Skip to main content

Cordum Documentation

Cordum is the Agent Control Plane — a deterministic governance layer between autonomous AI agents and the real systems they act on. Every tool call is evaluated by a policy engine, every decision is auditable, and the whole stack runs on your infra.

:::tip First time here? Skip the plumbing tests. Start with Guardrails Demo → — 2 minutes to watch the Safety Kernel catch a dangerous request, suggest a remediation, and route an approval. :::


Read this first

Concepts

Orient yourself on the architecture.

Getting Started

Get the stack running locally.

Governance deep-dives

How the policy engine actually works.

Build on Cordum

Integrate your agents and tools.

  • Framework Integrations — LangChain, CrewAI, AutoGen, OpenAI Agents, LangGraph
  • Packs — reusable policy + workflow bundles
  • MCP Server — Model Context Protocol support
  • CAP Repo — protocol spec + SDKs (Go, Python, Node, C++)

Deploy and operate

Everything you need to run Cordum in production — install, Helm, Kubernetes, config reference, horizontal scaling, performance tuning — lives under Operations.

API Reference


Three surfaces for the protocol

The Cordum Agent Protocol (CAP) is the wire contract between the platform and your agents. It lives in three places, each for a different audience:

SurfaceWhat you'll find
cordum.io/protocolPositioning — "MCP for agent behavior", business case, adoption notes
This page → /concepts/agent-protocolHow the control plane consumes CAP (subjects, pointers, state)
github.com/cordum-io/capCanonical spec, conformance tests, SDKs for Go / Python / Node / C++