# KAOS

A Kubernetes-native framework for deploying and orchestrating AI agents as cluster resources, with hierarchical multi-agent delegation and an OpenAI-compatible chat endpoint on every agent.

KAOS lets a developer describe an AI agent and a network of agents as Kubernetes custom resources, deployed and managed with a dedicated CLI or through Helm and kubectl. Every agent exposes an OpenAI-compatible chat completions endpoint, tools are wired in through the Model Context Protocol, and a coordinator agent can delegate parts of a task to specialist agents declared in the same resource, forming a hierarchical multi-agent system.

A visual dashboard, opened with the CLI, lets a developer monitor running agents, test chat interactions, and debug an agent's memory and tool calls; it can also be launched with monitoring enabled for further observability. The project's Kubernetes operator installs through a published Helm repository, and sample multi-agent configurations are provided for reference.

Website: https://axsaucedo.github.io/kaos