weibaohui/k8m

一款轻量级、跨平台的 Mini Kubernetes AI Dashboard，支持大模型+智能体+MCP(支持设置操作权限)，集成多集群管理、智能分析、实时异常检测等功能，支持多架构并可单文件部署，助力高效集群管理与运维优化。

What it solves

K8M is a lightweight, AI-powered dashboard designed to simplify the management of Kubernetes clusters. It replaces complex command-line operations with a user-friendly graphical interface and integrates AI to help users understand cluster states, debug logs, and manage resources more efficiently.

How it works

Built with a Golang backend and a frontend based on Baidu AMIS, K8M operates as a single executable file for easy deployment. It uses kom as its Kubernetes API client and can be deployed as a standalone binary, via Docker Compose, or directly within a Kubernetes cluster. The tool integrates LLMs (including built-in Qwen2.5-Coder-7B and support for Ollama or private models) to provide intelligent assistance and implements the Model Context Protocol (MCP) to allow AI models to execute cluster operations via a set of built-in tools.

Who it’s for

It is designed for developers and DevOps engineers who need a simple, efficient way to manage one or multiple Kubernetes clusters (including standard k8s, AWS EKS, k3s, kind, and k0s) without relying solely on the CLI.

Highlights

  • AI-Driven Operations: Provides word-based explanations, YAML attribute translation, AI-powered log diagnosis, and command recommendations.
  • MCP Integration: Acts as an MCP Server with 49 built-in tools, allowing LLMs to perform complex cluster operations while maintaining user-specific permission mapping.
  • Multi-Cluster Management: Automatically detects clusters in-cluster or via kubeconfig, supporting heartbeat detection and automatic reconnection.
  • Comprehensive Resource Control: Includes a Pod file manager (browse, edit, upload/download), real-time log viewing with grep-like search, and CRD management.
  • Cluster Health & Monitoring: Supports scheduled cluster inspections with custom Lua scripts and forwards Kubernetes events to webhooks with AI-generated summaries.
  • Helm Integration: Features a built-in Helm market for one-click installation, uninstallation, and upgrading of applications.

Related

  • Project
    skyhook-io/radar

    Radar is a single‑binary, zero‑install web UI for Kubernetes that runs locally (or via Helm in‑cluster). It provides interactive topology graphs, searchable resource tables, image‑filesystem browsing, timeline events, Helm release management, side‑by‑side resource diffs, and an optional MCP server for AI‑agent integration—all without requiring accounts, agents, or CRDs.

  • Project
    Flux159/mcp-server-kubernetes

    MCP Server Kubernetes is a Node/Bun‑based MCP server that lets AI assistants (Claude, Codex, VS Code extensions, etc.) run kubectl, Helm, port‑forward, node‑maintenance, and diagnostic commands against a Kubernetes cluster. It supports read‑only mode, optional OpenTelemetry tracing, and easy integration via `npx mcp-server-kubernetes`.

  • Project
    k8sgpt-ai/k8sgpt

    k8sgpt is a CLI (and optional operator) that scans Kubernetes clusters, runs built‑in analyzers, and uses LLMs (OpenAI, Azure, Bedrock, etc.) to turn raw diagnostics into plain‑English explanations and remediation advice. It supports multiple back‑ends, anonymizes data, offers an MCP server for tool integration, and can be installed via Homebrew, RPM/DEB, or Windows binaries.

  • Project
    containers/kubernetes-mcp-server

    A native Go implementation of the Model Context Protocol (MCP) server that allows AI agents to directly manage and troubleshoot Kubernetes and OpenShift clusters.

  • Project
    vfarcic/dot-ai

    An npm‑published Node library that adds LLM‑driven assistants to Kubernetes/DevOps workflows. It provides a CLI and a managed platform (MCP) for natural‑language cluster queries, deployment recommendations, automated remediation, policy‑driven prompt libraries, and semantic doc search, all packaged for easy installation on a Kubernetes cluster.