# Prokyber AI-on-the-Edge-Cam

> Open-source ESP32-S3 camera board with PoE, microSD, and Stemma QT designed for AI-powered utility meter reading using the AI-on-the-edge-device firmware with TensorFlow Lite inference.

## Quick Facts

- **Brand:** Prokyber
- **Board Type:** dev-board
- **Price:** ~$33
- **Product Readiness:** consumer
- **CPU:** ESP32-S3-N16R8
- **CPU Architecture:** Xtensa LX7 dual-core
- **RAM:** 512KB SRAM
- **PSRAM:** 8MB OPI
- **Flash:** 16MB
- **USB:** USB-C
- **Power:** 5V + PoE
- **Operating Voltage:** 3.3V
- **Antenna:** U.FL/IPEX
- **SD Card:** microSD

## Connectivity

- **Wifi:** 802.11 b/g/n
- **Bluetooth:** BLE 5.0
- **Zigbee:** false
- **Ethernet:** 10/100 Mbps PoE

## Open Source

- **Firmware:** Yes
- **Schematics:** Yes
- **PCB Layout:** No
- **License:** CERN-OHL-P-2.0

## Compatible Firmware

ai-on-the-edge-device, esphome, arduino, platformio

## Use Cases

- utility-meter-reading
- smart-metering
- ai-image-recognition
- computer-vision
- iot-sensor-node
- edge-computing
- data-logging
- remote-monitoring
- wired-networking
- poe-iot-gateway
- timelapse-photography
- environmental-monitoring

## Components

- **ESP32-S3** (mcu): Espressif ESP32-S3 dual-core Xtensa LX7 SoC at 240MHz with 16MB flash, 8MB PSRAM, WiFi 802.11 b/g/n, BLE 5.0, and AI vector extensions for TensorFlow Lite inference. — [Datasheet](https://openhardware.directory/r?to=https%3A%2F%2Fwww.espressif.com%2Fsites%2Fdefault%2Ffiles%2Fdocumentation%2Fesp32-s3_datasheet_en.pdf&ref=openhardware.directory&product=ai-on-the-edge-cam&source=md-export)
- **W5500** (ethernet-phy): Hardwired TCP/IP embedded Ethernet controller with SPI interface supporting 10/100 Mbps, 8 simultaneous sockets, and 32KB internal buffer. — [Datasheet](https://openhardware.directory/r?to=https%3A%2F%2Fdocs.wiznet.io%2Fimg%2Fproducts%2Fw5500%2FW5500_ds_v110e.pdf&ref=openhardware.directory&product=ai-on-the-edge-cam&source=md-export)
- **SI3404** (poe-controller): IEEE 802.3af/at compliant PoE powered device controller with integrated bridge rectifier driver and DC-DC converter support for up to 25.5W extraction from Ethernet cables. — [Datasheet](https://openhardware.directory/r?to=https%3A%2F%2Fwww.silabs.com%2Fdocuments%2Fpublic%2Fdata-sheets%2Fsi3404-datasheet.pdf&ref=openhardware.directory&product=ai-on-the-edge-cam&source=md-export)
- **OV2640** (camera): 2-megapixel UXGA (1600x1200) CMOS image sensor with built-in JPEG compression engine, DVP parallel interface, and up to 15fps at full resolution. — [Datasheet](https://openhardware.directory/r?to=https%3A%2F%2Fwww.uctronics.com%2Fdownload%2FOV2640_DS.pdf&ref=openhardware.directory&product=ai-on-the-edge-cam&source=md-export)
- **WS2812B** (led-driver): Four WorldSemi WS2812B individually addressable RGB LEDs providing configurable illumination for consistent camera image capture in varying lighting conditions. — [Datasheet](https://openhardware.directory/r?to=https%3A%2F%2Fcdn-shop.adafruit.com%2Fdatasheets%2FWS2812B.pdf&ref=openhardware.directory&product=ai-on-the-edge-cam&source=md-export)
- **stemma-qt** (connector): JST SH 4-pin I2C connector compatible with Adafruit Stemma QT and SparkFun Qwiic ecosystems for plug-and-play sensor expansion. — [Datasheet](https://openhardware.directory/r?to=https%3A%2F%2Flearn.adafruit.com%2Fintroducing-adafruit-stemma-qt%2Fwhat-is-stemma-qt&ref=openhardware.directory&product=ai-on-the-edge-cam&source=md-export)

