HomeProjectsArticlesPK BoardAbout
Explore Projects

Kubeshark

Active
GitHub Go Apache-2.0

Description

eBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, queryable by AI agents via MCP and humans via dashboard.

Key Features

  • eBPF-based kernel-level network traffic indexing across Kubernetes clusters
  • Automatic TLS/mTLS decryption without key management or sidecars
  • KFL query language combining Kubernetes, API, and network semantics
  • MCP server exposing traffic data to AI agents for natural language queries
  • Retrospective PCAP capture and export for Wireshark analysis
  • AI skills for network root cause analysis and traffic filtering

Use Cases

💡 Kubernetes network troubleshooting with AI-assisted root cause analysis
💡 API debugging by tracing requests across all microservices in a cluster
💡 Security auditing of encrypted traffic without certificate management
💡 Performance monitoring of inter-service communication in production
💡 Incident response automation using AI agents with network context

Strengths & Limitations

✅ Strengths

  • • Actively maintained, recent updates
  • • High community interest (12.0k stars)
  • • Permissive open-source license (Apache-2.0)
  • • Established track record (5 years in production)

Tags

observability devops mcp tools go

Categories

📊 Observability

Quick Start

helm repo add kubeshark https://helm.kubeshark.com && helm install kubeshark kubeshark/kubeshark && kubectl port-forward svc/kubeshark-front 8899:80. Open http://localhost:8899. For AI: brew install kubeshark && claude mcp add kubeshark -- kubeshark mcp
Visit GitHub Visit Website

Related Projects

Entire CLI

4.9k · Go
Active A

CLI that hooks into your Git workflow to capture AI agent sessions as you work — sessions are indexed alongside commits, creating a searchable record of how code was written in your repo.

gocodingagent +2
  • · Git-native integration that automatically captures AI agent sessions tied to commits
  • · Session replay: rewind to any historical agent checkpoint and resume work
  • · Full context preserved: prompts, responses, file changes, token usage all searchable
View on GitHub

ToolHive

2.0k · Go
Active A

An enterprise-grade platform for running and managing MCP servers with containerized deployment, security isolation, network policies, resource limits, and unified management of large-scale MCP server fleets via Kubernetes or Docker.

mcptoolsgo +4
  • · Isolated container-based MCP server execution with per-request identity and access policy enforcement
  • · Modular architecture: Gateway, Registry Server, Runtime, and Portal for enterprise-grade MCP management
  • · Kubernetes operator for fleet management with CRDs, multi-namespace support, and ingress integration
View on GitHub