solutions
Get the complete Linux kernel source in C, perfect for founders needing deep system control or tailored OS components.
ai-agent★ 1,514
kodus-ai: Fast AI Code Reviews with Flexible Model and Cost Control
Boost code quality and stay on budget with kodus-ai’s AI‑driven reviews, letting founders pick any model and set spending limits. Ideal for TypeScript teams seeking smart, affordable code assistance. 1.5k+ GitHub stars.
ai-agent★ 3,370
Build Resilient AI Agents with Langgraphjs
Get a framework for language agents as graphs, ideal for founders building AI-powered tools, backed by 3.0k+ GitHub stars
ai-agent★ 3
googlemapsdelivery: Streamline Delivery Routes with Google Maps
A lightweight JavaScript tool that lets founders plan optimal delivery routes, estimate travel times, and visualize stops directly on Google Maps.