Skip to content

For developers

The runtime beneath
the workspace.

VulRunWG is a lightweight Vulkan-based GPU compute and local AI inference runtime. It supports custom WGSL workloads across compatible hardware, alongside supported local models.

Proprietary runtime · Public release preparation in progress

The applicationVulRunWG: Suite

A locally hosted browser workspace.

The runtimeVulRunWG

The runtime for local inference and custom GPU compute.

The hubLessPrep

Our software, games and technology.

Connect locally

A familiar API.
Specific supported behavior.

The local server exposes OpenAI-compatible endpoints for supported chat, embeddings, image and speech workflows. Point a compatible client at the local address and use an installed model ID.

Compatibility is not a promise that every cloud feature or client option is implemented. Check the endpoint, model, request shape and limitations for the workflow you need.

The existing Developer Tools area provides the local API address, model IDs, Python/JavaScript/C# examples and a testing console. Those controls belong to VulRunWG: Suite; the local API and model execution come from the VulRunWG runtime.

Existing interface documentation

Compute beyond inference

Same infrastructure.
Different kernels.

WGSL is the shader language used for custom GPU workloads, such as particle simulation and other parallel computations. A compatible Vulkan device and driver are required; supported workloads depend on the hardware and interface.

The Far Off Up and Rules for Thee use dedicated WGSL kernels for game effects on shared GPU infrastructure. Particle motion, flocking and other visual effects are compute workloads—not AI inference.

These are existing, bounded integrations. Their presence does not make every internal GPU interface a supported, unrestricted general-purpose SDK.

See the actual integrations

The licensing boundary

Build with it. Know what you ship.

Established policy direction. Final legal agreements are still awaiting approval.

Free use

Connect to a separate runtime.

Local development, evaluation, testing and API access are free. Commercially sold software may connect to a separately installed VulRunWG runtime.

Ordinary business use and permitted internal deployment are also free. No subscription, account, activation fee or per-seat charge.

Separate agreement

Include the runtime in a sold product.

Embedding, bundling or redistributing VulRunWG as part of a commercially sold product requires a separate commercial license.

Free use does not grant unrestricted public redistribution. Model publishers and third-party components retain their own terms.

Ask about distribution

Keep the evidence attached

Numbers with context.

Hardware, model revisions, settings and limits belong beside a performance result. The original technical pages and measurement notes remain available without rewriting their results for this rebrand.