ToolVision Detector

ToolVision Detector

Finds wrenches, screwdrivers, hammers and pliers in a photo you upload, using a YOLO26n model that runs in your browser. It suits makers and workshops who want private photo checks.

Made by moindedroper on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: ToolVision Detector is a static web page that spots hand tools in a photo. You upload a picture and a YOLO26n model marks wrenches, screwdrivers, hammers and pliers. The model runs inside your browser through onnxruntime-web, so your photos stay on your device.

Who it suits: People who want a quick, private way to see which common hand tools are in a picture.

Industry | Who uses it | How they use it | Example
Workshops | Makers and hobbyists | Check which tools appear in a bench photo | A photo of a tool wall
Education | Trade teachers | Show how object detection finds items in an image | A classroom demo with a sample photo
Software | Computer vision developers | Study a small detector running in a page | Reading index.html and the model file
Hardware retail | Shop staff | Test whether a photo shows the expected tools | A product shot with pliers

If you need to detect other kinds of objects, or run it at scale on a server, you can skip it.

Where to use it:

• A web browser, on the Space's page at Hugging Face
• Windows, macOS or Linux, opening index.html from a downloaded copy

Use case | Who | What they get back
Tool spotting | Makers | The wrenches, screwdrivers, hammers and pliers found in a photo
Private checks | Anyone | A result with no photo sent off the device
Detector study | Developers | A small page and one ONNX model file to read

How to set it up:

• A web browser
• Python only if you want to download the files to your computer

1. Install the Hugging Face hub package.
2. Download the Space with the hf command.
3. Move into the downloaded folder.
4. Open index.html in a web browser.

pip install -U huggingface_hub
hf download moindedroper/toolvision-detector --repo-type space --local-dir toolvision-detector
cd toolvision-detector

How to use it: Open the Space page, or index.html from your copy, then upload a photo. The model looks for wrenches, screwdrivers, hammers and pliers in it.

Tool | What it does
index.html | The page where you upload a photo and run the detector
best.onnx | The YOLO26n model file the page runs in your browser

Example: You upload a photo of a workbench with a hammer and a pair of pliers on it. The page runs the model and shows which of the four tool types it found.

For newcomers and experts: Open the Space page and upload one clear photo of a tool. Nothing needs installing, and the photo is not sent anywhere.

The repository holds only a README, one HTML page and an ONNX model, so inference happens client side with onnxruntime-web. That keeps photos private and needs no server, but it limits the work to what your browser can run.

You upload a photo in the page
onnxruntime-web loads best.onnx
YOLO26n looks for the four tool types
Detections show on the page

Good to know:

• It looks for four tool types: wrenches, screwdrivers, hammers and pliers
• Built as static HTML, so there is nothing to install to use it online
• License: AGPL-3.0, which the author ties to Ultralytics YOLO training of the model
• Cost to run: none named
• Data it reaches: none beyond the photo you upload, which stays on your device
• Not for: tool types other than those four

On Hugging Face, 13 November 2026

• Likes: 1
• Built with: static
• License: agpl-3.0

Links

• Space: https://huggingface.co/spaces/moindedroper/toolvision-detector
• Files: https://huggingface.co/spaces/moindedroper/toolvision-detector/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.