SenseCAP Watcher is a voice-controlled, physical AI agent for LLM-based (Crowdfunding) space monitoring

Seeed Studio has launched a Kickstarter campaign for SenseCAP Watcher, a physical AI agent capable of monitoring spaces and taking action based on events in that space. Described as “the world’s first physical LLM agent for smarter spaces,” SenseCAP Watcher leverages on-board and cloud-based technologies to “bridge the gap between digital intelligence and physical applications.”

The SenseCAP Watcher is powered by an ESP32-S3 microcontroller paired with a Himax WiseEye2 HX6538 (Cortex-M55 and Ethos-U55 microNPU) chip for image processing and vector data. It is based on the Grove Vision AI V2 module and has a form factor that is about one-third the size of an iPhone. On-board features include a camera, touchscreen, microphone, and speaker, supporting voice recognition and multi-modal sensor expansion.

It runs the SenseCraft software suite, which integrates tinyML models on the device with powerful large language models running on a remote cloud server or on a local computer, such as the Nvidia Jetson-based reComputer series or any standard PC. SenseCraft is an open-source, no-code platform that allows users to train and deploy AI models. The on-device model identifies the target, and LLM uses that information to generate precise and actionable insights.

SenseCAP Watcher Specifications:

• Wireless MCU – Dual-core microcontroller ESP32-S3 @ 240MHz, 8MB PSRAM
• AI processor – Himax HX6538 (ARM Cortex-M55 + Ethos-U55 NPU)
• Storage
  • Flash – 32MB Flash for ESP32-S3, 16MB Flash for Himax HX6538
  • microSD card slot (up to 32 GB)
• Display – 1.45” touchscreen, 412×412 resolution
• Camera – 5MP OmniVision OV5647 camera module, 120° field of view
• Audio – 1W speaker output, mono microphone
• Network – Wi-Fi 2.4 GHz, Bluetooth 5 (LE) both via ESP32-S3
• USB – 1x USB-C (power only), 1x USB-C (power and programming)
• Expansion – 1x Grove I2C interface, 2x 4 female connectors (1xI²C, 2x GPIO, 2x GND, 1x 3.3V_OUT, 1x 5V_IN)
• Miscellaneous – Built-in Wi-Fi and BLE antenna, scroll wheel, 1x RGB LED for signaling, reset button
• Power
  • 5V DC power supply
  • 3.7V 400mAh lithium-ion battery
• Dimensions – to be determined
• Operating temperature – 0 to 45°C

SenseCAP Watcher can receive commands via Push to Talk (scroll wheel/button) and the SenseCraft mobile app. It works well with other systems and can be connected to Home Assistant and Node-Red flows. It is compatible with Raspberry Pi and Arduino boards, ESP32 series modules and boards, and has a Grove connector for expanding with over 100 sensors.

Watcher is fully open-source, but as of this writing, there is no active repository. Potential applications include smart home automation, healthcare monitoring, environmental monitoring, pet monitoring, and security surveillance.

The SenseCAP Watcher campaign is currently live on Kickstarter and has surpassed its funding goal with just a few days to go. The device itself is currently priced at $89, with a one-month free trial of the SenseCraft AI service ($6.90 value) for users who choose the remote LLM option. More information about the product can be found on the wiki page.

While it shares some similarities with the Rabbit R1, which received mixed reviews, the SenseCAP Watcher is more affordable, offers local LLM options, and looks more promising overall.

Support CNX Software! Donate with cryptocurrencies, become a Patron on Patreon or purchase goods on Amazon or Aliexpress