THE ORIGIN STORY
How ten intellectual traditions and a love of retro computing became a framework for orchestrating AI agents.
THE CONSTITUTIONAL CONVENTION
WinDAGs didn't start with code. It started with a question: what would happen if you let a dozen AI agents debate how AI agents should work? Not as a gimmick, but as a real design process with formal rules, dissent procedures, and ratification votes.
The result was a constitution: 15 architectural decisions, each one debated and stress-tested by agents playing devil's advocate. The agents argued about failure handling, cost budgets, quality layers, and when a machine should stop and ask a human. The constitution became the specification. The specification became the framework.
THE 10 TRADITIONS
WinDAGs draws from ten intellectual traditions. Each one contributes a specific capability.
| Tradition | Contribution to WinDAGs |
|---|---|
| Graph Theory | DAG structure, dependency resolution, topological sorting |
| Bayesian Statistics | Probabilistic skill ranking, multi-armed bandit optimization |
| Distributed Systems | Wave execution, backpressure, circuit breakers |
| Constitutional AI | Self-governing agent behavior, quality constraints |
| Software Craftsmanship | Four-layer quality evaluation (Floor/Wall/Ceiling/Envelope) |
| Operations Research | Cost optimization, resource scheduling, constraint satisfaction |
| Human-Computer Interaction | Progressive revelation, human-in-the-loop checkpoints |
| Resilience Engineering | 4D failure classification, graceful degradation |
| Knowledge Management | Skill lifecycle, pattern learning, institutional memory |
| Cooperative Computing | The Windows for Workgroups metaphor itself |
WHY “WINDOWS 3.11”?
We didn't pick Windows 3.1 randomly. Windows for Workgroups was Microsoft's first attempt at cooperative multitasking and network-aware computing.
WinDAGs is the same idea, 30 years later, for AI agents.
It's not a joke. It's a statement.
THE NAME
WinDAGs = Windows for Workgroups + DAGs. A nod to cooperative multitasking, 30 years later. The aesthetic is the philosophy: systems should be transparent, debuggable, and look like what they are.
BUILT BY CURIOSITECH
WinDAGs is built by Curiositech, Inc., a small team that believes AI orchestration should be transparent, auditable, and cost-conscious.
The framework is released under the Business Source License 1.1 (BSL 1.1). You can read the source, run it, modify it, and use it. The only restriction is offering it as a hosted service.
JOIN THE BETA
Beta testing Spring 2026. Request early access and help shape the future of multi-agent orchestration.
Request Early Access