# stereolabs/zed-sdk

⚡️The spatial perception framework for rapidly building smart robots and spaces

Repository: https://github.com/stereolabs/zed-sdk
Canonical: https://ross.abutalabs.com/products/zed-sdk
Homepage: https://stereolabs.com
Language: C++
License: MIT
License Family: permissive
Topics: zed-camera, stereo-vision, slam, 3d-reconstruction, computer-vision, depth-camera, depth-estimation, human-pose-estimation, machine-learning, object-detection, perception, point-cloud, realtime, stereo, stereolabs, zed, zed-x, zed2
Last push: 2026-06-18T15:04:44+00:00

## Health v2 (maintenance only)
Score: 91/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 88, release rhythm 89, longevity 100
- inputs: {"age_days": 3437, "days_push": 76, "days_rel": 76, "gap_med": 30, "n_releases_24m": 16}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1229, forks 506 (observed 2026-08-28T04:04:03.611029+00:00)

## What it is
The ZED SDK is a cross-platform spatial perception library for Stereolabs ZED stereo cameras, providing depth sensing, SLAM, 3D reconstruction, object detection, and human pose estimation. This repository hosts tutorials and code samples demonstrating the SDK API across multiple languages.

## Use cases
- build a robot that navigates using stereo depth and SLAM
- estimate depth maps and point clouds from a stereo camera
- reconstruct 3D meshes of indoor spaces in real time
- detect and track people with human pose estimation
- run object detection fused with depth on a Jetson device
- stream and record stereo video with H264/H265 encoding

## When to choose
- you are using a Stereolabs ZED camera and need depth, mapping, or AI perception
- you want GPU-accelerated spatial perception for robotics or AR on Jetson or desktop GPUs
- you need production-ready SLAM and 3D reconstruction without building it from scratch

## When to avoid
- you use a non-ZED camera, since the SDK is tied to Stereolabs hardware
- you need a CPU-only solution, as the SDK depends on NVIDIA GPUs
- you only need basic camera capture without depth or perception features

## Facets
- artifact type: library
- maturity: active
- function: computer-vision, machine-learning, image-processing, sdk, simulation
- domain: robotics, computer-vision, autonomous-vehicles, artificial-intelligence
- platform: cpp, python, windows, cross-platform
- tags: stereo-vision, slam, depth-estimation, 3d-reconstruction, zed-camera, point-cloud, object-detection, human-pose-estimation, spatial-perception, embedded-vision, linux, gpu, docker

## Member repositories
- stereolabs/zed-sdk (main) score 91

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:03.611029+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 2026-08-30T06:15:08.590348+00:00, confidence not recorded.
  - readme: https://github.com/stereolabs/zed-sdk (fetched 2026-08-28T04:04:03.611029+00:00, sha 56a09bb61394)
  - homepage: https://stereolabs.com (fetched 2026-08-29T12:22:39.061103+00:00, sha 48b027f50336)
- Data as of 2026-08-30T08:39:29.467469+00:00.