insight-platform/Savant

Python Computer Vision & Video Analytics Framework With Batteries Included

61
/ 100
Established

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.

video-analytics computer-vision real-time-processing edge-ai smart-cameras
No Package No Dependents
Maintenance 17 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

787

Forks

73

Language

Python

License

Apache-2.0

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.