RL Swarm is a fully open-source framework developed by GensynAI for building reinforcement learning (RL) training swarms over the internet. This guide walks you through setting up an RL Swarm node and a web UI dashboard to monitor swarm activity.
- CPU: Minimum 16GB RAM (more RAM recommended for larger models or datasets).
OR
- GPU (Optional): Supported CUDA devices for enhanced performance:
- RTX 3090
- RTX 4090
- A100
- H100
- Note: You can run the node without a GPU using CPU-only mode.
1. Update System Packages
sudo apt-get update && sudo apt-get upgrade -y2. Install General Utilities and Tools
sudo apt install screen curl iptables build-essential git wget lz4 jq make gcc nano automake autoconf tmux htop nvme-cli libgbm1 pkg-config libssl-dev libleveldb-dev tar clang bsdmainutils ncdu unzip libleveldb-dev -y3. Install Docker
# Remove old Docker installations
for pkg in docker.io docker-doc docker-compose podman-docker containerd runc; do sudo apt-get remove $pkg; done
# Add Docker repository
sudo apt-get update
sudo apt-get install ca-certificates curl gnupg
sudo install -m 0755 -d /etc/apt/keyrings
curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo gpg --dearmor -o /etc/apt/keyrings/docker.gpg
sudo chmod a+r /etc/apt/keyrings/docker.gpg
echo \
"deb [arch="$(dpkg --print-architecture)" signed-by=/etc/apt/keyrings/docker.gpg] https://download.docker.com/linux/ubuntu \
"$(. /etc/os-release && echo "$VERSION_CODENAME")" stable" | \
sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
# Install Docker
sudo apt-get update
sudo apt-get install docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin
# Test Docker
sudo docker run hello-world- Tip: To run Docker without sudo, add your user to the Docker group:
sudo usermod -aG docker $USER4. Install Python
sudo apt-get install python3 python3-pip python3-venv python3-dev -y5. Install Node
sudo apt-get update
curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash -
sudo apt-get install -y nodejs
node -v
sudo npm install -g yarnyarn -v6. Install Yarn
curl -o- -L https://yarnpkg.com/install.sh | bashexport PATH="$HOME/.yarn/bin:$HOME/.config/yarn/global/node_modules/.bin:$PATH"source ~/.bashrc1- Create account in HuggingFace
2- Create an Access Token with Write permissions here and save it
git clone https://github.com/gensyn-ai/rl-swarm/
cd rl-swarmOpen a screen to run it in background
screen -S swarmInstall swarm
python3 -m venv .venv
source .venv/bin/activate
./run_rl_swarm.shPress Y
1- You have to receive Waiting for userData.json to be created... in logs
2- Open login page in browser
- Local PC:
http://localhost:3000/ - VPS:
http://ServerIP:3000/
3-
- In windows start menu, Search Powershell and open its terminal in your local PC
- Enter the command below in your local terminal and replace your vps ip with
Server_IPand your vps port(.eg 22) withSSH_PORT
ssh -L 3000:localhost:3000 root@Server_IP -p SSH_PORT
- This prompts you to enter your VPS password, when you enter it, you connect and tunnel to your vps
- Now go to browser and open
http://localhost:3000/and login
4- Login with your preferred method
- After login, your terminal starts the installation.
5- Push models to huggingface
- Enter your HuggingFace access token you've created when it is prompted
1- Node name
- Now your node started runnin
6657
g, Find your name after word
Hello, like mine iswhistling hulking armadilloas in the image below (You can useCTRL+SHIFT+Fto search Hello in terminal)
2- Node .pem file
- Save
swarm.pemfile in this directory:/root/rl-swarm/
- Minimize:
CTRL+A+D - Return:
screen -r swarm - Stop and Kill:
screen -XS swarm quit
cd $HOME cd rl-swarmdocker compose up -d --buildOpen the dashboard in browser via:
- Local PC:
0.0.0.0:8080 - VPS:
ServerIP:8080
- Official dashboard: https://dashboard.gensyn.ai/
You can search your Node name in the dashboard after a while when you have done your first training completed
- To install the node on Hyperbolic check this Guide: Rent & Connect to GPU
- Add this flag:
-L 3000:localhost:3000in front of your Hyperbolic'sSSH-command, this will allow you to access to login page via local system.