automation

rllm

Democratizing Reinforcement Learning for LLMs
5,896 stars+12★ this week634 forksPythonUpdated 10/16/2026100% free · open source
What it does

RLLM enables reinforcement learning for large language models, allowing founders to fine-tune models for specific tasks and improve their performance

When to use it
  • •When you need to adapt a pre-trained language model to a custom task or dataset
  • •When you want to improve the performance of a language model on a specific task or metric
  • •When you need to integrate reinforcement learning with other machine learning workflows
Ready-to-paste prompt
python rllm/train.py --model-name t5-base --task-name sentiment-analysis --num-epochs 5 --batch-size 16
Heads up: Make sure you have the correct version of Python and the required dependencies installed, as specified in the README, and that you have a compatible GPU available for accelerated training
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/rllm && curl -fsSL https://workflowstacks.com/api/skills/rllm/claude-skill -o ~/.claude/skills/rllm/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 rllm works
Codeflow
Free to inspect

Rllm is a very large Python project (~82k lines across 453 code files, plus 121 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, Apache-2.0 license, has a test suite.

Size
Very large codebase
~82k lines · 453 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 · Docker
No API keys detected
Python 72%Jupyter Notebook 26%Shell 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    pyproject.toml
    Dependencies and the commands it exposes
  3. 3
    rllm/__init__.py
    Inside rllm/ — the main logic begins here
  4. 4
    examples/agentcore_math/prepare_gsm8k_data.py
    A worked example — copy this to get going
What's in each folder
rllm/Core code — the actual logic346 files
docs/Documentation90 files
examples/Examples you can copy61 files
cookbooks/Folder105 files
rllm-model-gateway/Folder41 files
scripts/Helper scripts18 files
design/Proposals & design notes1 files
tests/Tests — proof it works94 files
READMEHas testsDocumentedCI checksDocker readyExamples includedApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
rllm-org
Language
Python
Category
automation
Published
1/26/2025

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