A reactive notebook for Python — run reproducible experiments, execute as a script, deploy as an app, and version with git.

The Scene Language: Representing Scenes with Programs, Words, and Embeddings (arXiv preprint)

A modular embodied agent architecture and platform for building embodied agents

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

Agentic LLM Vulnerability Scanner / AI red teaming kit

Implementation of DynIBaR Neural Dynamic Image-Based Rendering (CVPR 2023)

Real-time behaviour synthesis with MuJoCo, using Predictive Control

All Algorithms implemented in Python

A fresh take on a low-level build system API.

DSPy: The framework for programming—not prompting—foundation models

Collection of reinforcement learning algorithms

MoDem Accelerating Visual Model-Based Reinforcement Learning with Demonstrations

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

Official PyTorch implmentation of paper "T-Stitch: Accelerating Sampling in Pre-trained Diffusion Models with Trajectory Stitching"

A JavaScript checker and optimizer.

Neural Networks: Zero to Hero

Vehicle and mobile robotics simulator. C++ & Python API. Use it as a standalone application or via ROS 1 or ROS 2

Machine learning from scratch

Clean PyTorch implementations of imitation and reward learning algorithms

A fork of OpenAI Baselines, implementations of reinforcement learning algorithms

openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 275+ supported cars.

Isaac Gym Reinforcement Learning Environments

Playing Pokemon Red with Reinforcement Learning