I run a team of AI agents on my Kubernetes cluster
Kubernetes-native orchestration for autonomous agents, but AI agent DevOps is early.
Autonomous agent inside Kubernetes handles code, builds, and ArgoCD deploys directly from GitHub issues.
Platform engineers managing Kubernetes GitOps pipelines
SWE-agent · OpenDevin · Devika
What makes this different from AI coding tools: kube-pilot doesn't just generate code and hand it back to you. It lives inside the cluster with direct access to the entire dev stack — git, Tekton (CI/CD), Kaniko (container builds), ArgoCD (GitOps deployments), kubectl, Vault. Every tool call produces observable state that feeds into the next decision. The cluster isn't just where code runs — it's where the agent thinks.
The safety model: all persistent changes go through git, so everything is auditable and reversible. ArgoCD is the only thing that writes to the cluster. Secrets stay behind Vault — the agent creates ExternalSecret references, never touches raw credentials. Credentials are scrubbed before reaching the LLM.
Live demo: I filed GitHub issues asking it to build a 4-service office suite (auth, docs API, notification worker, API gateway). It built and deployed all of them autonomously. You can see the full agent loop — code, builds, deploys, verification, comments — on the closed issues:
- https://github.com/fbongiovanni29/clouddesk-auth-service/iss... - https://github.com/fbongiovanni29/clouddesk-docs-api/issues/... - https://github.com/fbongiovanni29/clouddesk-notifications-wo... - https://github.com/fbongiovanni29/clouddesk-web-gateway/issu...
One helm install gives you everything — the agent, Gitea (git + registry), Tekton, ArgoCD, Vault, External Secrets. No external dependencies.
Coming next: Slack and Jira integrations (receive tasks and post updates where your team already works), Prometheus metrics and Grafana dashboards for agent observability, and Alertmanager integration so firing alerts automatically become issues that kube-pilot investigates and fixes.
Early proof of concept. Rough edges. But it works.
Kubernetes-native orchestration for autonomous agents, but AI agent DevOps is early.
Actual Kubernetes operator for agent lifecycle, but orchestrating agents is still a niche use case.
Kubernetes CRDs for AI agents, but pre-release status limits production use.
JSON-configured agents with cascading model selection and EU AI Act compliance.
Public live feed of an autonomous Lean 4 proof attempt on Ramsey numbers.
Feature-rich Kite dashboard adds AI agent layer, but Kubernetes dashboards are well-served by Lens, Rancher, Kubeflow.