KubeAstra investigates broken pods, finds the root cause with AI, and recovers your cluster. 32 kubectl tools. One agent. Zero guesswork.
32 kubectl investigation tools orchestrated by AI. From diagnosis to recovery, in seconds instead of minutes.
Pod diagnostics, log analysis, event correlation, node health, resource quotas, network policies, PVC status, and more.
Cross-references logs, events, and resource metrics to pinpoint exactly what went wrong and why. Powered by Google Gemini.
Pod restarts, deployment rollbacks, HPA scaling. Human-in-the-loop approval by default, or fully automated if you choose.
Next.js interface that shows investigations in real time. Watch the agent work, review findings, and approve actions.
Model Context Protocol server exposes all 32 tools to AI-powered editors. Debug clusters from Cursor or VS Code.
Deploy inside your cluster with Helm. Your data never leaves your infrastructure. No SaaS, no callbacks, no telemetry.
From broken pod to root cause in seconds, not minutes.
Point KubeAstra at a failing pod, or let it watch your cluster. It picks up CrashLoopBackOff, OOMKilled, ImagePullBackOff, pending pods, and other failure states.
The agent runs kubectl tools automatically: pod describe, logs (current and previous), events, node status, resource usage, deployment history, network policies, PVC mounts, and more.
AI processes all collected data together, cross-referencing signals across multiple resources to identify the root cause with confidence levels and supporting evidence.
Based on the analysis, KubeAstra recommends and can execute recovery actions: pod restarts, deployment rollbacks, or HPA scaling. Human approval required by default.
Watch KubeAstra investigate a failing pod, find the root cause, and suggest recovery.
KubeAstra is free, open source, and ready to deploy. Star the repo, try it out, or contribute.