Runs in your infrastructure.Your data never leaves.

Calling a model is solved. What decides whether an agent reaches production is everything around it — what it remembers, who it may call, what it keeps, what it cost, and whether you can prove it still works. Omnia makes each of those cluster configuration, on the stack you already run.

Free while you build. Free to run. Enterprise features when you need them.

Install it free Core vs Enterprise

DefineGovernProve

# agent.yaml — the agent is a cluster resource
kind: AgentRuntime
metadata:
  name: customer-support-agent
spec:
  promptPackRef:
    name: customer-support
    track: stable
  facades:
    - type: websocket
      port: 8080
  toolRegistryRef:
    name: support-tools

# kubectl get toolpolicy -o yaml
kind: ToolPolicy
spec:
  selector:
    registry: loan-tools
  mode: enforce
  onFailure: deny        # fails closed
  producers:            # CEL computes the facts
    - name: overLimit
      type: cel
      cel: has(body.amount) && double(body.amount) > 10000.0
  policy: |            # Cedar decides on them
    @id("loan-decisions-require-human")
    @message("Loan approval over £10,000 requires a human underwriter")
    forbid (principal, action == Action::"invoke", resource)
    when { context.overLimit };

# evals run on live sessions, not overnight
kind: AgentRuntime
spec:
  evals:
    enabled: true
    inline:                # in the runtime, synchronous
      groups: ["fast-running"]
    worker:                # LLM judges, out of band
      groups: ["long-running"]

policy enforced pre-callconsent honouredevery decision audited

THE HARD PART

Governing what the agent does is the work.

Any platform can call a model. The questions that decide whether an agent reaches production are what it remembers, who it may call, what it keeps, and what it cost — and in Omnia every one of them is cluster configuration you own.

What it remembers — and what it forgets

MemoryPolicy makes retention a cluster resource: TTL, LRU or decay, per tier. Revoke consent and the cascade runs — stop, soft-delete, or hard-delete on a grace clock. PII redaction on write.

Who it may call

ToolPolicy is a Cedar decision on every tool call, evaluated before the tool runs — CEL producers compute the facts, Cedar decides on them, and it is default-deny. It fails closed: if the broker cannot answer, the call does not happen.

What it may keep

SessionPrivacyPolicy decides what a session records and how long it survives. Enforcement is logged to a central audit hub, not left to each service.

Proof it still works

Evals run on live sessions, not overnight — fast checks inline in the runtime, LLM judges out of band, sampled so the expensive ones stay affordable. You learn an agent has drifted from the traffic, not from a nightly report.

What it cost

Every provider call is costed per session and per token, attributed back to the agent and the team that ran it.

No trapdoor

Agents are PromptPacks — an open specification. The pack you run here deploys elsewhere unchanged. Nothing about your agent is native to us.

In detail: who may call what, and how you prove it· what happens to the data· how you know it still works

FIND YOUR PATH

Documentation, four ways.

The Omnia docs follow Diátaxis — tutorials to learn, how-to guides to get things done, reference to look things up, explanation to understand the why.

PRACTICAL STEPSTHEORETICAL KNOWLEDGEWHEN LEARNING

Learning-oriented

Tutorials

From helm install to your first agent answering over a WebSocket — no prior setup assumed.

Understanding-oriented

Explanation

The thinking behind the platform — the why, not the how.

WHEN WORKING

Task-oriented

How-to guides

Focused recipes for the operational jobs you already know you need to do.

Information-oriented

Reference

Every custom resource, field, and option — exact and complete, for looking up.

INSTALL

Two Helm releases into your cluster.

CRDs first, then the operator, both over OCI. Apply an AgentRuntime and your agent reconciles into a running pod — facade, session wiring, and autoscaling. Nothing in here you don't already operate.

Read the quickstart CRD reference

$ helm install omnia-crds oci://ghcr.io/altairalabs/charts/omnia-crds$ helm install omnia oci://ghcr.io/altairalabs/charts/omnia --set dashboard.auth.mode=builtin

apiVersion: omnia.altairalabs.ai/v1alpha1
kind: AgentRuntime
metadata:
  name: checkout-agent
spec:
  promptPackRef: {name: my-pack}
  providers:
    - name: default
      providerRef: {name: claude-provider}
  facades: [{type: websocket, port: 8080}]

requires kubernetes 1.28+ · helm 3.x · free for development · licence for enterprise features in production