This article details how to set up a weather report on a Home Assistant dashboard using a local LLM (Ollama) for more user-friendly summaries and clothing suggestions, avoiding cloud-based services for privacy reasons. It covers the setup process, prompt engineering, and hardware considerations.
Stream Assist is a Home Assistant integration that allows users to turn almost any camera and speaker into a local voice assistant, offering privacy and customization benefits over commercial solutions like Alexa or Nest. It uses components like Stream, Assist pipeline, openWakeWord, Whisper, and Piper to process voice commands and control smart home devices.
Seeed Studio has revealed the TRMNL 7.5" DIY Kit, a 7.5-inch e-ink display kit compatible with Home Assistant and Arduino, offering a cost-effective solution for smart home enthusiasts. It includes a 7.5-inch 800x480 monochrome e-ink display, XIAO ESP32-S3 PLUS driver board, 2000 mAh rechargeable battery, and 10cm FPC extension cable. It is currently available for preorder for under $45.
AI-On-The-Edge-Cam is an ESP32-S3 board with a 2MP camera, microSD card, WiFi, BLE, and PoE Ethernet connectivity designed to digitize legacy utility meters such as water meters, gas meters, or electricity meters that require manual onsite reading. It supports Tensorflow Lite, has a web interface, and integrates with Home Assistant.
The author details their transition from Google Home to Home Assistant with a local LLM, highlighting the benefits of increased control, customization, and functionality. They discuss using Home Assistant's 'Okay Nabu' voice control, experimenting with display solutions like tablets and ESP32 devices, and the advantages of integrating a local LLM for more contextual and powerful interactions.
This article explores how you can use Node-RED, a visual programming tool, to enhance the functionality of your smart home. It provides examples of projects such as RFID-based access control, automated window blinds, thermostat, sprinkler systems, and light control, showing how Node-RED can simplify and expand home automation.
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.
A tag reader for Home Assistant, built using ESPHome and PN532 NFC module, with a GPL-3.0 license.
Learn how to create a low-cost, AI-powered personal assistant using Raspberry Pi and open-source software. The assistant can answer questions, play music, and control smart home devices.
