insight-platform/Savant
Python Computer Vision & Video Analytics Framework With Batteries Included
Savant helps computer vision and video analytics engineers build high-performance, real-time applications that process live video streams or recorded footage. It takes video inputs and applies AI models for tasks like object detection or facial blurring, producing analytical data or modified video outputs. This is for engineers and solution architects tasked with deploying robust, scalable computer vision systems.
787 stars. Actively maintained with 8 commits in the last 30 days.
Use this if you need to build production-ready, high-performance computer vision or video analytics applications leveraging Nvidia hardware, for both edge and data center deployments.
Not ideal if your project doesn't involve Nvidia GPUs or DeepStream, or if you're looking for a general-purpose machine learning framework without a focus on real-time video processing.
Stars
787
Forks
73
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 11, 2026
Commits (30d)
8
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/insight-platform/Savant"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
roboflow/supervision
We write your reusable computer vision tools. 💜
PeculiarVentures/GammaCV
GammaCV is a WebGL accelerated Computer Vision library for browser
ROCm/MIVisionX
MIVisionX toolkit is a set of comprehensive computer vision and machine intelligence libraries,...
cleanlab/cleanvision
Automatically find issues in image datasets and practice data-centric computer vision.
aisingapore/PeekingDuck
A modular framework built to simplify Computer Vision inference workloads.