# kagent docs

> 

This is the root documentation index. For detailed page listings, follow the section links below.



## kagent


### Introduction
- [Installing kagent](https://kagent.dev/docs/kagent/introduction/installation/): This guide covers ways to install and configure kagent in your Kubernetes environment. For a quick …
- [Introducing kagent](https://kagent.dev/docs/kagent/introduction/what-is-kagent/): kagent is an open-source, Kubernetes-native runtime for AI agents. Deploy, scale, and operate agents …
- [Features](https://kagent.dev/docs/kagent/introduction/features/): Everything works with a single helm install. No add-ons, no extra databases, no waiting for …


### Getting Started
- [Quick Start](https://kagent.dev/docs/kagent/getting-started/quickstart/): This guide will help you get started with kagent, an open-source framework that brings the power of …
- [Creating your first agent](https://kagent.dev/docs/kagent/getting-started/first-agent/): In this guide, you’ll learn how to create your first AI agent using the kagent dashboard. …
- [Adding MCP Tools to Your First kagent Agent](https://kagent.dev/docs/kagent/getting-started/first-mcp-tool/): MCP (Model Context Protocol) tools extend the agent’s abilities by calling external services …
- [Local development with kagent CLI](https://kagent.dev/docs/kagent/getting-started/local-development/): In this guide, you’ll learn how to develop, build and run an AI agent locally using kagent …
- [System Prompts](https://kagent.dev/docs/kagent/getting-started/system-prompts/): Writing good system prompts is one of the most important aspects of building an agent. It’s …


### Core Concepts
- [kagent Architecture](https://kagent.dev/docs/kagent/concepts/architecture/): kagent consists of multiple components running inside and outside of Kubernetes cluster.
kagent …
- [Agents](https://kagent.dev/docs/kagent/concepts/agents/): An AI agent is an application that can interact with users in natural language. Agents use LLMs to …
- [Tools](https://kagent.dev/docs/kagent/concepts/tools/): Tools are functions that the agent can use to interact with its environment. For example, a …
- [Agent Harness](https://kagent.dev/docs/kagent/concepts/agent-harness/): An AgentHarness is a Kubernetes custom resource that asks kagent to provision a long-running remote …
- [Agent Substrate](https://kagent.dev/docs/kagent/concepts/agent-substrate/): Agent Substrate is a Kubernetes-native runtime for running AI agents and other stateful workloads …
- [Agent Memory](https://kagent.dev/docs/kagent/concepts/agent-memory/): With agent memory, your agents can automatically save and retrieve relevant context across …
- [MCP Apps](https://kagent.dev/docs/kagent/concepts/mcp-apps/): MCP Apps are MCP tools that ship an interactive user interface with their results. Instead of …


### Supported Providers
- [Amazon Bedrock](https://kagent.dev/docs/kagent/supported-providers/amazon-bedrock/): You can use Amazon Bedrock models with kagent in two ways: the native Bedrock provider (recommended) …
- [Anthropic](https://kagent.dev/docs/kagent/supported-providers/anthropic/): Configuring Anthropic Create a Kubernetes Secret that stores the API key, replace …
- [Azure OpenAI](https://kagent.dev/docs/kagent/supported-providers/azure-openai/): Configuring Azure OpenAI Create a Kubernetes Secret that stores the API key, replace …
- [Gemini](https://kagent.dev/docs/kagent/supported-providers/gemini/): Gemini is Google’s AI model family that can be accessed directly through the Google AI Studio …
- [Google Vertex AI](https://kagent.dev/docs/kagent/supported-providers/google-vertexai/): Configuring Google Vertex AI Google Vertex AI is supported for Gemini and Anthropic models.
Create …
- [Ollama](https://kagent.dev/docs/kagent/supported-providers/ollama/): Configuring Ollama Ollama allows you to run LLMs locally on your computer or in a Kubernetes …
- [OpenAI](https://kagent.dev/docs/kagent/supported-providers/openai/): Configuring OpenAI Create a Kubernetes Secret that stores the API key, replace <your_api_key> …
- [BYO OpenAI-compatible model](https://kagent.dev/docs/kagent/supported-providers/byo-openai/): You can bring your own model from an OpenAI API-compatible LLM provider. The example integrates with …
- [xAI (Grok)](https://kagent.dev/docs/kagent/supported-providers/xai/): Configuring xAI (Grok) xAI’s Grok models are OpenAI-compatible, so you can use the BYO …
- [SAP AI Core](https://kagent.dev/docs/kagent/supported-providers/sap-ai-core/): Configuring SAP AI Core kagent connects to SAP AI Core through its Orchestration Service, which …


