Top 200 ReposEXPLORER
Browse agents, categories and pages
Back to results
Planned, not doneThe source describes an intention, not a finished result.

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.

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

The problem

How it works

Mealie stores recipes, plans meals for the week and builds shopping lists grouped by supermarket section, with an API for other apps. Its documentation describes optional AI features: an AI ingredient parser, a fallback when the normal scraper cannot read a recipe page, an Import with AI option that combines a link, pasted text and photos, recipe translation, and suggested tags and categories matched to existing ones. Providers are set in group settings and can be OpenAI, Azure or a self-hosted Ollama endpoint.

Results and limitations

The sources describe features, not a measured outcome. The documentation says the OpenAI free tier is not capable enough for Mealie, and that changing the built-in prompts can make imports less reliable.

Before you try it

With a hosted provider, recipe text and any photos you import are sent to that provider; use a self-hosted model through Ollama if you want them to stay on your network, keeping in mind that photo import needs an image-capable model. Costs depend on the provider and model. Check imported ingredient amounts and allergens before cooking or shopping. Mealie is AGPL-3.0 and deploys with Docker. Results depend on your setup and were not independently reproduced by Top 200 Repos.

Tools and repositories

Tools
Mealie (Docker) · Optional OpenAI-compatible provider or a local Ollama model
Prerequisites
A server or home machine with Docker; an AI provider only if you want the AI features.

Try it yourself: Draft a weekly meal plan from my recipe collection

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

Preview
Here are recipes from my Mealie collection with their ingredients and cooking times: [Recipe list]. Plan [Number of dinners] dinners for [Household] this week. Respect these needs: [Dietary needs]. Reuse ingredients across meals to reduce waste, keep weeknight meals under 40 minutes where possible, and use only recipes from the list. Then produce a combined shopping list grouped by supermarket section with quantities. Flag any recipe whose ingredients might conflict with the stated needs instead of assuming it is safe. Do not order anything; I will review the list and shop myself.

Double-check allergens against the original recipes before shopping.

Related videos

About ollama/ollama

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

Sources

  1. mealie-recipes/mealie README (opens in a new tab)

    Project documentation · github.com · Undated · Source checked 12 Nov 2026, 03:31 UTC

    What this source supports
    • Self-hosted recipe manager, meal planner and shopping list with a REST API backend
    • Imports recipes from a URL or by manual entry; plans meals for the coming week
    • Shopping lists organised by supermarket section; cookbooks; Docker deployment; AGPL-3.0 licence
  2. Mealie documentation: AI Providers (opens in a new tab)

    Project documentation · mealie.io · Undated · Source checked 12 Nov 2026, 03:41 UTC

    What this source supports
    • Works with OpenAI-compatible providers, including OpenAI, Azure and a self-hosted Ollama endpoint
    • AI features: ingredient parser, scraper fallback, Import with AI from links, text and photos, translation and organiser suggestions
    • Photo import needs an image-capable provider; video links need an audio provider for transcription
    • States that the OpenAI free tier is not sufficiently capable; changing prompts can make imports less reliable
Report a problem

Reported by source

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.

github.comhome-assistant/core, ollama/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
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
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
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

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