luxonis/depthai-core

DepthAI C++ Library

What it solves

It provides a standardized software interface for developers to communicate with and control Luxonis DepthAI hardware, enabling the creation of spatial AI applications without needing to write low-level hardware drivers.

How it works

Written in C++ with Python bindings, the library allows users to define processing pipelines consisting of various "nodes" (such as image detection filters) that execute on the device. It supports multiple connection protocols including USB and TCP/IP and provides a system for managing device bootup, connectivity, and telemetry.

Who it’s for

Developers building computer vision and robotics applications using Luxonis hardware, specifically those targeting RVC2 and RVC4 platforms.

Highlights

  • Multi-language support: Offers native C++ implementation with out-of-the-box Python bindings.
  • Experimental staging: Includes a beta namespace for testing new features before they are promoted to the stable API.
  • Flexible connectivity: Supports device discovery and connection via USB, TCP/IP, and TCP-SHD.
  • Extensible configuration: Provides a wide array of environment variables to tune timeouts, logging verbosity, and device search parameters.

Related

  • Project
    luxonis/depthai-python

    Python bindings for the depthai-core C++ library, allowing developers to build AI and computer vision applications for Luxonis hardware using Python.

  • Project
    luxonis/depthai

    The depthai library is the software framework for the Luxonis platform, allowing developers to create AI and computer vision applications on Luxonis hardware.

  • Project
    luxonis/oak-examples

    A collection of demonstrations and tutorials for Luxonis OAK devices, showcasing AI vision, depth measurement, and neural network implementation using DepthAI.

  • Project
    huangjunsen0406/py-xiaozhi

    py‑xiaozhi is a Python‑based, async‑first framework for building multimodal AI assistants that can listen, speak, see, and control hardware. It offers real‑time Opus voice streaming, offline wake‑word detection, vision‑language integration, a JSON‑RPC tool server, and secure WebSocket/MQTT communication. Runs on Windows/macOS/Linux desktops and on edge boards (Raspberry Pi, Jetson Nano). Provides GUI (PySide6/QML), CLI, and GPIO modes, and a plugin system for easy extension.

  • Project
    amd/RyzenAI-SW

    A suite of tools and runtime libraries for optimizing and deploying AI inference on AMD Ryzen AI-based PCs to maximize hardware acceleration.