k8sgpt

Giving Kubernetes Superpowers to everyone

What is k8sgpt?

Giving Kubernetes Superpowers to everyone

Overview of k8sgpt

What it is

k8sgpt is a tool for scanning Kubernetes clusters, diagnosing, and triaging issues in simple English. It has SRE experience codified into its analyzers and helps to pull out the most relevant information to enrich it with AI. It offers out-of-the-box integration with OpenAI, Azure, Cohere, Amazon Bedrock, Google Gemini, and local models.

Key features

  • Scans Kubernetes clusters and diagnoses issues using built-in analyzers (pod, PVC, service, ingress, deployment, etc.)
  • Provides AI-powered explanations for detected issues
  • Supports multiple AI backends: OpenAI, Azure, Cohere, Amazon Bedrock, Google Gemini, and local models
  • Allows filtering by resource type and namespace
  • Can output results in JSON format and anonymize sensitive data
  • Offers an operator mode for continuous cluster monitoring and integration with Prometheus and Alertmanager
  • Includes a Model Context Protocol (MCP) server for integration with tools like Claude Desktop

Use cases

  • Analyzing Kubernetes cluster health and getting detailed insights
  • Receiving recommendations for fixing issues
  • Querying cluster information via natural language (e.g., through Claude Desktop)
  • Filtering analysis by specific resources (e.g., Service, Pod) or namespaces
  • Integrating with existing monitoring stacks for continuous diagnostics

Getting started

Install via Homebrew on Linux/macOS:

brew install k8sgpt

Or download packages for RPM, DEB, APK, or Windows from the releases page.

Quick start:

k8sgpt generate
k8sgpt auth add
k8sgpt analyze --explain
k8sgpt analyze --explain --with-doc

For full instructions, see the repository README.

License and pricing

License: Apache-2.0. The project is open source and free to use.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/k8sgpt-aik8sgpt.svg)](https://yunodb.com/tools/k8sgpt-aik8sgpt?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/k8sgpt-aik8sgpt?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/k8sgpt-aik8sgpt.svg" alt="Featured on YunoDB" height="20"></a>