Instant local hosting
Open a tab, pick a model, and start hosting. RF-DETR and SmolVLM load in a Web Worker on WebGPU — no Python environment or driver setup.
Turn any browser with WebGPU into a cluster node. Share inference for LLM models — Host a model on your powerful workstation and access it securely from your phone, laptop, or let others connect to it.
Powered by WebGPU & Transformers.js · No GPU drivers to install · Open HTTP API
Contribute spare GPU cycles from your workstation. Clients send images over HTTP; your browser runs the model and returns results — privately, on your hardware.
Open a tab, pick a model, and start hosting. RF-DETR and SmolVLM load in a Web Worker on WebGPU — no Python environment or driver setup.
Inference runs on your GPU in the browser. Images are processed on your machine; nothing is sent to third-party AI APIs.
Connect from curl, Python, Node, or any HTTP client. Simple JSON endpoints for detection and image description — queue and broker included.
A lightweight Node broker coordinates tasks. Browser hosts stay connected via SSE and pull jobs when idle.
Browser host
WebGPU inference
Open the host page, choose a host id and model, then click Start hosting. Keep the tab open while you share GPU time.
The broker forwards detection and description tasks to your browser. One job runs at a time per host.
Point clients at POST /v1/detect
or /v1/describe
with your host id. Results return as JSON.
Use the cluster monitor to see online hosts and copy ready-made curl examples.
curl -X POST 'http://localhost:5180/v1/detect' \
-H 'Content-Type: application/json' \
-d '{
"host": "my-gpu-node",
"image_url": "https://example.com/photo.jpg",
"threshold": 0.5
}'
Models download from Hugging Face on first load. Pick one per host session.
Real-time object detection (COCO) via ONNX on WebGPU. Endpoint:
POST /v1/detect
Describe images with a compact VLM on WebGPU. Endpoint:
POST /v1/describe
Share your GPU or explore nodes already online.