Golioth showcased a Bluetooth node running a gesture detection program developed by EdgeImpulse on an nRF52840. The results of the detection are sent through a Bluetooth Gateway implementation packaged as a Snap and imported onto an Qualcomm iQ9 running Ubuntu.
Today we are launching tinymcp, a Model Context Protocol (MCP) server and framework that enables any connected device to expose remote functionality to Large Language Models (LLMs).
This post and video demonstrate taking a photo with a low power camera and cellular-based microcontroller and transmitting to the cloud for processing. Rick Jen from the Microsoft Azure team shows how to accept those images and work with the Azure AI OCR service to extract useful text and store it in a database.
The Golioth OTA service can handle more than just Over-the-Air firmware upgrade. This example application demonstrates multiple-artifact releases, where a picture to be shown on the screen of an IoT device is updated using OTA.
Uploading audio from IoT devices to the Cloud is easy with Golioth. Here's everything you need to know to deliver large chunks of data from your fleet to whatever cloud service you desire, all with just one API call and one callback function.
This post walks through how to upload images from IoT devices to Golioth over CoAP using block upload. Once the image is at the server, Golioth Pipelines can route the data to the destination of your choice!
The Hugging Face Inference API makes it easy to integrate any public or private AI model with Golioth Pipelines for use-cases such as text, video, and audio analysis.
Golioth enables AI applications by pushing TF Lite model updates directly to devices. These can be stored locally and begin running without a device restart. This example showcases the Golioth SDK running on ESP-IDF.
