Overview
The Intel® Retail AI Suite is a collection of sample open-source code for various retail use cases. It consists of modular software, performance data, and validated hardware. The suite focuses on the AI pipelines to help partners assess device configurations across Intel® product generations to enhance hardware decision-making and reduce the total cost of ownership.
View on GithubWhat's New
Announcing Open Edge Platform 2026.0
Open Edge Platform 2026.0 expands the Retail AI Suite with an Order Accuracy Dine-In pipeline for multi-camera, VLM-based order validation. Retail multimodal AI gets easier with Geti™ Instant Learn - a new low-code framework for image and text prompt learning — all accelerated on Intel® Core™ Ultra processors for real-time edge AI.
Learn MoreNew Intel® Core™ Series 2 Processor
Intel Core Series 2's 12 all-P-core architecture delivers the deterministic compute retail ODMs demand — running vision AI for loss prevention, order accuracy, and self-checkout on a single, compact platform. Consistent uptime, reduced footprint, lower power consumption, and simplified hardware mean lower total cost of ownership at scale. So retailers can spend less time managing fragmented platforms and more time delivering differentiated store solutions.
Learn MoreBenefits
Pre-built sample pipelines for accelerated application development, performance results to remove ambiguity on hardware choice, and co-marketing opportunities for hardware and software builders.
AI System Qualification
Determine hardware needs and TCO for scale deployments with performance results and validate results using the Performance Evaluation Tool.
Co-Marketing Opportunities
Feature your qualified systems in Intel® Edge Software Recommended Hardware for system reports, co-marketing and ISV match-making opportunities.
Accelerate Development
Utilize the sample AI pipelines to most effectively use Intel® Software frameworks to develop AI solutions optimized for Intel® hardware
Technology & Performance
Leverage Intel’s long-standing industrial robotics expertise, advanced compute to power real-time controls and AI acceleration on a single processor, and an open ecosystem to adapt next-generation robotics and scale physical AI-based robotics faster.
Advanced Compute
Intel delivers integrated, optimized hardware performance across a range of silicon form factors and systems to power AI acceleration with low-latency and scalability at the edge.
Intel® Core™ Ultra Processors
Power both real-time performance and AI acceleration on Intel® Core™ Ultra Series 2 and Series 3 processors to deliver efficiency and cost savings.
GPUs for AI Acceleration
Stream media analytics and deep learning pipelines at the edge with powerful GPU to accelerate advanced physical AI and fast model inference at the edge.
Intel® Core™ Series 2 Processors
Ensure predictable, consistent, deterministic performance for safety and motion control. Intel® Core™ Series 2 Processors eliminate latency, and variability to enable real-time control and AI workloads to run reliably on a single platform, reducing hardware complexity in manufacturing settings.
Qualified Intel® AI Edge Systems
Discover our comprehensive catalog of qualified Intel® AI Edge Systems, meticulously tested and validated through the Intel®...
Models Used
Listing of all CV and Gen AI models used across the various retail use case AI pipelines
Computer Vision Models
The CV models have been used to mimic develop the pipeline and run performance tests
Models:
- YOLO V11
- YOLO World
- EfficientNet
Generative AI Models
The Gen AI models have been used to mimic develop the pipeline and run performance tests
Models:
- Qwen 2.5B
- YOLO World
Open Edge Ecosystem
Intel’s empowers partners to seamlessly integrate AI solutions for retail that extend x86 architectures for real-time decision making, improved efficiency, and reduced latency through an open, collaborative approach ensure performance, scalability, and lower overall cost.
Verified AI Edge Systems
Intel partners with OEMs and ODMs to benchmark and verify hardware solutions optimized to meet heterogeneous computing requirements for IoT and AI-driven metro and public safety deployments to ensure optimized hardware and software integration across a range of power levels, sizes and performance options.
Open Edge Platform
A modular, open-source platform to simplify development, deployment and management of edge AI featuring industry-specific building blocks, microservices, frameworks, models, pipelines, and libraries that streamline integration and deployment with cloud-like simplicity and enterprise-grade security to enable infrastructure, applications and efficient AI deployments at scale.
ESQ Qualification Tool
Comprehensive catalog of qualified Intel® AI Edge Systems, meticulously tested and validated through the Intel® Edge System Qualification (ESQ) program, to ensure system performance. OEMs and ODMs can use tool to qualify their systems today and join our thriving Edge AI ecosystem to build Intel-powered offerings.