## Protocols

- **SPI**
- **I2C**
- **UART**
- **SDIO**
- **TCP/IP**
- **HTTP**
- **MQTT**

## Available Software

- **[AI-on-the-edge-device]()** (open-source)
- **[ESPHome]()** (open-source)
- **[Arduino]()** (open-source)
- **[PlatformIO]()** (open-source)

## Description

## Overview

The Prokyber AI-on-the-Edge-Cam is a purpose-built open-hardware board designed to run the AI-on-the-edge-device firmware, which uses TensorFlow Lite to digitize analog utility meters for water, gas, and electricity. Built around the ESP32-S3 N16R8 with 16MB flash and 8MB PSRAM, it provides enough memory and processing power for on-device neural network inference directly at the edge, eliminating the need for cloud-based image processing.

The board integrates Power over Ethernet via a WIZnet W5500 controller and Silicon Labs SI3404 PoE PD controller, enabling single-cable deployment where the same Ethernet cable provides both network connectivity and power. Four WS2812B addressable LEDs provide configurable camera illumination for consistent image capture in any lighting condition. A microSD card slot stores configuration, captured images, and firmware updates, while a Stemma QT (Qwiic-compatible) I2C connector allows easy expansion with external sensors like temperature or humidity modules.

With an ultra-low sleep current under 25 microamps and active current of only 200mA, the board is optimized for battery-powered deployments as well. Two 18650 cells can power daily meter readings for approximately one year. An optional LoRa shuttle shield adds LoRaWAN connectivity for transmitting readings in locations without Ethernet infrastructure. The hardware design is fully open-source under the CERN-OHL-P 2.0 license with schematics published on GitHub.

## Where to Buy

- [Tindie](https://openhardware.directory/r?to=https%3A%2F%2Fwww.tindie.com%2Fproducts%2Fallexok%2Fai-on-the-edge-cam-esp32-s3-with-poe-sd-camera%2F&ref=openhardware.directory&product=ai-on-the-edge-cam&source=md-export) — $33.00

## Resources

- [product](https://openhardware.directory/r?to=https%3A%2F%2Fwww.tindie.com%2Fproducts%2Fallexok%2Fai-on-the-edge-cam-esp32-s3-with-poe-sd-camera%2F&ref=openhardware.directory&product=ai-on-the-edge-cam&source=md-export)
- [github](https://openhardware.directory/r?to=https%3A%2F%2Fgithub.com%2Fprokyber%2Fai-on-the-edge-cam-hw-description&ref=openhardware.directory&product=ai-on-the-edge-cam&source=md-export)
- [schematics](https://openhardware.directory/r?to=https%3A%2F%2Fgithub.com%2Fprokyber%2Fai-on-the-edge-cam-hw-description%2Fblob%2Fmain%2FSchematic_ai-on-the-edge-cam_2025-08-27.pdf&ref=openhardware.directory&product=ai-on-the-edge-cam&source=md-export)
- [wiki](https://openhardware.directory/r?to=https%3A%2F%2Fjomjol.github.io%2FAI-on-the-edge-device-docs%2F&ref=openhardware.directory&product=ai-on-the-edge-cam&source=md-export)

## Tags

`esp32-s3`, `poe`, `camera`, `ai`, `meter-reading`, `tensorflow-lite`, `open-hardware`, `ov2640`, `w5500`, `stemma-qt`, `ws2812b`, `lorawan`, `cern-ohl-p`

## Images

![Prokyber AI-on-the-Edge-Cam](https://nbg1.your-objectstorage.com/openhardware-directory/entities/ai-on-the-edge-cam/3d0b2b6ee960.png)

---
[View full device page](https://openhardware.directory/devices/ai-on-the-edge-cam)