PearPass is an open-source, privacy-first password manager with peer-to-peer syncing and end-to-end encryption.

QVAC Fabric: cross-platform LLM inference and fine-tuning, optimized for edge devices and heterogenous GPUs

WDK is a modular plug-in framework designed to simplify multi-chain wallet development. This package orchestrates all WDK modules.

PearPass is an open-source, privacy-first password manager with peer-to-peer syncing and end-to-end encryption.

PearPass is an open-source, privacy-first password manager with peer-to-peer syncing and end-to-end encryption.

Open-source local AI SDK - run AI on-device with no cloud, no API keys. Supports GGUF, RAG, image, music, and video generation, speech-to-text, P2P inference, and more. Cross-platform: Linux, macOS…

Everything required to run your own Base node

Empowering everyone to build reliable and efficient software.

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

The agent engineering platform.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Collection of comprehensive TypeScript libraries for Interaction with the Ethereum JSON RPC API and utility functions.

The Advanced API Python SDK is a Python package that makes it easy to interact with the Coinbase Advanced API. The SDK handles authentication, HTTP connections, and provides helpful methods for int…

An index of 18F and TTS work in the national security & intelligence space

Code for the Neural GPU model originally described in "Neural GPUs Learn Algorithms"

Code for the paper "On First-Order Meta-Learning Algorithms"

A reverse proxy that provides authentication with Google, Github or other provider

Code for the paper "Emergent Complexity via Multi-agent Competition"

Training Sonic with RLlib

Efficient GPU kernels for block-sparse matrix multiplication and convolution

PyTorch package for the discrete VAE used for DALL·E.

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

Production-Grade Container Scheduling and Management

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering

The official .NET library for the OpenAI API

This is a simple demonstration of more advanced, agentic patterns built on top of the Realtime API.

The official Java library for the OpenAI API

The official Go library for the OpenAI API

Instructions on how to use the Realtime API on Microcontrollers and Embedded Platforms