Skip to content

Plumerai Documentation Overview

These pages contain technical documentation for Plumerai’s products. For company information, visit our main website and for updates visit our blog.

This page links to the most important documentation sections. You can also navigate via the sidebar on the left.

Plumerai Video Intelligence

Plumerai Video Intelligence is a complete AI stack for consumer cameras, video doorbells, and commercial security cameras. It has been deployed at scale and field-tested on millions of cameras across dozens of different SoCs.

The Video Intelligence software can be deployed on-device, on-prem, in the cloud, or in any hybrid combination of these.

It provides fast, accurate detection of people, vehicles, packages, and animals, and supports advanced features such as Familiar Face Identification (with Stranger Detection) and Vision Language Model (VLM)-based capabilities that can run on-device. The models are highly optimized for low-power hardware and can be integrated using our unified API.

Components

The following Plumerai Video Intelligence components are available:

Platforms, API, and deployment

Plumerai Video Intelligence runs on a wide variety of platforms and operating systems while using the same unified API across environments.

Depending on the compute and memory available on the target platform, the end-to-end AI pipeline can be deployed entirely at the edge, or partitioned so that some components run on-device while others run on a hub, on-prem server, or in the cloud.

Demos

We provide demo applications that run:

Plumerai Inference Engine

Plumerai Inference Engine is the world's fastest deep learning inference engine for Arm Cortex-M and other microcontrollers.

For background and benchmarks, see:

Technical documentation is available here: Plumerai Inference Engine docs.