Stars
Letta (formerly MemGPT) is a framework for creating LLM services with memory.
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
The repository demonstrates implementation of immersive 360 depth (image and video) in WebXR powered by A-Frame, Three.js and Depth Anywhere.
A high-throughput and memory-efficient inference and serving engine for LLMs
The Bluesky Social application for Web, iOS, and Android
A suite of image and video neural tokenizers
The development repository for the deal.II finite element library
[3DV'25] 3D Reconstruction with Spatial Memory
ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…
Rust bindings for the C++ api of PyTorch.
Inference code for the paper "Spirit-LM Interleaved Spoken and Written Language Model".
Productive, portable, and performant GPU programming in Python.
A generative and self-guided robotic agent that endlessly propose and master new skills.
Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.
Code for "Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation"
SAPIEN Manipulation Skill Framework, a open source GPU parallelized robotics simulator and benchmark, led by Hillbot, Inc.
Generative Agents for video games. Based on Generative Agents: Interactive Simulacra of Human Behavior
Generative Agents: Interactive Simulacra of Human Behavior
The communications platform that puts data protection first.
Multi-Joint dynamics with Contact. A general purpose physics simulator.
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
Simplifying reinforcement learning for complex game environments