Open Control Stack by Cognous | Runtime governance for AI agents
>_ Open _ Control _ Stack
by

Runtime governance
for AI agents.

AI agents have started to act — calling tools, moving data, and changing enterprise systems. Open Control Stack is open infrastructure for governing those actions at runtime. Authorize what an agent may do. Enforce policy before it runs. Turn every run into portable evidence.

Apache 2.0 Vendor-neutral Open specification Reference implementation JSON Schemas Conformance tests
Runtime authorization

Every proposed action is checked against policy and authority before it runs.

Decision recording

Each run is captured as a structured, replayable record of inputs, decisions, and outcomes.

Governance evidence

Records become business-readable proof for security, risk, and audit teams.

Why this exists

AI agents need more than logs.

As AI agents begin using tools and triggering workflows, enterprises need to answer practical questions before and after each run: What was this agent allowed to propose? What did it actually propose? What did policy allow, block, or escalate? What did the agent rely on? Can the run be reconstructed later? Can the evidence be shared with security, risk, compliance, or audit teams?

Traditional logs, dashboards, and policy documents are not enough by themselves. Governed AI-agent deployment requires structured runtime records and portable evidence artifacts.

Why Open Control Stack

Open by design. Neutral by default.

The stack is built to fit into existing systems, not replace them — and to keep governance portable across teams, vendors, and boundaries.

Vendor-neutral

No lock-in to a model, framework, or cloud provider.

Interoperable

Open formats that drop into existing agent stacks.

Extensible

Add tools, policies, and profiles without forking.

Portable

Evidence travels across teams, systems, and boundaries.

Auditable

Every action leaves a structured, reconstructable record.

Governed

Authority and policy are enforced before actions run.

Architecture at a glance

One path from intent to evidence.

Every governed action follows the same runtime path — proposed by the agent, authorized, evaluated against policy, executed, and recorded.

Agent
Proposes an action
Authority
Who authorized it
Policy
Allow, block, escalate
Execution
Acts on the system
Evidence
Recorded and provable
The four-part stack

Declare, control, replay, and evidence AI-agent behavior.

Four open-source reference components, each mapping to one stage of the governed lifecycle — from action inventory to governance review. Use one, or run them in sequence.

1 — Declare
Agent Action Manifest

Declare what an agent may propose.

The manifest declares the agent's intended action surface.

A lightweight manifest format for documenting an agent's tools, action types, authority requirements, review posture, reliance requirements, payload policies, and redaction hints before runtime deployment.

Explore →
2 — Control
Agent Control Plane

Control proposed actions at runtime.

The control plane records and gates proposed actions during runtime.

A minimal runtime control layer that records action proposals, evaluates policy decisions, captures blocked actions, records authority and reliance, and generates replayable run records before agents affect enterprise systems.

Explore →
3 — Replay
Agent Replay Bundle

Package runs for reconstruction.

The replay bundle packages a run into portable technical evidence.

A portable replay-bundle format for capturing the task frame, action proposals, policy decisions, evaluation traces, blocked actions, authority records, reliance records, validation reports, redaction metadata, and signature metadata.

Explore →
4 — Evidence
Agent Governance Evidence Pack

Translate records into governance evidence.

The evidence pack converts technical records into business-facing review material.

A business-facing evidence-pack format for summarizing agent purpose, deployment context, tools, actions, authority model, policy controls, blocked actions, reliance, replay bundles, validation results, redacted exports, risks, and review records.

Explore →
What the stack helps teams answer

Concrete questions, before and after every run.

What actions can this agent propose?
Which tools and systems can it access?
Which actions require authority or human review?
What did the agent propose during a run?
What was allowed, blocked, or escalated?
What sources did the agent rely on?
Can the run be replayed or reconstructed?
Can sensitive fields be redacted before review?
Can replay artifacts be signed for export integrity?
Can governance teams review evidence in business-readable form?
What this is not

Open-source reference stack, not a complete enterprise platform.

The Cognous Open Control Stack is intentionally narrow. It is not an agent framework, not a model runtime, not a hosted dashboard, not a complete compliance product, and not a full enterprise governance platform. It is a public reference layer that defines practical artifacts for governed AI-agent deployment.

×Not an agent framework
×Not a model runtime
×Not a hosted dashboard
×Not a complete compliance or governance platform
Who it is for

Built for teams moving agents into production.

Enterprise AI teams

Move agents into production with governance built in, not bolted on.

Platform engineers

Add a runtime control layer without adopting a whole framework.

Security & governance

Review what an agent did — and prove it — in business-readable form.

Application developers

Declare an agent's actions once; get authorization, records, and replay.

Relationship to ODES

Separate standard, adjacent evidence layer.

ODES, the Open Decision Evidence Standard, is a separate proposed open, vendor-neutral public standard for portable decision evidence in AI-mediated and cross-boundary decisions. Cognous Open Control Stack is not ODES and does not define ODES conformance. The stack may produce, package, or reference evidence that could support ODES-style records in future profiles, but the relationship is optional mapping and supporting evidence — not identity and not conformance.

Get started

Start with the open-source stack.

Open, vendor-neutral infrastructure for governing AI agents at runtime. Adopt one component, or run the whole stack.

View on GitHub Read the one-pager