What is Orkena

Orkena is a governed agent runtime — the substrate you deploy agents onto when a regulator will eventually ask what the agent did, on what authority, and how you know.

A governed agent runtime executes agent workflows and enforces your controls as part of that execution, rather than reporting on them afterwards. Four properties define it:

1. Authorization before execution. Every action an agent proposes — tool call, model call, credential use, edge traversal — is evaluated against policy-as-code before it reaches a system of record. A denial is a control that fired, not an incident that was noticed.
2. Evidence in the same transaction. The audit record commits atomically with the step that produced it, into an append-only hash-chained ledger with Ed25519-signed anchors. There is no window in which an action exists without its evidence.
3. Deterministic replay. Runs are event-sourced; any run can be replayed byte-for-byte or forked from any checkpoint to interrogate a decision.
4. Evaluation-gated change control. No version reaches production without passing its regression suite. Self-proposed rules stay inert until they pass the same suite and a human declines to veto them.

Who this is for#

Orkena is for platform engineering, compliance, and risk teams at regulated institutions — banks, insurers, healthcare payers, government agencies — that want to put agents into production with an audit posture a supervisor will accept. It is sold on annual platform licences; there is no free tier and no self-serve signup.

Not a dashboard, not a wrapper#

Orkena is not an observability platform (though it emits OpenTelemetry), not a model gateway (it is model-agnostic, bring-your-own-key), and not a compliance dashboard (it produces the evidence; your certifier interprets it). It is the runtime.

If you are new to the category, read What is a Governed Agent Runtime — the essay that defines it.