Overview

Omnia

The Kubernetes platform for deploying AI agents

Omnia is a Kubernetes operator that deploys, scales, and manages AI agents as Kubernetes resources. Deploy intelligent assistants that can safely access private, proprietary information — all within your existing infrastructure.

Open core: the core platform is free and open source under Apache 2.0. Advanced production and scale features ship in the Enterprise edition under the Functional Source License in ee/. See Licensing & Features for what’s included in each edition.

Features

• Kubernetes-Native: Deploy AI agents as custom resources with full GitOps support
• Multiple LLM Providers: Support for Claude, OpenAI, and Gemini with per-agent provider selection
• Autoscaling: Scale-to-zero with KEDA or standard HPA based on active connections
• Tool Integration: HTTP, gRPC, and MCP tool adapters for extending agent capabilities
• Session Management: Redis or in-memory session stores for conversation persistence
• Observability: Integrated Prometheus metrics, Grafana dashboards, Loki logs, and Tempo traces
• Production-Ready: Health checks, graceful shutdown, and RBAC

Quick Start

Prerequisites

• Kubernetes 1.28+
• Helm 3.x
• kubectl configured for your cluster

Install the Operator

helm install omnia oci://ghcr.io/altairalabs/charts/omnia \
  --devel \
  --namespace omnia-system \
  --create-namespace \
  --set dashboard.auth.mode=builtin \
  --set dashboard.auth.sessionSecret="$(openssl rand -base64 32)"

--devel is required while Omnia ships pre-release (beta) charts. The dashboard uses builtin auth — after install, open it and register the first user. See Dashboard Auth.

Deploy Your First Agent

1. Create a PromptPack with compiled prompts:

apiVersion: v1
kind: ConfigMap
metadata:
  name: my-prompts
data:
  # Compiled PromptPack JSON (use `packc` to compile from YAML source)
  pack.json: |
    {
      "$schema": "https://promptpack.org/schema/latest/promptpack.schema.json",
      "id": "my-assistant",
      "name": "My Assistant",
      "version": "1.0.0",
      "template_engine": {"version": "v1", "syntax": "{{variable}}"},
      "prompts": {
        "main": {
          "id": "main",
          "name": "Main Assistant",
          "version": "1.0.0",
          "system_template": "You are a helpful AI assistant. Be concise and accurate.",
          "parameters": {"temperature": 0.7, "max_tokens": 4096}
        }
      }
    }
---
apiVersion: omnia.altairalabs.ai/v1alpha1
kind: PromptPack
metadata:
  name: my-pack
spec:
  packName: my-pack
  version: "1.0.0"
  source:
    type: configmap
    configMapRef:
      name: my-prompts

Tip: Use packc to compile PromptPacks from YAML source files with validation.

2. Create a Provider for LLM credentials:

apiVersion: v1
kind: Secret
metadata:
  name: llm-credentials
stringData:
  ANTHROPIC_API_KEY: "sk-ant-..."
---
apiVersion: omnia.altairalabs.ai/v1alpha1
kind: Provider
metadata:
  name: claude-provider
spec:
  type: claude
  model: claude-sonnet-4-20250514
  secretRef:
    name: llm-credentials

3. Deploy an AgentRuntime:

apiVersion: omnia.altairalabs.ai/v1alpha1
kind: AgentRuntime
metadata:
  name: my-agent
spec:
  promptPackRef:
    name: my-pack
  providerRef:
    name: claude-provider
  facades:
    - type: websocket
      port: 8080

4. Connect to your agent:

kubectl port-forward svc/my-agent 8080:8080
websocat ws://localhost:8080/ws

Custom Resources

CRD	Description
AgentRuntime	Deploys and manages an AI agent with its facade, sessions, and scaling
PromptPack	Defines agent prompts and system instructions
ToolRegistry	Configures tools available to agents (HTTP, gRPC, MCP)
Provider	Reusable LLM provider configuration with credentials

Architecture

┌──────────────────────────────────────────────────────────────┐
│                     Omnia Operator                            │
│                                                               │
│  ┌─────────────┐  ┌─────────────┐  ┌─────────────┐           │
│  │ AgentRuntime│  │ PromptPack  │  │ToolRegistry │           │
│  │ Controller  │  │ Controller  │  │ Controller  │           │
│  └──────┬──────┘  └──────┬──────┘  └──────┬──────┘           │
└─────────┼────────────────┼────────────────┼──────────────────┘
          │                │                │
          ▼                ▼                ▼
┌──────────────────────────────────────────────────────────────┐
│                      Agent Pod                                │
│  ┌────────────┐  ┌────────────┐  ┌────────────┐              │
│  │  Facade    │  │  Runtime   │  │   Tools    │              │
│  │ (WebSocket)│◄─┤  (gRPC)    │──┤  Adapter   │              │
│  └────────────┘  └────────────┘  └────────────┘              │
└──────────────────────────────────────────────────────────────┘

Documentation

Full documentation is available at omnia.altairalabs.ai.

• Getting Started
• Local Development
• CRD Reference
• Scaling Agents
• Observability Setup

Ecosystem

Omnia is part of the AltairaLabs open-source ecosystem:

Project	Description
PromptKit	Go SDK for building AI agents with tool use and streaming
PromptPack	Specification for portable, testable AI agent definitions
Omnia	Kubernetes platform for deploying PromptKit agents at scale

Security

To report a vulnerability, see our Security Policy (please use private disclosure — not a public issue).

Vulnerabilities are scanned continuously and triaged in the Security tab: govulncheck (reachability-based Go stdlib + module CVEs, gating CI), Trivy (container images), CodeQL (SAST), Dependabot + dependency-review (dependencies), and OpenSSF Scorecard (supply-chain posture). All service images build statically onto distroless/static:nonroot, keeping the base-layer CVE surface minimal.

Contributing

Contributions are welcome. Please read our Contributing Guide for details.

License

Omnia is open core:

• The core platform is licensed under Apache 2.0 — see LICENSE.
• Enterprise features under ee/ are licensed under the Functional Source License 1.1 (FSL-1.1) — see ee/LICENSE.

See Licensing & Features for the Open Core vs Enterprise comparison.

---

Built with care by AltairaLabs