Job submitted
submitAn AI agent submits a job with context pointers and risk metadata.
AI Agent Governance
The Control Plane for AI Agents
Enforce policy before execution, require human approvals where risk demands it, and keep a full audit trail — from first action to final result.
Source-available · No credit card required · Deploy in minutes
Cordum — Command Center
Jobs Today
247
Approved
98.4%
Avg Latency
42ms
Approval granted
db-migration-prod · policy v2.1 · hash 7f8a9d
deploy-staging-v2.42s agoApproved
db-migration-prodnowRunning
scale-k8s-clusterqueuedPending
Plugins available for every major AI platform
Hover or focus this section to pause the scrolling integration list.
OpenAI
Anthropic
LangChain
AWS
Google Cloud
Azure
Hugging Face
LlamaIndex
Temporal
CrewAI
AutoGen
Mistral
Cohere
Vertex AI
Bedrock
n8n
Zapier
OpenAI
Anthropic
LangChain
AWS
Google Cloud
Azure
Hugging Face
LlamaIndex
Temporal
CrewAI
AutoGen
Mistral
Cohere
Vertex AI
Bedrock
n8n
Zapier
Start With These AI Agent Governance Guides
Learn pre-dispatch governance, AI agent security measures, approval workflows, and platform comparisons before shipping autonomous AI agents to production.
What Is AI Agent Governance?
Core concepts, decision models, and implementation roadmap for production teams.
AI Agent Security Measures Guide
Practical security controls for policy checks, approvals, output safety, and audit trails.
AI Governance Platforms Comparison
Compare control-plane options for autonomous AI agents and enterprise governance needs.
How to Add Governance to OpenClaw
Step-by-step implementation tutorial for OpenClaw policy enforcement and approvals.
OpenClaw Governance Plugin (CordClaw)
Product landing page for pre-dispatch AI agent policy enforcement, approvals, and audit trails.
AI Agent Security Measures: 12 Controls
A practical control matrix for securing autonomous AI agents in production.
AI Agent Security Tools Guide
Evaluate policy enforcement, approvals, output safety, and audit coverage before you buy.
AI Agent Orchestration Control Plane Guide
Compare orchestration reliability, policy controls, and audit readiness for production AI agents.
Deploy AI Agents in Production
Architecture, rollout gates, monitoring, and rollback checklists for production deployment.
The Problem
AI agents are going autonomous. Governance can’t wait.
Teams are deploying autonomous AI agents fast. Without a control plane, risk and ambiguity scale faster than value.
Ungoverned autonomy
Agents can restart services, write to production systems, or push code without explicit policy approval.
No reliable audit trail
When someone asks what happened, teams stitch together logs across tools and still miss key decisions.
Shadow automation risk
Teams build one-off safety checks under pressure. Control is inconsistent and hard to review.
The Solution
The control plane for Autonomous AI Agents
Cordum gives you a single governance layer between agent intent and production action — enforce policy, require approval, and audit every decision.
Safety Kernel
Policy-as-code evaluates every job before it can execute.
- ALLOW, DENY, REQUIRE_APPROVAL, or ALLOW_WITH_CONSTRAINTS
- Snapshot-based decisions with replayable reasoning
- Simulation support before policy rollout
Human-in-the-loop
Approval gates pause high-risk operations until the right person approves.
- Risk-aware approval routing
- Decision binding to job hash and policy snapshot
- Fast, clear operator experience
Full audit timeline
Every action and decision is captured in a deterministic run history.
- Append-only execution records
- Searchable decision context
- SIEM-friendly export paths
Extensible packs
Add domain workflows and workers without destabilizing the core platform.
- Installable overlays for policy and config
- Scoped schema and workflow namespaces
- Disable or purge with clear rollback paths
How It Works
From job to result—governed every step
Policy checks, approval gates, and execution telemetry are built into the workflow lifecycle.
1
2
Safety check
checkThe Safety Kernel evaluates policy in milliseconds before any dispatch happens.