### Examples
- [Exposing agents through A2A protocol](https://kagent.dev/docs/kagent/examples/a2a-agents/): Every AI agent created with kagent implements the A2A protocol and can be invoked by an A2A client. …
- [Using agentgateway with kagent](https://kagent.dev/docs/kagent/examples/agentgateway/): As your kagent deployment grows, you might need governance over how your agents communicate with LLM …
- [Bringing your own ADK agent to kagent](https://kagent.dev/docs/kagent/examples/a2a-byo/): Bring your own custom agents. This example uses the Agent Development Kit (ADK), but you can also …
- [Bringing your own CrewAI agent to kagent](https://kagent.dev/docs/kagent/examples/crewai-byo/): Bring your own custom agents. This example uses CrewAI, but you can also try out the ADK guide or …
- [Bringing your own LangGraph agent to kagent](https://kagent.dev/docs/kagent/examples/langchain-byo/): You can bring your own LangGraph agent to kagent by configuring the kagentCheckpointer in your …
- [Using kagent agents via MCP](https://kagent.dev/docs/kagent/examples/agents-mcp/): kagent exposes all running agents via a Model Context Protocol (MCP) server embedded in the control …
- [Creating an agent leveraging documentation](https://kagent.dev/docs/kagent/examples/documentation/): In this example, we’re going to crawl a documentation website, store the content in a vector …
- [Integrating kagent with Slack](https://kagent.dev/docs/kagent/examples/slack-a2a/): };
kagent enables you to create AI agents that run inside your Kubernetes cluster. They have access …
- [Integrating kagent with Discord](https://kagent.dev/docs/kagent/examples/discord-a2a/): };
kagent enables you to create AI agents that run inside your Kubernetes cluster. They can access a …
- [Talk to Your Kubernetes Cluster from Telegram](https://kagent.dev/docs/kagent/examples/telegram-bot/): What if you could manage your Kubernetes cluster from Telegram? Not through a half-baked webhook …
- [Add skills to agents](https://kagent.dev/docs/kagent/examples/skills/): Skills are descriptions of capabilities that help agents act more autonomously. They guide the …
- [Human-in-the-Loop with kagent](https://kagent.dev/docs/kagent/examples/human-in-the-loop/): AI agents that can take action are powerful — but you don’t always want them acting without …
- [Agent Harness](https://kagent.dev/docs/kagent/examples/agent-harness/): AgentHarness creates a long-running remote execution environment on Agent Substrate. Unlike an Agent …
- [Agent Substrate](https://kagent.dev/docs/kagent/examples/agent-substrate/): In this guide, you install Agent Substrate and kagent on a local kind cluster, then deploy a …


### Observability
- [Audit kagent prompts](https://kagent.dev/docs/kagent/observability/audit-prompts/): Audit all prompts (inputs) and replies (outputs) from your agents.
Such auditing capability can help …
- [Tracing](https://kagent.dev/docs/kagent/observability/tracing/): Set up tracing for your kagent agents.
Before you begin Install kagent.
Install Jaeger Install a …
- [Launch the UI](https://kagent.dev/docs/kagent/observability/launch-ui/): Access the kagent dashboard to manage your agents, tools, and models. You can open the dashboard by …


### Operations
- [Operational considerations](https://kagent.dev/docs/kagent/operations/operational-considerations/): Review the following operational considerations when running kagent in production environments, …
- [Upgrade kagent](https://kagent.dev/docs/kagent/operations/upgrade/): Follow these steps to upgrade kagent to the latest version and keep your cluster up to date with new …
- [Uninstall kagent](https://kagent.dev/docs/kagent/operations/uninstall/): Remove kagent from your Kubernetes cluster using the kagent CLI or Helm.
Warning: Uninstalling …
- [Debug kagent](https://kagent.dev/docs/kagent/operations/debug/): Troubleshoot and debug issues with your kagent installation.
My agent doesn’t seem to be …

- [Resources](https://kagent.dev/docs/kagent/resources/llms.txt)


## kmcp


### Develop MCP servers
- [FastMCP Python](https://kagent.dev/docs/kmcp/develop/fastmcp-python/): FastMCP Python is a lightweight, high-performance Python framework that implements the Model Context …
- [MCP Go](https://kagent.dev/docs/kmcp/develop/mcp-go/): MCP Go uses the native Go SDK to implement the Model Context Protocol (MCP). The framework provides …


### Deploy to Kubernetes
- [Install the kmcp controller](https://kagent.dev/docs/kmcp/deploy/install-controller/): The kmcp controller manages the lifecycle of MCP servers that are defined in an MCPServer custom …
- [Deploy MCP servers](https://kagent.dev/docs/kmcp/deploy/server/): Use the kmcp controller to automatically spin up your MCP server in a Kubernetes environment. …


### Reference
- [API Reference](https://kagent.dev/docs/kmcp/reference/api-ref/): Packages kagent.dev/v1alpha1 kagent.dev/v1alpha1 Package v1alpha1 contains API Schema definitions …
- [kmcp add-tool](https://kagent.dev/docs/kmcp/reference/kmcp-add-tool/): Create a boilerplate for a sample echo tool in the tools directory of your MCP project and update …
- [kmcp build](https://kagent.dev/docs/kmcp/reference/kmcp-build/): Build a Docker image for your MCP server. You can later use this image to deploy your MCP server in …
- [kmcp deploy](https://kagent.dev/docs/kmcp/reference/kmcp-deploy/): Deploy an MCP server to Kubernetes by generating the MCPServer CRDs. The command uses the kmcp.yaml …
- [kmcp init](https://kagent.dev/docs/kmcp/reference/kmcp-init/): Create a scaffold for a new FastMCP or MCP Go server project.
kmcp init [subcommand] [project-name] …
- [kmcp install](https://kagent.dev/docs/kmcp/reference/kmcp-install/): Install the KMCP controller and its required Custom Resource Definitions (CRDs) on a Kubernetes …
- [kmcp run](https://kagent.dev/docs/kmcp/reference/kmcp-run/): Run an MCP server on your local machine by using the Model Context Protocol inspector tool.
Note: If …
- [kmcp secrets](https://kagent.dev/docs/kmcp/reference/kmcp-secrets/): Manage secrets for MCP server projects and apply them to a Kubernetes cluster.
kmcp secrets …
- [kmcp completion](https://kagent.dev/docs/kmcp/reference/kmcp-completion/): Generate the autocompletion script for kmcp for the specified shell. See each sub-command’s …
- [kmcp help](https://kagent.dev/docs/kmcp/reference/kmcp-help/): Help provides help for any command in the kmcp CLI.
kmcp help [command] [flags]

---
Generated on 2026-08-05 20:01:03 UTC
Site: https://kagent.dev