K8sGPT vs Rootly

K8sGPT scans Kubernetes clusters with SRE-grade analyzers and explains problems in plain English. It provides a CLI, an in-cluster operator, and an MCP interface for AI assistants. The project lists 23 built-in analyzers and supports custom analyzers over gRPC. Fourteen cloud or local AI backends are listed, including OpenAI, Azure OpenAI, Amazon Bedrock, Google Vertex AI, Ollama, and LocalAI. Documented integrations include Prometheus, Trivy, Kyverno, KEDA, and AWS. Analysis without the explain option can run without an AI backend, while explanations require one. Local or air-gapped operation can use Ollama, LocalAI, or a custom REST backend. Anonymization masks names and identifiers before prompts are sent. Optional operator auto-remediation uses a configurable risk threshold. CLI, Docker, and operator paths require a reachable cluster and kubeconfig; operator installation requires Helm 3.

Rootly is an AI-native incident management platform for engineering teams, combining incident response, on-call scheduling, and AI SRE functions. AI SRE examines alerts and changes to identify probable root causes with evidence, prepare impact analysis, and draft remediation steps and pull requests. Incident Response supports Slack and Microsoft Teams, AI chat, similar-incident suggestions, meeting transcription, playbooks, roles, action items, and reminders. On-Call provides alert grouping and routing, live call routing, schedules, escalation policies, PTO calendars, overrides, and coverage requests. Rootly also offers AI retrospectives, with Smart Default in Essentials and custom processes in Enterprise. Integrations include Anthropic, AWS CloudWatch, Datadog, GitHub, Linear, Notion, Sentry, Slack, Terraform, and Zoom. Security information lists CCPA, GDPR, SOC 2, role-based access controls, private incidents, and real-time audit logging. Plans start at $20/user/mo, with a 14-day trial. It runs on Android, iOS, web, and API.