Explorando:

NVIDIA-NeMo

Search local documentation in the docs/ folder for content related to a topic

anam-org

Pluggable sample-level metadata versioning for incremental multimodal pipelines.

epiblastai

The multimodal biomedical data atlas builder

Trongdepzai-dev

Unified multimodal I/O with Gemini 3. Handle text/image/audio/video inputs, generate images (Imagen/Gemini), videos (Veo). Supports media resolution control, thinking levels, streaming.

pipecat-ai

Open Source framework for voice and multimodal conversational AI

huggingface

Transformers.js permite ejecutar modelos de aprendizaje automático de última generación directamente en JavaScript. Soporta tareas de NLP, visión por computadora y audio.

huggingface

Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in Node.js and browsers (with WebGPU/WASM) using pre-trained models from Hugging Face Hub.

dartsim

DART contribution workflow - branching, PRs, code review, dual-PR for bugfixes

muxinc

A typescript library for connecting videos in your Mux account to multi-modal LLMs.

twarogowski

Un experto en SurrealDB es un desarrollador con habilidades avanzadas en bases de datos multi-modelo y SurrealQL

Will-Barnard-WB

Multi-modal WhatsApp AI assistant that turns voice notes, images, links, and text into structured knowledge articles using a Claude agent.

huydepzai121

ffmpeg es un framework de multimedia que proporciona herramientas de línea de comandos y bibliotecas para grabar, convertir y transmitir audio y video