README.md

---
title: Mozilla.ai
emoji: 🤖
colorFrom: green
colorTo: red
sdk: static
pinned: false
---

# Mozilla.ai

## What we're working on:

### 🤖Agents

- [any-agent](https://github.com/mozilla-ai/any-agent): A single interface to different Agent frameworks.

### 🐊 Lumigator

[Lumigator](https://github.com/mozilla-ai/lumigator) is an open-source platform developed to help users select the most suitable language model for their specific needs

### 📘 Blueprints

Blueprints are customizable workflows that help developers build AI applications using open-source tools and models. See our collection of Blueprints below:

- [Document-to-podcast](https://github.com/mozilla-ai/document-to-podcast): Convert input documents into a podcast featuring multiple speakers.

- [Document-to-Markdown](https://github.com/mozilla-ai/document-to-markdown): Transform documents into markdown format with Docling, developed in collaboration with [EleutherAI](https://www.eleuther.ai/).

- [Structured-QA](https://github.com/mozilla-ai/structured-qa): A simple LLM workflow to answer questions based on structured documents.

- [Speech-To-Text](https://github.com/mozilla-ai/speech-to-text): Transcribe audio files using Speaches, developed in collaboration with [EleutherAI](https://www.eleuther.ai/).

- [Speech-To-Text Finetune](https://github.com/mozilla-ai/speech-to-text-finetune): Create your own Speech-to-Text model tailored for your specific language & use-case.

- [Fake-Audio-Detection](https://github.com/mozilla-ai/fake-audio-detection): Train and deploy an ML model that detects synthetic audio, developed in collaboration with [UncovAI](https://uncovai.com/)

- [OpenStreetMap AI Helper](https://github.com/mozilla-ai/osm-ai-helper): Map Features in OpenStreetMap with Computer Vision.

- [Federated Finetuning](https://github.com/mozilla-ai/federated-finetuning): Finetune a language model with federated AI, developed in collaboration with [Flower](https://flower.ai/).

- [Build Your Own Timeline Algorithm](https://github.com/mozilla-ai/byota): An approach to personal, local timeline algorithms that people can either run out-of-the-box or customize.