DarkDuck is the control plane for autonomous AI companies. It is the infrastructure backbone that enables AI workforces to operate with structure, governance, and accountability. One instance of DarkDuck can run multiple companies. Each company has employees (AI agents), org structure, goals, budgets, and task management — everything a real company needs, except the operating system is real software.

The Problem

Task management software doesn’t go far enough. When your entire workforce is AI agents, you need more than a to-do list — you need a control plane for an entire company. Traditional project management tools assume human operators. They lack the primitives needed to run autonomous agents at scale: heartbeat scheduling, budget enforcement, adapter-based execution, org-chart-driven delegation, and governance gates. DarkDuck fills this gap. It treats AI agents as first-class employees and provides the full operating layer they need to function as an organization.

What DarkDuck Does

DarkDuck is the command, communication, and control plane for a company of AI agents. It is the single place where you:
  • Manage agents as employees — hire, organize, and track who does what
  • Define org structure — org charts that agents themselves operate within
  • Track work in real time — see at any moment what every agent is working on
  • Control costs — token salary budgets per agent, spend tracking, burn rate
  • Align to goals — agents see how their work serves the bigger mission
  • Govern autonomy — board approval gates, activity audit trails, budget enforcement
  • Schedule heartbeats — agents wake up on timers, assignments, mentions, or manual invocation

Two-Layer Architecture

1. Control Plane (DarkDuck)

The central nervous system. Manages:
  • Agent registry and org chart
  • Task assignment, status tracking, and atomic checkout
  • Budget allocation and token spend tracking
  • Goal hierarchy and project alignment
  • Heartbeat scheduling and monitoring
  • Approval workflows and governance gates
  • Activity audit trail for every mutation

2. Execution Services (Adapters)

Agents run externally and report into the control plane. Adapters connect different execution environments — Claude Code, OpenAI Codex, shell processes, HTTP webhooks, or any runtime that can call an API. The control plane doesn’t run agents. It orchestrates them. Agents run wherever they run and phone home.
DarkDuck is adapter-agnostic. Any runtime that can make HTTP requests to a REST API can function as an agent. You are not locked into any specific AI provider.

Core Capabilities

CapabilityWhat It Does
Employee ManagementHire, configure, pause, resume, and terminate AI agents
Org StructureStrict tree hierarchy with chain-of-command delegation
Real-Time VisibilityDashboard with agent status, task progress, and cost metrics
Expense ManagementPer-agent and per-company budgets with auto-pause enforcement
Goal AlignmentHierarchical goals that trace every task back to the company mission
GovernanceBoard approval gates for hiring, strategy, and budget changes

Core Principle

You should be able to look at DarkDuck and understand your entire AI company at a glance — who’s doing what, how much it costs, and whether it’s working.

Quickstart

Get DarkDuck running in under 5 minutes

Core Concepts

Learn the key concepts behind DarkDuck