Contributors per cycle
Accepted projects each year, against the median organization that year
View as table
| OpenVINO Toolkit | Median organization | |
|---|---|---|
| 2016 | 0 | 4 |
| 2017 | 0 | 4 |
| 2018 | 0 | 3 |
| 2019 | 0 | 4 |
| 2020 | 0 | 4 |
| 2021 | 0 | 4 |
| 2022 | 3 | 3 |
| 2023 | 5 | 4 |
| 2024 | 8 | 4 |
| 2025 | 16 | 5 |
| 2026 | 18 | 4 |
In GSoC 2026Growing in 2026
OpenVINO Toolkit
OpenVINO is an open‑source toolkit designed to optimize and deploy deep learning models from cloud to edge. It accelerates inference for a wide range of use cases—including computer vision, generative AI, and agentic AI—supporting models from popular frameworks such as PyTorch, TensorFlow, ONNX, and more. With OpenVINO, you can convert and optimize models, then deploy them across diverse Intel hardware and environments, whether on-premises, at the edge, on AI PCs, or in the cloud.
Contributors in 2026
18
+2 from 2025
Projects since 2016
50
10 a cycle on average
Cycles
5 of 11
5-cycle streak
Rank in 2026
#11
of 183, 1.6% of slots
Mentors
18
for 8 projects in 2024
Stack and topics
Each one has its own page of organizations and trends
Technologies
# Topics
Quick answers
- Is OpenVINO Toolkit in GSoC 2026?
- Yes, with 18 contributors.
- How long has it taken part?
- 5 of 11 cycles since 2016, first in 2022, with a 5-cycle streak running.
- How many contributors does it usually take?
- 10 a cycle on average, 50 in total. Its largest cycle was 2026, with 18.
- What does it build with?
- Python, C++, x86, Arm.
Accepted projects
18 projects in 2026 · All 50 projects since 2016
Synthetic Anomaly Generation
Abhay Kumar Das
Unsupervised anomaly detection models in Anomalib rely on synthetic anomalies to calibrate decision thresholds, but the current Perlin-based pipeline...
AVX2-Accelerated Collision Detection for Real-Time MPC in Humanoid Robotics
asterich
This project aims to resolve the computational bottleneck in self-collision detection within the OCS2 framework for humanoid robotics. The current...
Demonstrating integration of openhands with OpenVINO Model Server
devesh-047
This proposal aims to create a production-ready, single-command deployment integrating the OpenHands AI coding agent with the OpenVINO Model Server...
OpenVINO GenAI: Add Image-to-Video Support to LTX Video Generation Pipeline
goyaladitya05
OpenVINO GenAI currently supports text-to-video generation via the LTX pipeline but lacks image conditioning. This project adds Image-to-Video (I2V)...
OpenVINO Profiling using VTune & GTPin
Jayakaran
The existing GPU profiling workflow in OpenVino, through benchmark_app connects kernels to the model layers (primitives) and reports their execution...
Agentic AI for Predictive Maintenance using OpenVINO
JOHYEONGSEOB
This project aims to develop an agentic AI system for predictive maintenance of urban infrastructure using OpenVINO. The goal is to enable...
GGUF Reader V2 in OpenVINO GenAI for Direct GGUF Execution via Dynamic Graph Translation
KARNAV SHAH
The current GGUF reader in OpenVINO GenAI manually reconstructs model architectures by parsing metadata and building the OpenVINO model layer by...
Agentic Toolkit for AI PC with OpenVINO
Lagmator22
OVAT is a modular Python toolkit with a CLI for building and running local AI agents on Intel AIPCs. Uses OVMS as the inference backbone, adds...
Show 10 more projects
Optimize a VLA Model for Embodied Intelligence: OpenVINO Toolkit (Intel) Project #21
MDerazNasr
VLA models like unifolm-vla combine a vision-language backbone with a flow matching action head. On Intel iGPU, these models face two major...
Automated Agent System for Adding New Model Support to Optimum-Intel
Mohamed Ashraf Ibrahim
Develop an autonomous multi-agent system using LangGraph to automatically analyze Hugging Face model architectures and generate the necessary code,...
No Code AI Workflow Automation with n8n and OpenVINO Model Server for GPU and NPU
Nand-Kishore
This project integrates n8n, a no-code workflow automation platform, with OpenVINO Model Server to let users build AI-powered workflows that run on...
Web-Based AI-Assisted OS Image Builder for Intel Edge AI Suites
Neel Barke
Deploying Intel Edge AI Suites (Metro AI, Manufacturing AI, Retail AI, Robotics AI) requires users to manually configure OS images with correct...
Multi-Object Tracking Integration for OpenVINO Training Extensions (OTX)
Omkar Kabde
OTX supports 15+ detection models but has no built-in tracking.Every real-world video application (conveyor belt counting, asset monitoring,...
