Hacktoberfest 2026 week 2 - CartaClara

What I Built

CartaClara helps restaurants turn a Spanish-language menu into a QR menu in English, French, and German. It suggests translations and tags each dish with the 14 EU allergens, then lets the restaurant owner review and confirm every dish before publishing.

It’s designed for independent restaurants that want to serve international guests without translating and maintaining multiple menus by hand. A restaurant could pay for the time saved and an easier-to-update multilingual menu. Allergen information still needs to be checked by the restaurant; the suggestions aren’t a substitute for that review.

Demo

There isn’t a public demo deployed yet. You can run CartaClara locally by following the setup instructions in the repository README. With the default mock backend, you can try the workflow without configuring a model.

Code

https://github.com/kit57/side_hustle_hacktoberfest2026

How I Built It

CartaClara uses an open-weight language model to suggest dish translations and allergen tags. The project includes a Tinker fine-tuning pipeline for Spanish dishes, plus mock and OpenAI-compatible backends—including a local open-weight model served through Ollama. The prompt and output format are shared between inference and training, and the evaluation script compares the base model with the fine-tuned checkpoint on held-out dishes.

The app also supports an optional restaurant glossary: when an owner corrects and confirms a suggestion, that correction can be saved and used for that restaurant’s future menus.

Why Does Open Innovation Matter?

Restaurants need to trust and correct the menu suggestions, especially when allergen information is involved. Building on open-weight models gives the project room to experiment with Spanish food terminology, fine-tune for the task, and offer different ways to run a model—including a local OpenAI-compatible server—instead of tying the product to one closed model API.

Open development also makes the training examples, evaluation approach, and application code available for others to inspect and improve.

Prize Categories

Tinker, BACKBOARD

Comments

[Harun - solo dev]

laura, this is a highly practical and deeply necessary application of open-weight models. translating menus is common, but coupling it with eu allergen tagging makes this a high-stakes, high-value tool.

two architectural choices here are absolutely brilliant:

1. the optional restaurant glossary: this is a lightweight, elegant form of domain-specific memory (essentially a micro-rag). allowing the system to learn and persist a specific establishment's preferred terminology over time is exactly how you move from a generic tool to an indispensable workflow.
2. mandatory human-in-the-loop for allergens: making it clear that the llm assists but does not autonomously decide on health-critical data is the exact right ethical and safety boundary.

leveraging tinker for spanish food terminology fine-tuning, while keeping the inference flexible (ollama/openai-compatible), is the perfect way to avoid vendor lock-in and ensure data privacy for independent restaurants.

fantastic hacktoberfest submission. keeping the training data and evaluation open is exactly how we build trustworthy, localized ai. 🐯🍽️

[Laura Valencia Gracia]

Thank you for your kind words!