Lobster Trap: OpenClaw in Containers from Local to K8s and Back
summary
Demo shows a reproducible pipeline: one container image runs locally with Podman and on Kubernetes by flipping a flag, you spin up a sub agent in two seconds with a Podman command, secrets use Podman secrets + OpenClaw secret refs, volumes provide backup and PVC parity, and an Nvidia team runs ten OpenClaws in Kubernetes doing model evals that used to take six people. Tools: Podman, Kubernetes, OpenClaw, volumes, secret refs.
AI-written summary · about
chapters (15)
- 0:00Introduction and background on Sally Ann O'Malley
- 1:25Discovering and experimenting with OpenClaw
- 2:35Benefits of running AI agents in containers
- 3:05Introducing Forever Claw and sub-agents
- 5:52Using containers for agent configuration and tools
- 6:21Managing secrets with Podman and Kubernetes
- 8:10Scaling agent workloads with Kubernetes
- 9:15Nvidia team case study: Model evaluations
- 11:09Backup, recovery, and persistence with volumes
- 11:47Vision for workplace agent standardization
- 14:14Local demo: Running OpenClaw with Podman
- 16:45Choosing providers and configuring settings
- 17:50SSH sandbox features
- 18:22Running the Podman command and checking agent status
- 20:52Transitioning agent workloads to Kubernetes and OpenShift
related talks
53mFinding, Building, Sharing & Deploying Containers
34mHibernate and Evolving: Taming OpenClaw With OpenKruise Agents
15mPuppet and containers: A multi-tenancy deployment
47mContainerizing your Security Operations Center
16mFrom Podman to Prod: Building Trusted Container Images with Konflux on OpenShift
30mBreaking Barriers: Bringing Application Developers Closer To the CNCF
03h 31mAll Things Containers - Docker, Kubernetes, Helm, Istio, GitOps and more
23mThe Claw: Minions of Toil
