ABOUT WINDAGS
A local-first DAG runtime for multi-agent workflows, built around a 503-skill catalog and a five-stage retrieval cascade for selecting expertise per node.
WHAT IT IS
WinDAGs decomposes a natural-language task into a directed acyclic graph of subtasks, matches each node to a hand-written skill from a 503-skill catalog, and executes the graph in waves of parallelclaude -pprocesses. Each wave's outputs feed forward into the next.
The skill catalog is the differentiator. Vanilla Claude does fine on the first response; the second response forgets the project's conventions. WinDAGs grafts the right specialist into the prompt for each node — a cursor-pagination expert for the GraphQL node, a Postgres failover expert for the database node, and so on — chosen by a five-stage retrieval cascade rather than a vector lookup or a keyword tag.
Source-available under the Business Source License 1.1. github.com/erichowens/workgroup-ai.
INFLUENCES
Each row below is a piece of prior work that maps to a concrete subsystem in the codebase. Where there's a paper or canonical reference, follow the link in the source.
| Tradition | Contribution to WinDAGs |
|---|---|
| Graph Theory | DAG structure, dependency resolution, topological sorting |
| Information Retrieval | Five-stage cascade (BM25 + Tool2Vec + RRF + cross-encoder + attribution k-NN) for skill selection |
| 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 Multitasking | Wave-based parallel execution: nodes in the same wave run concurrently, downstream waves consume upstream outputs |
DESIGN PRINCIPLES
SkillSearchService.search(). Used to not be true. The bugs were terrible.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