Jean-Luc Aufranc writes about the CamThink NeoEyes NE302, a compact vision camera designed for developers and makers. Utilizing an Arm Cortex-M55 MCU with an integrated Neural-ART NPU, the device supports high-performance edge tasks like object detection and pose estimation while maintaining efficient power consumption through a dedicated STM32U073 "WakeCore" controller. Unlike its predecessor, this version lacks a battery and relies on USB-C for 5V power delivery only.
- Features an ST Neural-ART NPU capable of up to 600 GOPS
- Supports WiFi 6 and Bluetooth 5.3 LE connectivity
- Includes hardware acceleration for H.264 and JPEG encoding (up to 1080p @ 30fps)
- Utilizes an OS04C10 4MP camera sensor with M12 lens mount options
- Offers a Web UI for real-time preview and model execution
- Features an ST Neural-ART NPU capable of up to 600 GOPS
- Supports WiFi 6 and Bluetooth 5.3 LE connectivity
- Includes hardware acceleration for H.264 and JPEG encoding (up to 1080p @ 30fps)
- Utilizes an OS04C10 4MP camera sensor with M12 lens mount options
- Offers a Web UI for real-time preview and model execution
The Metis M.2 card is a high-performance AI inference accelerator designed for constrained, small-footprint devices. Powered by a single quad-core Metis AIPU, it enables state-of-the-art AI capabilities including multi-camera inference and support for multiple independent parallel neural networks. The card offers seamless integration via the Voyager SDK and maintains high prediction accuracy through advanced quantization tools.
MimiClaw is an OpenClaw-inspired AI assistant for ESP32-S3 boards, acting as a gateway between Telegram and Claude LLM to control hardware via chat. It's written in C, requires minimal resources (16MB flash, 8MB PSRAM), and offers low-power operation (0.5W).
This project guides you through building a portable AI agent using the UNIHIKER K10, Xiaozhi AI firmware, and a custom 3D-printed case. It covers hardware overview, firmware flashing, console setup, and 3D printing services.
Sipeed NanoCluster is a palm-sized cluster board with seven slots for Raspberry Pi CM4/CM5, Sipeed LM3H, and/or Sipeed M4N system-on-modules. It features a RISC-V Gigabit switch, independent UART and power control for each module, and supports up to 60W USB-C PD or PoE.
The article announces the launch of the OpenMV AE3 and N6 cameras on Kickstarter. These cameras feature onboard AI acceleration for computer vision applications, making them suitable for various Edge AI tasks. The AE3 is a compact, efficient device with dual NPU cores, while the N6 offers higher performance with a larger form factor and more features.
Seeed Studio has introduced two new mmWave sensor kits, designed for edge AI detection of falls and heartbeats respectively. These kits are powered by the company's XIAO ESP32C6 development board and pre-installed edge-AI algorithms.
