🐿️ A collection of projects focused on connectivity that enable building cross-device experiences.

A novel data compression framework

As we migrated from Github to Docusaurus, I wanted to share the script, the AI and I developed, so you can start from there and save time and (AI) costs

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

A header only library for creating and validating json web tokens in c++

The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.

Blazingly fast LLM inference.

Documentation for the Model Context Protocol (MCP)

The P programming language.

The C JSON Web Token Library +JWK +JWKS

A C++ header-only HTTP/HTTPS server and client library

MongoDB Community Kubernetes Operator

OAuth 2.x and OpenID Connect C library

Hyrise is a research in-memory database.

Public repository of the QuickJS Javascript Engine.

Speech To Speech: an effort for an open-sourced and modular GPT4-o

MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.

GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

ObjectBox Sync Documentation

Official Documentation for ObjectBox, the object and vector database

C++11/14/17 std::optional with functional-style extensions and reference support

🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

An open source implementation of CLIP.

Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/

A comparative, extendable benchmarking suite for C and C++ hash-table libraries.

A custom RAG pipeline for multi-document QA from PDF/DOCX documents, in Android

A self-organizing file system with llama 3

LLM training in simple, raw C/CUDA