The open source tool to build vision applications

Prototype, experiment, test, integrate, and deploy pipelines to production
cogs
Integrated workflow builder and deployment infrastructure ensures that what you configure can be deployed
cctv
Deploy using a fully managed infrastructure with an API endpoint or on-device, internet connection optional, without the headache of environment management
cubes
Combine custom models, open source models, LLM APIs, pre-built logic, and external applications

How to Build a Workflow

Learn how to use a low-code open source platform to simplify building and deploying vision AI applications.
1
cube icon

Choose a Block

Choose from 40+ pre-built blocks that let you use custom models, open source models, LLM APIs, pre-built logic, and external applications. Blocks can be models from OpenAI or Meta AI, applications like Google Sheets or Pager Duty, and logic like filtering or cropping.
2
connected blocks icon

Connect Blocks

Each block can receive inputs, execute code, and send outputs to the next block in your Workflow. You can use the drag-and-drop UI to configure connections and see the JSON definitions of what’s happening behind the scenes.
3
rocket icon

Deploy Workflows

You’ll receive an output of the final result from your Workflow and the format you want it delivered in, like JSON. Once your Workflow produces sufficient results, you can use the Workflow as a hosted API endpoint or self-host in your own cloud, on-prem, or at the edge.

Workflow Templates

Explore pre-made templates for specific use cases.
Detect road signs and save to CSV
  • YOLO-NAS
  • CSV Sink
Detect fire and smoke then send SMS notification
  • YOLO-NAS
  • SMS
Detect text and run OCR
  • YOLO-NAS
  • OCR Model
Segment houses in aerial images and save to CSV
  • YOLOv8 Instance Segmentation
  • CSV Sink
Segment packages and save to CSV
  • YOLOv8 Instance Segmentation
  • CSV Sink
Segment license plates and save to CSV
  • YOLOv8 Instance Segmentation
  • CSV Sink

Explore Popular Combinations

Save time with powerful model and logic connections to solve complex problems.
Model
Sink

YOLOv7 Instance Segmentation to Active Learning Data Collector

Build a computer vision workflow that connects YOLOv7 Instance Segmentation to Active Learning Data Collector.
Model
Sink

YOLOv5 to Active Learning Data Collector

Build a computer vision workflow that connects YOLOv5 to Active Learning Data Collector.
Model
Sink

YOLOv8 to Active Learning Data Collector

Build a computer vision workflow that connects YOLOv8 to Active Learning Data Collector.
Model
Sink

YOLOv8 Keypoint Detection to Active Learning Data Collector

Build a computer vision workflow that connects YOLOv8 Keypoint Detection to Active Learning Data Collector.
Model
Sink

YOLOv8 Instance Segmentation to Active Learning Data Collector

Build a computer vision workflow that connects YOLOv8 Instance Segmentation to Active Learning Data Collector.
Model
Sink

YOLO-NAS to Active Learning Data Collector

Build a computer vision workflow that connects YOLO-NAS to Active Learning Data Collector.

Customize Your Pipeline

Connect models from OpenAI or Meta AI, applications like Slack or Pager Duty, and logic like filtering or cropping.
View All Blocks

Simplify Building and Deploying Vision AI Applications

Integrated workflow builder and deployment ensures what you configure runs in production
list of model blocks

Models

Integrated workflow builder and deployment ensures what is configured runs in production
list of transformation blocks

Transformations

Dynamically process inputs to improve the results of your model predictions
list of branching blocks

Branching

Add custom or pre-built logic for flow-control and processing
list of customization blocks

Customization

Create and add custom blocks to your pipeline
list of integration blocks

Integrations

Connect your pipeline to external applications

Deploy Workflows at Scale

Roboflow powers millions of daily inferences for the world’s largest enterprises on-device and in the cloud
Deploy your Workflows directly on fully managed infrastructure through an infinitely-scalable API endpoint for high volume workloads
Run Workflows on-device, internet connection optional, without the headache of environment management, dependencies, and managing CUDA versions.
Isolate dependencies in your software by using the Python SDK or HTTP API to operate and maintain your Workflows separate from other logic within your codebase
Supported devices include ARM CPU, x86 CPU, NVIDIA GPU, and NVIDIA Jetson

Building Blocks for Custom Pipelines

Blocks receive inputs, execute code, and send outputs to the next block in your Workflow
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.