kubernetes-error-message-translation
Translates cryptic Kubernetes error messages and pod failure logs into human-readable explanations with root cause analysis. Uses LLM intelligence to interpret kubectl output and cluster events that would normally require deep Kubernetes expertise to understand.
automated-cluster-issue-diagnosis
Automatically scans Kubernetes cluster for common misconfigurations, resource issues, and operational problems without manual investigation. Identifies pod crashes, resource constraints, networking issues, and other cluster health problems.
cluster-event-interpretation
Interprets Kubernetes cluster events and warnings to provide context and actionable insights. Translates technical event messages into understandable explanations of what happened and why.
sre-operational-insights
Provides SRE-focused insights and recommendations for operational improvements, reliability patterns, and incident prevention. Analyzes cluster state to suggest operational best practices.
kubernetes-security-vulnerability-scanning
Scans Kubernetes cluster configurations for security misconfigurations, policy violations, and vulnerabilities. Identifies issues like missing RBAC policies, insecure pod security contexts, exposed secrets, and other security risks.
kubectl-workflow-integration
Integrates directly with kubectl command-line workflows, allowing users to invoke K8sGPT diagnostics without leaving their terminal or changing their existing Kubernetes management practices.
multi-llm-backend-support
Supports multiple LLM backends including OpenAI, Azure OpenAI, and local models, allowing users to choose their preferred AI provider without vendor lock-in. Users can switch between providers based on cost, privacy, or performance requirements.
pod-failure-root-cause-analysis
Analyzes pod failures and crashes to identify root causes, examining logs, events, and cluster state to determine why pods are not running successfully. Provides specific remediation steps for common failure patterns.
+4 more capabilities