Stop Searching,
Start Building.

The Developer First Hub for Open-Source AI Workflows

Text Link
Blueprint of the Week
Build Your Own Timeline Algorithm

This blueprint introduces an approach to personal, local timeline algorithms that people can either run out-of-the-box or customize.

Fetch Posts & Generate Embeddings with LLM
Personalized Timeline
Mozilla.ai
Preview this Blueprint in action
00:00
00:00
Blueprint Related Content

You don’t want to miss these events!

Stay updated on key events shaping the future of open-source development and innovation.

Lumigator: AI Translation - Mar 25th, 4 PM UTC, Discord

Explore Lumigator's latest innovation!

Blueprints Brainstorm Session - Mar 26th, 5 PM UTC, Discord

Join the Mozilla.ai team exploring new ideas!

Agentic Systems - Mar 27th, 4 PM UTC, Discord

A deep dive into Automated Design of Agentic Systems.

Scaling your OS Project - Apr 4th, 5 PM UTC, Discord

Helping businesses connect with the right partners.

PyCon - Apr 6th-7th, Eisenstadt, Austria

Join the most beginner-friendly Python event!

Foss North - Apr 14th-15th, Gothenburg, Sweden

A conference covering both OS software and hardware.

OpenSearchCon - Apr 30th - May 1st, Amsterdam, Netherlands

The conference for the OpenSearch community.

This week in Open Source

Stay informed with the latest news, trends, and breakthroughs on open-source development.

Trending in the Hub this week

Explore the open-source resources we use to build our Blueprints.

Tools
Llama.cpp

Enable LLM inference with minimal setup and state-of-the-art performance on a wide range of hardware

Streamlit

Streamlit is an open-source Python framework for creating interactive data applications effortlessly.

OuteTTS

OuteTTS is an package for using OuteTTS text-to-speech models.

Datasets
Common Voice

A multilingual, crowdsourced collection of voice recordings from Mozilla.

Alpaca-gpt4

This dataset contains English Instruction-Following generated by GPT-4 using Alpaca prompts for fine-tuning LLMs.

Models
OuteTTS-0.1-350M

OuteTTS-0.1-350M is a novel text-to-speech synthesis model.

Qwen2.5-3B-Instruct-GGUF

Qwen2.5-3B-Instruct-GGUF is an instruction-tuned model that generates long-form content, and is optimized for efficient deployment via the GGUF format.

Kokoro-82M

Kokoro is an open-weight TTS model with 82 million parameters.