kyegomez/Gemini

The open source implementation of Gemini, the model that will "eclipse ChatGPT" by Google

55
/ 100
Established

This project offers an early open-source version of a multi-modal AI model, capable of processing and generating content across different types of data. It takes in text, images, and audio, and processes them together to produce various outputs, including new images. The intended users are AI researchers and engineers who want to experiment with or build upon cutting-edge multi-modal AI architectures.

460 stars.

Use this if you are an AI researcher interested in implementing and experimenting with transformer models that integrate text, image, and audio inputs for generative tasks.

Not ideal if you need a production-ready, fully trained multi-modal AI model for immediate application, as this is an early-stage implementation requiring significant development and training.

AI Research Multi-Modal AI Generative AI Deep Learning Transformer Models
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

460

Forks

62

Language

Python

License

MIT

Last pushed

Feb 02, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/kyegomez/Gemini"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.