Whoosh’d
Operator-controlled inference for local and self-hosted model workflows. One surface for routing, readiness, and runtime visibility.
Prototyped
Whoosh’d gives local AI applications one operator-controlled surface for routing, readiness, model inventory, streaming, lifecycle visibility, and overload behavior. It is a control plane above local model runtimes, not a replacement for them.
A runtime layer that Nodes can use when they need local or self-hosted inference with explicit governance instead of ambient behavior.
Builders operating local or self-hosted inference without turning runtime management into a pile of scripts.
Evidence
Status reflects evidence in the corresponding source repositories at time of writing. See the research page for the broader picture.