Deepmind Python Packages

pysc2

StarCraft II Learning Environment

llm4ad-next

A next-generation automatic algorithm design platform, making automated algorithm design more accessible and easier to use

alphavx

CLI tool that batch-scores VCF variants against AlphaGenome and generates interpretable multi-modal effect reports.

reaver

Reaver: Modular Deep Reinforcement Learning Framework. Focused on StarCraft II. Supports Gym, Atari, and MuJoCo.

nfnets-pytorch

NFNets and Adaptive Gradient Clipping for SGD implemented in PyTorch. Find explanation at tourdeml.github.io/blog/

nalu

Basic pytorch implementation of NAC/NALU from Neural Arithmetic Logic Units paper by trask et.al

spriteworld

Spriteworld: a flexible, configurable python-based reinforcement learning environment

alphagenome-viewer

Web app for interacting with Google DeepMind's AlphaGenome model — interval predictions, variant effect analysis, and visualization

disco-torch

A PyTorch port of DeepMind's Disco103 — the meta-learned reinforcement learning update rule from Discovering State-of-the-art Reinforcement Learning Algorithms (Nature, 2025).

turbokv

First open-source implementation of TurboQuant (arXiv 2504.19874) — 4-7x LLM KV cache compression. pip install turbokv

turboquant-impl

First open-source implementation of TurboQuant (arXiv 2504.19874) — 4-7x LLM KV cache compression. pip install turbokv