KAOS — K8s Agent Orchestration System

What does this agent do, and when should you use it?

KAOS (K8s Agent Orchestration System) is a Kubernetes-native framework for deploying and orchestrating AI agents through custom resources: Agent, MCPServer, and ModelAPI. Its core is a Go operator with three controllers — Agent Controller, MCPServer Controller, and ModelAPI Controller — that manage Agent pods, MCP tool pods, and model-serving pods (Ollama/LiteLLM). Agents run on PAIS (Pydantic AI Server), an enterprise wrapper around Pydantic AI that adds an OpenAI-compatible /v1/chat/completions HTTP API, distributed memory, multi-agent delegation, A2A discovery, health probes, and OpenTelemetry instrumentation. Users can install and manage everything through the kaos CLI, deploy the operator directly with Helm, and monitor agents, test chat, and debug memory and tools in a web dashboard. The project is Apache-2.0 licensed and requires Kubernetes >=1.28.

The KAOS operator reconciles three CRDs: ModelAPI (runs model backends like Ollama/LiteLLM in Hosted mode), MCPServer (exposes tools via the Model Context Protocol, definable dynamically with a python-runtime type and tools.fromString embedded Python functions), and Agent (binds a modelAPI and mcpServers, with agentNetwork defining hierarchical multi-agent access). Once applied, each Agent runs as a pod with the PAIS runtime exposing /v1/chat/completions, callable via kubectl port-forward and curl. A coordinator agent can automatically delegate tasks to specialist agents such as researcher or analyst. The kaos CLI provides kaos system install, kaos modelapi deploy, kaos agent deploy, kaos agent invoke, and kaos ui (which opens the web UI and runs kubectl proxy, with optional --monitoring-enabled telemetry). Sample YAML lives in operator/config/samples/.

1. Platform teams that need to deploy, scale, and monitor multiple AI agents as Kubernetes resources
2. Teams building hierarchical multi-agent systems where a coordinator delegates to specialist agents
3. Developers who want to attach custom Python tools to agents via the MCP standard
4. Teams with an existing LLM gateway or Ollama that want agents consumable through an OpenAI-compatible endpoint
5. Operators who need a visual dashboard to monitor agents, test chat, and debug memory and tools
6. CI/CD pipelines running end-to-end tests against a kind cluster

How do you install or deploy this agent?

Option 1: install via the CLI (requires a configured Kubernetes cluster, kubectl, and Helm):

pip install kaos-cli
kaos system install

Option 2: install the operator directly with Helm:

helm repo add kaos https://axsaucedo.github.io/kaos/charts
helm repo update
helm install kaos kaos/kaos-operator -n kaos-system --create-namespace

Running tests in a development environment:

cd python && uv sync && uv run pytest tests/ -v
cd operator && make test
cd operator && make kind-create
cd operator && make kind-e2e-run-tests

How do you use this agent?

Deploy and invoke an agent with the CLI:

kaos modelapi deploy my-api --mode Hosted --model "smollm2:135m"
kaos agent deploy my-agent --modelapi my-api --model "smollm2:135m"
kaos agent invoke my-agent --message "Hello"
kaos ui
kaos ui --monitoring-enabled

Or deploy declaratively with YAML (simple-agent.yaml):

apiVersion: kaos.tools/v1alpha1
kind: ModelAPI
metadata:
  name: ollama
spec:
  mode: Hosted
  hostedConfig:
    model: "smollm2:135m"
---
apiVersion: kaos.tools/v1alpha1
kind: MCPServer
metadata:
  name: echo-tools
spec:
  type: python-runtime
  config:
    tools:
      fromString: |
        def echo(message: str) -> str:
            """Echo back the message."""
            return f"Echo: {message}"
---
apiVersion: kaos.tools/v1alpha1
kind: Agent
metadata:
  name: assistant
spec:
  modelAPI: ollama
  mcpServers:
    - echo-tools
  config:
    description: "AI assistant with echo tools"
    instructions: "You are a helpful assistant."
    env:
      - name: MODEL_NAME
        value: "ollama/smollm2:135m"

kubectl apply -f simple-agent.yaml
kubectl wait --for=condition=ready pod -l agent=assistant --timeout=120s
kubectl port-forward svc/agent-assistant 8000:8000
curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model": "assistant", "messages": [{"role": "user", "content": "Hello!"}]}'

In multi-agent systems, a coordinator agent lists the specialists it can delegate to via agentNetwork.access:

apiVersion: kaos.tools/v1alpha1
kind: Agent
metadata:
  name: coordinator
spec:
  modelAPI: ollama
  config:
    description: "Coordinator that delegates to specialists"
    instructions: "Delegate research to researcher, calculations to analyst."
  agentNetwork:
    access:
      - researcher
      - analyst

Complete multi-agent examples are in operator/config/samples/.

What are this agent's strengths and limitations?

How does this agent compare with similar options?

Key facts side by side with the most closely related agents.

How does FollowAgents rate this agent?

Recent releases

Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.

1. v0.8.5 2026-10-30
   Release notes excerpt

   What's Changed * chore: bump version to 0.8.5-dev by @github-actions[bot] in https://github.com/axsaucedo/kaos/pull/381 * chore(deps): bump the all group across 1 directory with 41 updates by @dependabot[bot] in https://github.com/axsaucedo/kaos/pull/384 * chore(deps-dev): bump brace-expansion from 5.0.8 to 5.0.12 in /kaos-ui in the all-security group across 1 directory by @dependabot[bot] in https://github.com/axsaucedo/kaos/pull/378 * chore(deps): bump the uv group across 3 directories with 2 updates by @dependabot[bot] in https://github.com/axsaucedo/kaos/pull/382 …

   View on GitHub ↗
2. v0.8.4 2026-10-16
   Release notes excerpt

   Overview KAOS v0.8.4 is a dependency-maintenance release. It carries three grouped Dependabot updates — the Go control-plane modules, the Python lock set across all four Python directories, and 36 npm packages in kaos-ui — together with a change to how Dependabot proposes major versions in the first place. There are no changes to KAOS's own runtime code. There are no CRD, API, wire-format or Helm chart changes, and no behavioural changes to the operator, agent runtime, memory service, CLI or UI. Upgrading from v0.8.3 requires no migration. Highlights Control plane …

   View on GitHub ↗
3. v0.8.3 2026-10-10
   Release notes excerpt

   Overview KAOS v0.8.3 is a maintenance release. It carries one grouped Dependabot update of eight npm packages in kaos-ui, all minor or patch, together with a fix to the memory-service test environment in CI. There are no changes to KAOS's own runtime code. There are no CRD, API or wire-format changes, and no behavioural changes to the operator, agent runtime, memory service or CLI. Upgrading from v0.8.2 requires no migration. Highlights UI - One grouped update of eight dependencies, all minor or patch: lucide-react …

   View on GitHub ↗

FAQ