DepthAI (depthai-core)

A C++ library with Python bindings for interfacing with Luxonis DepthAI hardware, supporting pipelines that can span one or several devices.

Made by Luxonis, United States (checked on github.com/luxonis (opens in a new tab)).

Licenses

Code: MIT (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (MIT) at commit ed9961b (opens in a new tab), on 16 Oct 2026.
Commercial use: Yes

Builds pipelines of nodes that run on Luxonis DepthAI devices, with Python bindings included.
Lets one pipeline drive multiple devices, linking streams between them and handling device loss and reconnection.
Provides a beta namespace for experimental nodes, with on-device execution supported only on RVC4.
Offers C++ and Python examples, built with CMake and optional OpenCV and PCL.
Can be installed as a dynamic library and integrated into CMake projects via find_package.
Supports many environment variables for logging, timeouts, device filtering and crash dump collection; telemetry is on by default.

Written by Robotheca from the project's README (opens in a new tab) at commit ed9961b.

Difficulty: Intermediate
Hardware it needs, as the project states it: Linux needs libudev >= 1.0.0. Optional OpenCV 4 is needed for examples and record/replay, and optional PCL for the point cloud example.
How to start: The project's README (opens in a new tab)

Checked on GitHub on 16 Oct 2026.

No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.

Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.