Official implementation of the paper: Sub-JEPA: Subspace Gaussian Regularization for Stable End-to-End World Models.

Unreal Engine smooth voxel terrain plugin

Minimal library for distributed python work. Can efficiently run CPU and GPU tasks across 100s of machines.

The best way to get AI coding agents to solve hard problems in complex codebases.

Hierarchical Reasoning Model Official Release

Efficient optimizers

Beads - A memory upgrade for your coding agent

Curated, CC0 reference hub for 3D, VFX, and game dev. 3,400+ tools, assets, and tutorials across 12 sections. Searchable, filterable, free.

The agent that grows with you

Hermes Agent 从入门到精通 · 橙皮书系列 · Nous Research 开源 AI Agent 框架实战指南

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

AI agents running research on single-GPU nanochat training automatically

Unreal Engine Plugin for Lua APIs implementation

A comprehensive guide to setting up NVIDIA Prime Offloading alongside GPU passthrough (VFIO, without rebooting) and Looking Glass on Linux systems

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

Introductory lecture notes on programmable cryptography

Renderer for the harmony response format to be used with gpt-oss

An open-source AI agent that brings the power of Gemini directly into your terminal.

Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents

A payments protocol for the internet. Built on HTTP.

A hyperparameter optimization framework

A set of beautifully-designed, accessible components and a code distribution platform. Works with your favorite frameworks. Open Source. Open Code.

Cython QuantLib wrappers

Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.

A curated collection of reinforcement learning resources

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset

LLM training code for Databricks foundation models

Open source software that helps you create and deploy high-frequency crypto trading bots