Allocate
Korrx divides shared concurrency and token capacity among Tyr instances using versioned, expiring grants.
Distributed LLM capacity control
Korrx (pronounced "kor") allocates capacity across the system. Tyr enforces it locally before each LLM request begins.
Fast local rejection · Priority-aware capacity · Exact decision provenance
Overload is stopped early. Tyr rejects excess work before a provider call is created.
Authority expires safely. Tyr fails closed when its Korrx grant is no longer valid.
Every decision is traceable. Grant, revision, and controller epoch remain attached to the admission.
How it works
Korrx coordinates shared capacity in the background while Tyr keeps the request path local and predictable.
Korrx divides shared concurrency and token capacity among Tyr instances using versioned, expiring grants.
Tyr evaluates each request against the current grant without adding a control-plane call to the request path.
When capacity is unavailable, Tyr fails fast. Rejected work never reaches the model provider.
Architecture
The control plane distributes authority. The data plane enforces it without consulting Korrx for every request.

System layers
Distributed allocation
Local enforcement
LLM capacity engine
Concurrency foundation
Project status
The core path has been verified for active grants, local overload rejection, admission provenance, fail-closed expiration, and recovery under a renewed grant.
Current priorities include workload identity, authentication, OpenTelemetry, durable audit exports, and production deployment support.
Built for systems under load