Repository Index

Multi-Joint dynamics with Contact. A general purpose physics simulator.

• robotics
• physics
• mujoco

This repository contains implementations and illustrative code to accompany DeepMind publications

Open source code for AlphaFold 2.

A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

• ai
• attention
• claude
• claude-ai

TensorFlow-based neural network library

• machine-learning
• artificial-intelligence
• neural-networks
• deep-learning

AlphaFold 3 inference pipeline.

Search your computer by what's in your files: photos, PDFs, documents, recordings, videos and code. On-device on Mac, Windows and Linux, built on Google DeepMind's EmbeddingGemma 2.

• embeddinggemma
• embeddings
• llama-cpp
• local-first

A TensorFlow implementation of DeepMind's WaveNet paper

Build Graph Nets in Tensorflow

• graph-networks
• graphs
• deep-learning
• neural-networks

A library of reinforcement learning components and agents

• reinforcement-learning
• agents
• research

TensorFlow Reinforcement Learning

Optax is a gradient processing and optimization library for JAX.

• machine-learning
• optimization

The original code from the DeepMind article + my tweaks

PettingZoo and Gymnasium bindings for popular reinforcement learning environments outside of Farama

• deepmind-control-suite
• deepmind-lab
• gymnasium
• reinforcement-learning

Reproducing the results of "Playing Atari with Deep Reinforcement Learning" by DeepMind

Build AI text detectors whose decisions are mechanistically grounded and human-auditable (EMNLP 2026)

• ai-text-detection
• explainable-ai
• interpretability
• mechanistic-interpretability