allenporter/home-assistant-datasets
This package is a collection of datasets for evaluating AI Models in the context of Home Assistant.
This package helps AI model developers and researchers evaluate the performance of conversational AI agents within a smart home context. It provides synthetic home environments and device states as input, runs various AI models (like OpenAI or Google) through Home Assistant, and then collects and evaluates their responses, such as device actions or summaries. The output helps users track how different models, prompts, or tools improve over time.
191 stars. Available on PyPI.
Use this if you are developing or fine-tuning AI models for smart home voice control and need a standardized way to test their accuracy in controlling devices or understanding home states.
Not ideal if you are an end-user looking to simply install and use a smart home AI system, as this is a development and evaluation tool.
Stars
191
Forks
13
Language
Jupyter Notebook
License
—
Category
Last pushed
Feb 21, 2026
Commits (30d)
0
Dependencies
7
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/allenporter/home-assistant-datasets"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
huggingface/datasets
🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient...
little1d/SpectrumLab
A pioneering unified platform designed to systematize and accelerate deep learning research in...
J0nasW/science-datalake
Unified data lake of 293M scientific papers from 8 scholarly sources + 13 ontologies (960 GB...