Kagent

Kagent is an open-source programming framework and Kubernetes-native platform for building, running and managing AI agents. Instead of requiring bespoke infrastructure, the framework turns agents into standard Kubernetes custom resource definitions (CRDs) that teams can deploy, scale and secure using their existing GitOps pipelines. This allows teams proficient in Kubernetes to build custom agents without needing to learn a new operational model. Kagent provides a built-in runtime with OpenTelemetry, secure sandboxing, memory support and native Model Context Protocol (MCP) integrations to easily connect agents with external tools and model providers.

We've moved Kagent into Trial after successfully using it to support production environments. At a recent client, we transitioned a multi-agent support bot to Kagent from a previous tool that restricted connections to a single MCP server and required hosting on a personal account. Because the client's team was already familiar with Kubernetes, the migration was simple. The resulting deployment features an orchestrator and multiple specialist agents that use Kagent's built-in Agent-to-Agent (A2A) Protocol to communicate, helping developers debug incidents and solve general questions directly within team channels.

Kagent es un framework de código abierto para ejecutar inteligencia artificial basada en agentes dentro de clústeres de Kubernetes. Permite que los agentes basados en LLMs planifiquen y ejecuten tareas operativas como diagnosticar problemas, corregir configuraciones o interactuar con herramientas de observabilidad mediante APIs nativas de Kubernetes e integraciones con Model Context Protocol (MCP). Su objetivo es llevar el concepto de “AgentOps” a la infraestructura cloud-native, combinando la gestión declarativa con el razonamiento autónomo. Como proyecto del CNCF Sandbox, Kagent debe implementarse con precaución, especialmente por los riesgos asociados a otorgar capacidades de gestión operativa a los LLM. Técnicas como el análisis de flujo tóxico pueden ser especialmente útiles para evaluar y mitigar estos riesgos.