Stars
High performance build system for Windows, OSX and Linux. Supporting caching, network distribution and more.
Model Context Protocol Servers
Model Context Protocol (MCP) Server for the JFrog Platform API, enabling repository management, build tracking, release lifecycle management, and more.
Incredibly fast JavaScript runtime, bundler, test runner, and package manager – all in one
Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
A curated collection of fun and creative examples generated with Nano Banana🍌, Gemini-2.5-flash-image based model. We also release Nano-consistent-150K openly to support the community's development…
LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG paradigm.
This repo powers my blog experiment where ChatGPT manages a real-money micro-cap stock portfolio.
StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.
lightweight, standalone C++ inference engine for Google's Gemma models.
Securing open-source package ecosystems by originating, validating, and augmenting build attestations.
tome is a powerful tool for script organization, sharing, and testing.
A TTS model capable of generating ultra-realistic dialogue in one pass.
[CVPR 2025] Official PyTorch implementation of "EdgeTAM: On-Device Track Anything Model"
A powerful AI coding agent. Built for the terminal.
LiteRT, successor to TensorFlow Lite. is Google's On-device framework for high-performance ML & GenAI deployment on edge platforms, via efficient conversion, runtime, and optimization
Infinite Photorealistic Worlds using Procedural Generation
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
Building an assistant for Boletin Oficial del Estado (BOE) using Retrieval Augmented Generation (RAG)
On-device AI across mobile, embedded and edge for PyTorch
Official Pytorch Implementation for "VidToMe: Video Token Merging for Zero-Shot Video Editing" (CVPR 2024)
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.