ESQ for Intel® AI Edge Systems
Intel® ESQ for Intel® AI Edge Systems enables you to self-qualify your hardware with benchmarked...
Use Cases
Accelerate your edge Al application development journey with Intel® Al Edge Systems-backed by curated Edge Al Suites, and Toolkits to optimize Vision and Gen Al workloads across industries.
Automated Self-Checkout
Enabling faster checkout and increasing customer convenience while bringing operational efficiencies to the store.
The sample application defines a pre-configured pipeline to detect and classify products at the self-checkout station including those with and without descriptive text and barcodes.
Learn More
Loss Prevention at the Checkout
The sample application is a pre-defined pipeline to detect possible theft at the checkout. The pipeline detects fake scans, product switching, concealing products and several potential theft scenarios.
Learn More
Order Accuracy
Increase order assembly and packing accuracy to ensure a great customer experience and reduce returns and complaints.
The sample application consists of a pre-defined pipeline and a video recall function. The pipeline verifies what's being packed against the order receipt to ensure packing accuracy. The video recall provides transparency in the event of a dispute.
Learn MoreResources
Accelerate your edge Al application development journey with Intel® Al Edge Systems-backed by curated Edge Al Suites, and Toolkits to optimize Vision and Gen Al workloads across industries.
Advancing utility management with industry solutions that enhance operational efficiency.
Retail Innovation Unlocked: Open Source Vision-Enabled Solutions
Computer vision is revolutionizing various industries, and retail is no exception. By automatically extracting and analyzing important characteristics from images and videos...
Workload performance benchmarking
With rapidly changing technologies, maintaining a reliable approach to monitoring workload performance is essential. However, performance benchmarking tools are often tightly...
Streamline Development of Automated Self-Checkout Use Cases
Computer vision (CV) pipelines use many AI models based on use case and complexity. In the retail checkout space, developers design and assemble their applications with models...
Quickly Build Your Vision-Enabled Self-Checkout Solution
Automated self-checkout solutions are revolutionizing retail, but building an application that can scale requires a deep understanding of hardware and software....
Advancing utility management with industry solutions that enhance operational efficiency.
Demo of heterogenous compute in use for vision pipelines
This is a demo of Intel's Automated Self-Checkout Reference Implementation showing how to deploy and monitor computer vision workloads. The demo describes the ease...
Automated Self Checkout video
This is a demo of Intel's Automated Self-Checkout Reference Implementation showing how to deploy and monitor computer vision workloads. The demo describes the ease in which these...
Order Accuracy, VLM, Agentic AI, Computer vision
This is a demo showing the interactions in a fast food chain when orders are being packed. It focuses on packing accuracy and offers playback for future customer queries...
CV, OpenVINO, DLStreamer, self-checkout
This is an introduction to using AI and computer vision on retail applications. The training covers a high level overview of AI performance optimization with Intel software frameworks and heterogeneous compute...
Developer Tools
Accelerate your edge Al application development journey with Intel® Al Edge Systems-backed by curated Edge Al Suites, and Toolkits to optimize Vision and Gen Al workloads across industries.
Performance Evaluation Tool
The performance evaluation tool helps determine appropriate hardware for running each AI workload at scale by generating the necessary performance metrics across Intel’s heterogeneous architectures.
TGStreamer is an open source framework licensed under LGPL. You are solely responsible for determining if your use of Gstreamer requires any additional licenses.
Learn More
Support
Provides comprehensive support for Edge AI and Intel technologies, delivered by global professional technical experts.
Contact UsSubscribe To Our Newsletter
Subscribe to the newsletter for the latest updates on materials posted on the Intel Industry Solution Builders program.
By submitting this form, you are confirming you are an adult 18 years or older and you agree to share your personal information with Intel to use for this business request. You also agree to subscribe to stay connected to the latest Intel technologies and industry trends by email and telephone. You may unsubscribe at any time. Intel’s websites and communications are subject to our Privacy Notice and Terms of Use.
By submitting this form, you are confirming you are an adult (18 years or older) and you agree to share your personal information with Intel to use for this business request. You also agree to subscribe to stay connected to the latest Intel technologies and industry trends by email. You may unsubscribe at any time. Intel’s websites and communications are subject to our Privacy Notice and Terms of Use.