Klaus - Orquestrador de Agentes IA em Kubernetes
giantswarm/klaus
Rode agentes Claude Code em Kubernetes com MCP
Ver no GitHubServidor MCP que encapsula Claude Code para executar agentes de IA coding dentro de Kubernetes com gerenciamento de ciclo de vida, health checks e autenticação OAuth. Expõe ferramentas para prompting, status, parada e resultado de tarefas via HTTP.
Instalação
npx convez-ai giantswarm/klaus1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Orquestração de agentes de coding em ambientes Kubernetes
- Automação de tarefas de desenvolvimento com delegação a subagentes
- Integração de Claude Code com sistemas de infraestrutura existentes
Veredito

Klaus é uma solução enterprise-ready para operacionalizar agentes IA em Kubernetes, com suporte robusto a extensões (skills, subagentes, hooks, MCP servers). Ideal para times que precisam integrar IA generativa em pipelines DevOps com garantias de disponibilidade e controle.
README
A tradução para o português deste README ainda está na fila.
klaus
An MCP server that wraps Claude Code to run AI coding agents inside Kubernetes.
Overview
Klaus runs the Claude Code CLI as a managed subprocess and exposes it over HTTP as a Streamable HTTP MCP endpoint. This allows orchestrating AI coding agents in Kubernetes with proper lifecycle management, health checks, and optional OAuth authentication.
MCP Client --> /mcp --> MCP Server --> Prompter --> Claude Code CLI (subprocess)
MCP Tools
| Tool | Description |
|---|---|
prompt | Send a task to the Claude agent. Non-blocking by default (set blocking=true to wait for completion). |
status | Query agent state, progress, and result. Returns completed with result when a non-blocking task finishes. |
stop | Terminate the running agent |
result | Get full untruncated result and message history from the last run (debugging tool) |
Extension system
Klaus supports the full Claude Code extension surface, configured via Helm values, klausctl config, or operator CRDs:
- Skills -- Domain knowledge loaded as
SKILL.mdfiles - Subagents -- Specialized agents for task delegation
- Hooks -- Lifecycle hooks for validation and automation
- MCP Servers -- External tool integrations
- Plugins -- OCI-distributed extension bundles
Quick start
export ANTHROPIC_API_KEY=sk-ant-...
klaus serve
# MCP endpoint available at http://localhost:8080/mcp
Or with Docker:
docker run -d -p 8080:8080 -e ANTHROPIC_API_KEY=$ANTHROPIC_API_KEY gsoci.azurecr.io/giantswarm/klaus:latest serve
Or deploy to Kubernetes:
helm install klaus helm/klaus/ -n klaus \
--set anthropicApiKey.secretName=anthropic-api-key
Documentation
Full documentation is available in the docs/ directory, organized by the Diataxis framework:
| Section | Purpose |
|---|---|
| Tutorials | Step-by-step guides to get started |
| How-to Guides | Task-oriented guides for specific goals |
| Reference | Technical specifications (env vars, MCP tools, Helm values) |
| Explanation | Architecture, design, and background context |
Development
See docs/development.md for local setup, building, and testing.
Related repositories
| Repository | Description |
|---|---|
| klaus-operator | Kubernetes operator for dynamic instance management |
| klausctl | CLI for managing local klaus containers |