1. Starting the Container Set the image 1 export IMAGE=nousresearch/hermes-agent:v2026.6.5 Set directory permissions 1 2 mkdir -p hermes-agent-home chmod -R 777 hermes-agent-home Set environment variables 1 2 3 cat <<EOF > hermes-agent-home/.env GATEWAY_ALLOW_ALL_USERS=true EOF Start hermes-agent 1 2 3 4 5 6 7 8 9 10 nerdctl run -d \

1. Start the Container Set the image 1 export IMAGE=ghcr.io/openclaw/openclaw:2026.3.2 Generate a random token 1 openssl rand -hex 32 Set the gateway token 1 export OPENCLAW_GATEWAY_TOKEN=xxx This token is used for authentication on both the remote web UI and the local TUI. Set directory permissions 1 2 mkdir -p openclaw-home

1. Deployment Plan Before starting the containerized deployment, a few requirements: To simplify delivery, only one image is needed For reliability, deploy as many replicas as possible Start different services through different parameters Inject configuration through environment variables and render it into configuration files Below is the deployment plan for DeepSeek 3FS:

1. What the Image Tag Suffixes Mean base/cuda: includes the CUDA runtime runtime: builds on base, adding the CUDA math libraries and the NCCL and cuDNN runtimes devel: builds on runtime, adding headers and the development tools used to build CUDA images; particularly useful for multi-stage builds cuddn: builds on the above, adding the cuDNN neural network acceleration library

Statistics show that most files inside a container are never used. Based on this characteristic, Nydus defines a custom filesystem in the Rafs format, enabling on-demand loading of image files to solve the slow startup and storage consumption caused by large images. In AI scenarios, whether for inference or training, images often start at several GB, or even tens of GB, so Nydus is very well suited.