Optimizing Quantized Model Inference on ARM with OpenVINO
Passavee
This project aims to improve INT8 inference performance for quantized YOLO26 models on ARM devices using OpenVINO. Currently, several transformation...
Continuous Face-Detection with Automatic Device Switching on AI PCs using OpenVINO AUTO feature
Saeed Fahim
Modern AI PCs have multiple inference devices (CPU, GPU, NPU) but most applications use only one device at a time. This project aims to build a...
Auto-Labeling "Data Factory" & Edge Training Integration
Saptadip Saha
This project introduces a ‘Cold Start’ Data Factory that turns zero/one-shot prompting into a full data-to-training workflow. The core contribution...
Build a GUI Agent with Local LLM/VLM using OpenVINO for Desktop Automation
Shehroz Kashif
A lot of everyday computer tasks—like navigating applications, managing files, and configuring settings—are repetitive and require multiple manual...
Object Tracking in MP with OpenVINO Inference
Vishwa Teja Konkala
This project aims to integrate bytetrack algorithm into a Mediapipe graph using OpenVINO inference calculators. The bytetrack graph will be deployed...
Interactive Multimodal Data Explorer using Datumaro and OTX
Aarya PandeyMentored by Samet Akcay, Laurens Hogeweg
Managing and refining large-scale multimodal datasets—comprising images, text, and other data types—poses significant challenges due to the lack of...
OpenVINO GenAI provider for LangChain
bhuminjaysoniMentored by Anastasia Natarova, Przemysław Wysocki
This project aims to develop an OpenVINO GenAI extension for LangChain, enabling users to utilize OpenVINO as a backend for running language models....
Enhancing Anomalib with SOTA Anomaly Detection Benchmarks, Models and Evaluation Metrics
code-dev05Mentored by AshwinV, Samet Akcay
This project aims to enhance Anomalib by integrating state-of-the-art (SOTA) anomaly detection models, including GLASS, GLAD, MuSc, for both...
Improve OTX Classification via DoRA and Transformer Backbone.
GyuIlLimMentored by Vladi, kprokofi
This project addresses the inefficiency of full fine-tuning in classification tasks on small-scale datasets and low-resource environments within...
Optimized Serving endpoint for classic machine learning model training and inference
Harshitha ManneMentored by Dariusz Trawinski, Milosz Zeglarski
As machine learning models grow in size and complexity, there is a rising need for fast, efficient, and scalable ways to serve them in production...
Proposal for 20. Demonstrating integration of open-webui with OpenVINO Model Server
HuanliMentored by Dariusz Trawinski, Milosz Zeglarski
The goal of this project is to enable seamless integration between Open-WebUI—a comprehensive frontend platform designed for generative AI...
Traffic Intersection Monitoring System with OpenVINO
Jatin SachdevaMentored by ZhuoWu, Hassnaa
The project is designed to detect vehicles, pedestrians, and traffic violations such as red-light jumping in real time. At its core, the system uses...
Fine-tuning Vision-Language Models for Object Detection and Hierarchical Classification
Jiayu LiMentored by Samet Akcay, Rajesh Gangireddy, Laurens Hogeweg
This project aims to fine-tune Vision-Language Models (VLMs) for domain-specific tasks like object detection and hierarchical classification,...
Show 8 more projects
OpenVINO AI PC Model Training Kit
LeoHeimMentored by Shivam Basia, omeraish
This proposal outlines a detailed, structured, and actionable two-phase strategy for developing an OpenVINO AI PC Model Training Kit. The core...
Keras hub GenAI/LLM pipelines for the OpenVINO backend in Keras 3
Mohamed Ashraf IbrahimMentored by mvafin, Roman Kazantsev, Anastasiia Pnevskaia
Enable popular Keras Hub GenAI/LLM pipelines for the OpenVINO backend in Keras 3 and optimize their performance. This project focuses on implementing...
Project 18: Multimodal embeddings based on OVMS
Raghav YadavMentored by Dariusz Trawinski, dkalinowski
This project aims to optimize the calculation of multimodal embeddings (text, image, audio, video) by exposing REST API endpoints in OpenVINO Model...
Expand OpenVINO AUTO
RaghavSharma
The AI PC has multiple processing units. While most face detection models use just one unit throughout their lifetime, we try to use all the units...
Accelerating Inference of NNCF-Compressed LLMs with Triton
Riffat Khan
Large Language Models (LLMs) have demonstrated exceptional performance across a wide range of tasks, leading to their widespread adoption. However,...
OpenVINO Messenger AI-Assistant for an AI PC
Siddhant ChauhanMentored by Ethan Yang, Dmitriy Pastushenkov
Modern messaging platforms like Discord and Slack are not just used for communication but also for consuming news, discussions, and topic-specific...
Gesture Control with OpenVINO
VijayKr338Mentored by ZhuoWu, Ethan Yang
This project aims to develop a hand-gesture computer control system by porting MediaPipe’s Gesture Recognizer to OpenVINO, enhancing performance on...
