Skip to content

The computer vision platform with Vero built inSpeak to your data.Let Vero train your model.

Vero is the vision AI agent inside VisionRepo, a computer vision platform for your images and video. Ask it to find, label, train, test and report. You approve every step.

Free planNo credit cardPro from $20/mo
visionrepo.averroes.ai · Wafer Surface DefectsLive app
Sample data
162 images to label in line-2scratchparticle

Wafers, boards, panels, fabric. Any visual data, labeled the same way.

What it changes

One AI vision platform. Better data, models and products.

What changes when your visual data, your models and Vero share one AI vision platform.

Defective
Higher production quality

Catch defects with models trained and tested on your own parts, boards and panels.

A review task marking labels correct or incorrect
Datasets you can trust

Every AI label is a draft. Every review is recorded. Every version is kept.

Testing a model on new images
Models you can prove

Accuracy for every model, and tests on new data before anything goes live.

A dashboard Vero built
Answers without the busywork

Ask Vero for labels, counts, charts and scheduled reports.

How it works

From a folder of images to a model you can call.

Five steps in the real app. Click a step, or let it play.

visionrepo.averroes.ai · UploadLive app
Sample data
Vero · the vision AI agent

You ask. Vero plans. You approve.

Speak to your data in plain words. Vero finds images, labels folders, trains and compares models, and builds dashboards. Every change waits for your OK.

visionrepo.averroes.ai · Wafer Surface DefectsLive app
Sample data
Label the scratches and particles in the unlabeled images in line-2
  • Labels up to 20,000 images per job
  • Reviews every image after labeling
  • Labels land as drafts you approve
Pick the model: Vero, Claude Fable or OpenAI AstraActs with your permissionsAgents on every plan
10labeled images to start training
4model types, from classification to anomaly
27export formats, COCO to YOLOv8
20,000images per Vero labeling job
Organize

Your visual data, organized.

Folders, metadata and tags, filters you can combine, bulk actions across the whole repository, and versions every model points to.

  • Metadata and tags on any image, video or folder
  • Advanced filters with AND / OR
  • Splits into train and hold-out sets
visionrepo.averroes.ai · Wafer Surface DefectsLive app
Sample data
Pricing

Prices on the page. Start free.

Compare plans
Free
$0/month
No credit card

One person, one project.

  • 1 seat
  • 1 project · 1 repository
  • 2 GB storage
  • Limited daily usage
Start free
Most popularPro
$20/month
Billed monthly

A small team labeling and training.

  • 3 seats
  • Unlimited projects & repositories
  • 20 GB storage · 30 GB downloads
  • Standard daily usage
Choose Pro
Ultra
$200/month
Billed monthly

Teams labeling together.

  • 7 seats
  • Unlimited projects & repositories
  • 100 GB storage · 300 GB downloads
  • Extended daily usage
Choose Ultra
Production & on-prem
Custom
With the Averroes team

Inspection on the line, on your own servers if you need it.

  • Monitors on every new image
  • Pass / reject rules and alerts
  • Cloud, on-prem or air-gapped
Talk to us
FAQ

Questions, answered.

What is Vero?

The vision AI agent built into VisionRepo. Speak to your data, and let Vero label it and train your model. Ask it to label, train, chart or explain; it shows a plan and waits for your approval. Every action is also a button.

What is VisionRepo?

A computer vision platform, and a vision AI platform, by Averroes.ai, with a vision AI agent, Vero, built in. Store images and video, label them, and train models you can test, compare and call over an API, by hand or by asking Vero. SOLAR-1 and PCBA-1 turn the same engine into solar reports and board results.

What happens right after I sign up?

You land in an empty workspace with Create Your First Repo. Upload images and video, or Try a Sample, then label, train and test. The upload dialog shows those four steps.

How many images do I need?

Training starts at 10 labeled images; aim for 20 to 50 per class. Anomaly detection (Ultra) needs only images of good parts.

Is there a free plan?

Yes: $0, no card, 1 seat, 1 project, 2 GB. Pro is $20/mo, Ultra $200/mo.

Can it run on my production line?

VisionRepo runs in the cloud and serves models over an API. Inline, on-prem and air-gapped inspection is Averroes production inspection.

Put your visual data to work.

Free plan, no credit card. Bring your own images or start from a sample.

Free planNo credit cardPro from $20/mo
Sample data