3
Approval when needed
approveHigh-risk jobs pause until an authorized operator approves or rejects the action.
4
Worker execution
executeScheduler routes to capable workers with retries, timeout controls, and backpressure.
5
Audit sealed
auditRun results and decisions are written to immutable timeline records for review.
workflow.yaml
name: incident-remediation
steps:
collect_signals:
type: worker
topic: job.ops.collect
approval_gate:
type: approval
depends_on: [collect_signals]
restart_service:
type: worker
topic: job.ops.restart
depends_on: [approval_gate]
publish_audit:
type: notify
depends_on: [restart_service]Approval steps are first-class workflow nodes, not custom glue code.
Architecture
Production-ready architecture
Built for teams that need predictable behavior under pressure.
incident-response-v2
ActiveTrigger
Customer Request
Ticket #492
Step
Planner
Routing to Agents
Step
Model: Claude 3.5
Draft Reply
Step
Tool: Stripe MCP
mcp: refund_charge
API Gateway
Unified HTTP, WebSocket, and gRPC control plane surface for jobs, runs, approvals, and policy.
Realtime stream support
Scheduler + Safety Kernel
Least-loaded routing with policy enforcement, budget checks, and stale-job reconciliation.
Deterministic dispatch
Workflow Engine
DAG execution model with retries, dependency handling, and run-level timeline tracking.
Parallel steps + failure semantics
NATS + Redis backbone
Message durability, pointer-based state, locks, and artifact metadata for production-grade agent governance.
JetStream-ready
Trust & rollout
Transparent for builders. Controlled for production.
Read the code, validate the operating model, and choose the rollout path that matches your team.
Source-available. No black boxes.
Inspect the platform in the open, review protocol details, and adopt Cordum with clear eyes.
Inspect the core
Review the core platform, CLI, and protocol details before you commit to a rollout.
Build in the open
Use published docs, examples, and contribution paths instead of opaque vendor workflows.
Validate your fit
Start with community deployment patterns, then layer in stricter governance when needed.
Enterprise controls when you're ready
Move from pilot to production without changing the control-plane model your operators already understand.
- SSO / SAML and advanced role controls
- Compliance-focused audit retention and exports
- Priority support and rollout partnership
Editions
Start with Community. Grow into Team or Enterprise.
Community gets you live quickly, Team adds more collaboration capacity, and Enterprise adds identity, audit, and rollout support.
Community
For individual builders and internal teams validating autonomous AI agents.
- Full control plane (Safety Kernel, Scheduler, Workflow Engine)
- Dashboard & CLI
- Up to 3 workers
- Community support (Slack & GitHub)
Team
Coming Soon
Expanded capacity and collaborative governance for teams running multiple agents.
- Everything in Community
- Up to 25 workers
- Multi-approver gates
- 90-day audit retention
Enterprise
Recommended
SSO, compliance-grade audit controls, and SLA-backed support for governing AI agents at scale.
- SSO / SAML and advanced RBAC
- Unlimited audit retention + SIEM export
- Priority support with response SLAs
- Managed or on-prem deployment options
Newsletter signup
Frequently Asked Questions
What is Cordum used for?
Cordum is used to govern autonomous AI agents in production. It provides pre-execution policy checks, approval gates for risky work, and a full audit timeline of every decision and action.
How is Cordum different from an agent framework?
Agent frameworks focus on reasoning and chaining tasks. Cordum is the control plane that governs whether actions are allowed, who must approve them, and how they are audited.
Is Cordum open source?
Cordum is source-available under the Business Source License (BUSL-1.1). You can view, clone, run, and modify the core for internal use. Enterprise capabilities are available for organizations that need expanded governance and support.
What does a production setup need?
A standard deployment uses Go services with NATS and Redis. Production environments typically enable durable messaging, timeout reconciliation, and policy governance workflows.
Ready to ship autonomous AI agents safely?
Start in minutes with the quickstart, or talk with our team about enterprise governance needs.