# NVIDIA-AI-IOT/deepstream_python_apps

DeepStream SDK Python bindings and sample applications

Repository: https://github.com/NVIDIA-AI-IOT/deepstream_python_apps
Canonical: https://ross.abutalabs.com/products/deepstream_python_apps
Language: Jupyter Notebook
License: NOASSERTION
License Family: other
Last push: 2026-04-01T08:46:09+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 75, release rhythm 15, longevity 100
- inputs: {"age_days": 2500, "days_push": 154, "days_rel": 352, "gap_med": 332, "n_releases_24m": 2}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1881, forks 537 (observed 2026-08-28T04:05:48.668400+00:00)

## What it is
Python bindings and sample applications for NVIDIA's DeepStream SDK, built with Pybind11 and Gst Python for constructing video analytics pipelines. It provides access to DeepStream metadata and a collection of example apps for AI-powered video processing on NVIDIA hardware.

## Use cases
- build video analytics pipelines in python with deepstream
- run object detection on rtsp camera streams on jetson
- access deepstream metadata from python
- process video with nvidia gpu inference in gstreamer
- learn deepstream through sample applications
- build custom python bindings for deepstream metadata structures

## When to choose
- you use NVIDIA DeepStream SDK and want to build pipelines in Python
- you need Python access to DeepStream metadata on Ubuntu with NVIDIA GPUs or Jetson
- you want reference sample apps for DeepStream video analytics

## When to avoid
- you need a supported pip wheel - bindings are deprecated from DeepStream 9.0 onward
- you are not on Ubuntu 24.04 with DeepStream 9.0 and Python 3.12
- you want a pure-Python video framework without NVIDIA hardware dependencies

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, video-processing, machine-learning, sdk, developer-tools
- domain: computer-vision, artificial-intelligence, developer-tools, iot
- platform: python, embedded
- tags: deepstream, gstreamer, nvidia, python-bindings, video-analytics, pybind11, sample-applications, video, linux, gpu

## Member repositories
- NVIDIA-AI-IOT/deepstream_python_apps (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:48.668400+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:13:57.714402+00:00, confidence not recorded.
  - readme: https://github.com/NVIDIA-AI-IOT/deepstream_python_apps (fetched 2026-08-28T04:05:48.668400+00:00, sha 9681bbaa1c97)
- Data as of 2026-08-30T08:39:29.467469+00:00.