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).
- 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 (details in the docker-compose.yaml section).
1. Update System Packages
sudo apt-get update && sudo apt-get upgrade -y2. Install General Utilities and Tools
sudo apt install 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-pipgit clone https://github.com/gensyn-ai/rl-swarm/
cd rl-swarmThis file defines the services: the RL Swarm node, telemetry collector, and web UI.
- Rename the old file:
mv docker-compose.yaml docker-compose.yaml.old- Create the new file:
nano docker-compose.yaml- Paste the following configuration:
version: '3'
services:
otel-collector:
image: otel/opentelemetry-collector-contrib:0.120.0
ports:
- "4317:4317" # OTLP gRPC
- "4318:4318" # OTLP HTTP
- "55679:55679" # Prometheus metrics (optional)
environment:
- OTEL_LOG_LEVEL=DEBUG
swarm_node:
image: europe-docker.pkg.dev/gensyn-public-b7d9/public/rl-swarm:v0.0.1
command: ./run_hivemind_docker.sh
runtime: nvidia # Enables GPU support; remove if no GPU is available
environment:
- OTEL_EXPORTER_OTLP_ENDPOINT=http://otel-collector:4317
- PEER_MULTI_ADDRS=/ip4/38.101.215.13/tcp/30002/p2p/QmQ2gEXoPJg6iMBSUFWGzAabS2VhnzuS782Y637hGjfsRJ
- HOST_MULTI_ADDRS=/ip4/0.0.0.0/tcp/38331
ports:
- "38331:38331" # Exposes the swarm node's P2P port
depends_on:
- otel-collector
fastapi:
build:
context: .
dockerfile: Dockerfile.webserver
environment:
- OTEL_SERVICE_NAME=rlswarm-fastapi
- OTEL_EXPORTER_OTLP_ENDPOINT=http://otel-collector:4317
- INITIAL_PEERS=/ip4/38.101.215.13/tcp/30002/p2p/QmQ2gEXoPJg6iMBSUFWGzAabS2VhnzuS782Y637hGjfsRJ
ports:
- "8080:8000" # Maps port 8080 on the host to 8000 in the container
depends_on:
- otel-collector
- swarm_node
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:8000/api/healthz"]
interval: 30s
retries: 3- GPU/CPU Note: If you don't have an NVIDIA GPU or the NVIDIA Container Runtime, remove the
runtime: nvidialine underswarm_nodeto run on CPU.
- otel-collector: Gathers telemetry data (metrics, traces).
- swarm_node: The core RL Swarm node connecting to the network.
- fastapi: The web UI dashboard for monitoring.
Start the services with:
docker compose up --build -d && docker compose logs -f- Note: The first run may take time due to image downloads. Look for this log to confirm your node joined the swarm
- Exit Logs: Press
Ctrl+C
- RL Swarm node:
docker-compose logs -f swarm_node- Web UI:
docker-compose logs -f fastapi- Telemetry Collector:
docker-compose logs -f otel-collector- All Logs: Use
docker-compose logs -fwithout a service name.
- VPS:
http://<your-vps-ip>:8080/ - Local PC:
http://localhost:8080orhttp://0.0.0.0:8080
-
The dashboard displays collective swarm data, not individual node stats. To track your node:
1- Check the
swarm_nodelogs for your node’s unique ID (e.g.,[F-d2042cff-01c9-4801-8ea7-1c1afc29c9b6]):
2- Search for this ID in the dashboard data to see your node’s contributions.
- Note: The dashboard monitors all peers together. The node ID in the logs is likely your identifier but I am keep experimenting to find out more about the node metrics!