-
MIT / Harvard
- struct.inc
- @lukehollis
- in/luke-hollis
Highlights
- Pro
Stars
Tensors and Dynamic neural networks in Python with strong GPU acceleration
The simplest, fastest repository for training/finetuning medium-sized GPTs.
We write your reusable computer vision tools. 💜
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
🦔 PostHog provides open-source web & product analytics, session recording, feature flagging and A/B testing that you can self-host. Get started - free.
A generative world for general-purpose robotics & embodied AI learning.
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!
A collaboration friendly studio for NeRFs
An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
Hackable and optimized Transformers building blocks, supporting a composable construction.
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!
A free, online learning platform to make quality education accessible for all.
TripoSR: Fast 3D Object Reconstruction from a Single Image
Unified framework for robot learning built on NVIDIA Isaac Sim
SkyReels-V2: Infinite-length Film Generative model
[ICLR 2024 Oral] Generative Gaussian Splatting for Efficient 3D Content Creation
[NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling
Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)
A library for mechanistic interpretability of GPT-style language models
A collection of high-quality models for the MuJoCo physics engine, curated by Google DeepMind.
Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model
PyTorch code and models for VJEPA2 self-supervised learning from video.
Mastering Diverse Domains through World Models