kagent-devkagent-devOfficialยท3 Agent Skills Included

kagent

Build, deploy, and manage AI agents natively on Kubernetes

Builds, deploys, and manages AI agents as Kubernetes custom resources using familiar kubectl workflows. Connects agents to multiple LLM providers and MCP tool servers without custom infrastructure code. Provides a web UI, CLI, and OpenTelemetry tracing to monitor and debug agent behavior. Removes the manual work of wiring models, tools, and runtimes into production clusters.
npx skills add kagent-dev/kagent --all -g -y
Available:

Gives the AI agent the repository's architecture rules, component boundaries, testing commands, and change workflow so it can safely modify and extend the kagent codebase.

All Skills in This Repository (3)

Pure Emerald Level Indicators

Frequently Asked Questions

FAQPage Schema
How to install kagent?โ–ผ

Run `npx skills add kagent-dev/kagent --all -g -y` in your terminal to install all skills in this suite globally.

What is kagent used for?โ–ผ

Kagent is a Kubernetes-native framework for building, deploying, and managing AI agents. Agents, models, and tools are defined as Kubernetes custom resources you manage with kubectl.

Which LLM providers does kagent support?โ–ผ

It supports OpenAI, Azure OpenAI, Anthropic, Google Vertex AI, Ollama, and custom providers through AI gateways, configured via the ModelConfig resource.

Can kagent agents use external tools?โ–ผ

Yes. Agents connect to any MCP server, and kagent ships with built-in tools for Kubernetes, Istio, Helm, Argo, Prometheus, Grafana, and Cilium.

How do I monitor kagent agents in production?โ–ผ

Kagent supports OpenTelemetry tracing, so you can observe agent and tool activity with standard monitoring frameworks.

Related Repositories in Software Engineering

View All in Software Engineeringโ†’