AI agents have started to act — calling tools, moving data, and changing enterprise systems. Open Control Stack authorizes what an agent may do, enforces policy before it runs, and turns every run into portable evidence.
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?
Traditional logs, dashboards, and policy documents are not enough by themselves. Governed AI-agent deployment requires structured runtime records and portable evidence artifacts.
Four open-source reference components, each mapping to one stage of the governed lifecycle. Use one, or run them in sequence.
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.
Read the specificationA 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.
Read the specificationA portable replay-bundle format capturing the task frame, action proposals, policy decisions, evaluation traces, blocked actions, authority records, reliance records, validation reports, redaction metadata, and signature metadata.
Read the specificationA business-facing evidence-pack format summarizing agent purpose, deployment context, tools, actions, authority model, policy controls, blocked actions, reliance, replay bundles, validation results, redacted exports, risks, and review records.
Read the specificationEvery governed action follows the same runtime path — proposed by the agent, authorized, evaluated against policy, executed, and recorded.
The same artifacts serve engineering and governance — one record, read four different ways.
Move agents into production with governance built in, not bolted on.
Add a runtime control layer without adopting a whole framework.
Review what an agent did — and prove it — in business-readable form.
Declare an agent's actions once; get authorization, records, and replay.
The Cognous Open Control Stack is intentionally narrow. It is a public reference layer that defines practical artifacts for governed AI-agent deployment — nothing more.
A five-minute overview of what the stack governs and why it matters.
Read PDF →Non-technical collateral on value, scope, and adoption.
Read PDF →The four component specs: manifest, control plane, replay, and evidence.
View specs →Source, JSON Schemas, and conformance tests on GitHub.
Open GitHub →Open, vendor-neutral infrastructure for governing AI agents at runtime. Adopt one component, or run the whole stack.