Vision Lab — VR

Point at a glyph in your headset, pull the trigger, and a vision-language model describes what's in front of you. Compatible candidates orbit an anchored star in your view, sized and tilted by their real classifier-supplied orbital parameters. Inference runs on the Meridian MCP — captured frames are POSTed to mcp.ask-meridian.uk/v1/vision and the operator pays for the GitHub Models call.

GPT-4o-mini Server-side · operator-paid · no client-side model download

Press Begin to verify XR support and enter the gate.

Find candidates routes via the Meridian MCP — no PAT, no setup. Llama-3.3-70B authors candidates and the orbital classifier ranks them server-side.

No bundler — modules load from esm.sh on first hit and are then cached by the browser. Open in the Quest browser and press the VR button to enter the scene.