This skill should be used when configuring agentgateway for AI/LLM provider routing, MCP server routing, external processing, and traffic policies. Use when the user asks to "add an LLM provider backend", "configure MCP routing", "set up Ollama backend", "add OpenAI backend", "configure Anthropic", "add Vertex AI backend", "set up rate limiting", "configure CORS", "add external processing", "upgrade agentgateway", or "troubleshoot AI routing". Supports Ollama, OpenAI, Anthropic, Gemini, Vertex AI, Azure OpenAI, and Bedrock backends.
Expert guidance for agentgateway — the AI/agentic proxy for LLM routing, MCP server routing, and external processing on Kubernetes.
agentgateway is a Linux Foundation project that extends Kubernetes Gateway API for AI workloads. It provides:
Note: Starting v2.3.0, agentgateway diverges from kgateway into its own repo (agentgateway/agentgateway) and namespace (agentgateway-system). See references/helm-lifecycle.md.
This plugin includes slash commands for gateway operations:
| Command | Purpose |
|---|
/gw-status | Show all gateway resources status |
/gw-logs [count|controller] | Tail controller logs for debugging |
/gw-debug | Full diagnostic with events and recommendations |
/gw-backend <provider> | Generate backend YAML (ollama, openai, anthropic, gemini, vertexai, azureopenai, bedrock) |
/gw-eval | Evaluate current config against best practices |
/gw-versions | Compare installed vs latest helm chart versions |
/gw-upgrade [component] | Guide helm chart upgrades with pre/post validation |
The gateway-manager agent handles multi-step workflows: "add an Anthropic backend", "set up Vertex AI routing", "upgrade my gateway", "why isn't my route working".
┌─────────────────────────────────────┐
│ agentgateway proxy │
│ (port 8080 - LoadBalancer) │
└─────────────┬───────────────────────┘
│
┌─────────────────────────┼─────────────────────────┐
/ollama/* /anthropic/* /mcp/*
/openai/* /gemini/*
│ │ │
▼ ▼ ▼
┌───────────────┐ ┌───────────────┐ ┌───────────────┐
│AgentgatewayBackend │AgentgatewayBackend │AgentgatewayBackend
│ (AI type) │ │ (AI type) │ │ (MCP type) │
└───────────────┘ └───────────────┘ └───────────────┘
Configures the agentgateway proxy deployment (logging, resources).
Routes to LLM providers or MCP servers. Two types:
spec.ai.provider with host/port and provider typespec.mcp.targets for MCP server endpointsTraffic policies targeting Gateway or HTTPRoute:
apiVersion: agentgateway.dev/v1alpha1