Training Edge-Deployable Models via Collaborative Annotation with Humans and Large Foundation Models
Yuki WakaiMentored by Samet Akcay, Rajesh Gangireddy
This project aims to implement a framework that leverages Large Foundation Models (LFMs) for automated dataset annotation. It also aims to distill...
Porting and Optimizing OpenVINO for RISC-V Devices with Vector Extension
BHbeanMentored by Dmitry Gorokhov, Alexandra Sidorova
[Problem] The project aims to enhance the runtime performance of OpenVINO on RISC-V devices to fully leverage their power efficiency for running...
OpenVINO adapters - PyTorch adapter
Luca TamMentored by jiwaszki, Anastasia Natarova, Przemysław Wysocki
This project aims to make PyTorch and OpenVINO interchangeable. By using the Python API of OpenVINO, we will create an adapter for PyTorch, the first...
1. OpenVINO Extension for Automatic1111 Stable Diffusion WebUI
Mengbing WangMentored by anna_likholat, Mustafa Cavus
This proposal is provided by OpenVINO team. I just copy and paste here. Short description: Automatic1111 is a powerful web user interface based on...
VisionGuard: Smart Screen Time Management
InbasekaranMentored by ZhuoWu, Dmitriy Pastushenkov, Ria Cheruvu
VisionGuard is a desktop application designed for AI-enabled PCs to mitigate eye strain through real-time gaze tracking. The app builds on OpenVINO's...
Inference of Neural model in Node.js environment using OpenVINO
qxPrakashMentored by Nikolai Vishniakov, Alicja Miłoszewska
This project targets the expansion of OpenVINO's functionality within the Node.js ecosystem, the Node.js API which currently lacks comprehensive...
OpenVINO GenAI
Yongsheng XuMentored by Suyang2024-intel, Fiona Zhao
I will extend the existing OpenVINO GenAI text-to-image pipeline to support image-to-image functionality by incorporating ControlNet and utilizing...
Improve Generative AI workload performance on ARM devices with OpenVINO
mory91Mentored by Aleksandr Voron, Dmitry Gorokhov
This project aims to enhance the performance of Generative AI (GenAI) workloads on ARM devices using the OpenVINO toolkit, focusing on reducing...
AnomalibVLM: Enhancing Anomaly Detection with Vision Language Models.
Bepitic - Paco Amoros CubellsMentored by AshwinV, Dick Ameln, Samet Akcay
Problem: Traditional anomaly detection systems often struggle with limited data scenarios and can lack the ability to explain their detections....
Industrial meter reading with OpenVINO
Ashish BangwalMentored by ZhuoWu, Ethan Yang
The aim of the project is to read industrial meter with Deep Learning frameworks and OpenVINO .The project is divided into two parts. In the first...
Add ensembling methods for tiling to Anomalib
Blaž RolihMentored by Dick Ameln, Samet Akcay
When tackling the challenge of detecting defects in high-resolution images, we encounter many challenges. One significant problem is the difficulty...
Anomaly Segmentation Metrics for anomalib
Joao P C BertoldoMentored by Dick Ameln, Samet Akcay
This project proposes novel evaluation metrics for anomaly segmentation in computer vision, taking into account pixel-level and spatial information....
Add OpenVINO support to John Snow Labs Spark NLP
Rajat KrishnaMentored by Junwen Wu, Ravi Panchumarthy
Performance-focused, production-level machine learning libraries need to leverage the resources at their disposal to the maximum extent to deliver...
Showcase performance of PyTorch Image Models (Timm) with OpenVINO
Sawradip SahaMentored by Liubov Talamanova, Alexander Kozlov
My proposal aims to optimize PyTorch Image Models (Timm) using OpenVINO and NNCF libraries. The problem at hand is that these models are...
3D Jupyter Notebooks and WebGL Integration for OpenVINO
Ran PiaoMentored by Raymond Lo, Zhuo Wu
We usually need visualization, in fact, to enhance the interpretability of data or results, and facilitate the understanding of developers and users....
Object Detection demo application to run AI on ARM-based Android devices
Bo LvMentored by Raymond Lo, Junwen Wu
The openvino_contrib contains The ARM CPU Plugin project, which provides support for ARM CPUs, and Java Wrappers access The underlying infering...
Train a DL model for synthetic data generation for model optimization
Athanasios MasourisMentored by mansis, Zhuo Wu
The project is divided into two parts. The goal for the first part is to train a lightweight Deep Learning model to generate a dataset of synthetic...
No accepted proposals or progress posts from OpenVINO Toolkit contributors yet. Contributed here? Share yours.
Claim your projectNumFOCUS
27 contributors in 2026 · 11 cycles
HumanAI
15 contributors in 2026 · 3 cycles
Ste||ar group
4 contributors in 2026 · 10 cycles
API Dash
3 contributors in 2026 · 3 cycles
Data: Google Summer of Code public archive. Contributor counts are accepted projects.