Top 200 ReposEXPLORER
Browse agents, categories and pages
Back to results
Reported by sourceThe source says this happened. Top 200 Repos has not reproduced it.

Control smart-home devices with a local LLM voice assistant

Connect Home Assistant to a local Ollama model as its conversation agent so you can ask it to control exposed devices privately.

Try the promptRead the original (opens in a new tab)

The problem

How it works

Home Assistant is local-first home automation software. Its Ollama integration adds a conversation agent backed by a model on your own Ollama server; you set the server URL, model, instructions and context size. Enabling the experimental device-control tools lets the model act only on entities you have exposed to voice assistants.

Results and limitations

The docs present this as a way to talk to your home through a locally hosted model, while marking device control as experimental.

Before you try it

Only tool-capable models can control devices, smaller models make more mistakes, and the docs suggest exposing fewer than 25 entities while experimenting. Larger context windows use more server RAM. Results depend on your setup and were not independently reproduced by Top 200 Repos.

Tools and repositories

Tools
Home Assistant · Ollama
Prerequisites
A running Home Assistant instance and a network-reachable Ollama server with a tool-capable model.

Try it yourself: Set up a local home assistant agent

Fill the fields to adapt the prompt. Empty fields stay as visible [placeholders].

Preview
Help me connect Home Assistant to my Ollama server at [Ollama server URL] using [Model] as a conversation agent. Confirm the model supports tools before enabling device control. Propose a short list of entities to expose, at most [Entity limit], drawn from [Rooms], and leave locks, alarms and garage doors unexposed unless I explicitly add them. Draft the agent instructions in plain language, including that it must confirm before turning off heating or opening anything. Show me every setting before I apply it, then suggest five test phrases and what the correct result of each should be.

Keep security-critical devices out of the exposed list until you trust how the model behaves.

Related videos

About ollama/ollama

Independent creators. Listing a video implies no endorsement, sponsorship or partnership.

Sources

  1. home-assistant/core README (opens in a new tab)

    Project documentation · github.com · Undated · Source checked 9 Nov 2026, 22:23 UTC

    What this source supports
    • Open source home automation focused on local control and privacy
    • Runs on modest hardware such as a Raspberry Pi
  2. Ollama integration (opens in a new tab)

    Project documentation · home-assistant.io · Undated · Source checked 9 Nov 2026, 22:24 UTC

    What this source supports
    • Adds a conversation agent backed by a local Ollama server
    • Experimental device control limited to entities exposed to voice assistants
    • Only tool-capable models can control Home Assistant
    • Suggests exposing fewer than 25 entities while experimenting
Report a problem

Reported by source

Extract invoice fields locally with a vision model on Ollama

Stephen Sebastian replaced a paid cloud OCR API with Gemma 4 E4B on Ollama to pull date, amount and description from contractor invoice photos on his laptop.

dev.toollama/ollama
Reported by source

Run an open-weight model locally and call it from your code

Install Ollama, pull an open model and call it through the local REST API so prompts stay on your machine.

github.comollama/ollama
Planned, not done

Import recipes and plan the week's meals in self-hosted Mealie with an AI provider

Mealie is a self-hosted recipe manager and meal planner; with an OpenAI-compatible provider it can turn web pages, pasted text or photos into recipes, parse ingredients and suggest tags.

github.comollama/ollama
Planned, not done

Auto-tag receipts and bills in Paperless-ngx with paperless-ai

paperless-ai suggests titles, tags, correspondents and dates for documents in a Paperless-ngx archive, using a local Ollama model or a cloud LLM, with manual review and undo.

github.comollama/ollama
Planned, not done

Record and summarise meetings on your own machine with Meetily

Meetily records calls, transcribes them on the device with Whisper or Parakeet, and writes summaries with a local Ollama model or a cloud model you pick.

github.comollama/ollama
Planned, not done

Turn public competitor pages into a structured market scan with Crawl4AI

Crawl4AI crawls pages into clean Markdown and extracts fields such as product names and prices with CSS or XPath schemas or an LLM, giving an agent tidy input for a market or competitor comparison.

github.comunclecode/crawl4ai, ollama/ollama