Adam Wentz

ML4AlgComb. ML Benchmarks in Algebraic Combinatorics

galois. A performant NumPy extension for Galois fields and their applications

torchlens. Capture every activation and gradient of any PyTorch model — forward and backward — with automatic graph visualization, rich metadata, and live interventions. Works on any architecture, including dynamic and recurrent ones.

pytanque. Python API for lightweight communication with the Rocq proof assistant

ruff. An extremely fast Python linter and code formatter, written in Rust.

alpaca-mcp-server. Alpaca’s official MCP Server lets you trade stocks, ETFs, crypto, and options, run data analysis, and build strategies in plain English directly from your favorite LLM tools and IDEs

unit-scaling. A library for unit scaling in PyTorch

pre-rmsnorm-transformer. Python

deepeval. The LLM Evaluation Framework

atproto. Social networking technology created by Bluesky

frequent-directions. Implements the frequent directions algorithm for approximating matrices in streams

MMRec. A Toolbox for MultiModal Recommendation. Integrating 10+ Models...

quix-streams. Python Streaming DataFrames for Kafka

ChemROAR. A novel generative embedding architecture. Find clusters of molecules with specific properties and then generate new molecules from those clusters.

llm-sandbox. Lightweight and portable LLM sandbox runtime (code interpreter) Python library.

ws4kp. A web-based WeatherStar 4000

konami-js. Adding the Konami Code easter egg to your projects since 2009! Compatible with gestures on smartphones and tablets as well. Compatible with all front-end frameworks and vanilla JavaScript

mattersim. MatterSim: A deep learning atomistic model across elements, temperatures and pressures.

mattergen. Official implementation of MatterGen -- a generative model for inorganic materials design across the periodic table that can be fine-tuned to steer the generation towards a wide range of property constraints.

ACE-Step. ACE-Step: A Step Towards Music Generation Foundation Model

redis-vl-python. Redis Vector Library (RedisVL) -- the AI-native Python client for Redis.

ypy-websocket. WebSocket Connector for Ypy

yjs. Shared data types for building collaborative software

pydantic-ai. AI Agent Framework, the Pydantic way

redis-om-python. Object mapping, and more, for Redis and Python

typesense-python. Python client for Typesense: https://github.com/typesense/typesense

Torch2PC. Software for using predictive coding algorithms to train PyTorch models.

FrEIA. Framework for Easily Invertible Architectures

rayhunter. Rust tool to detect cell site simulators on an orbic mobile hotspot

atproto. The AT Protocol (🦋 Bluesky) SDK for Python 🐍

PyBHV. Boolean Hypervectors with various operators for experiments in hyperdimensional computing (HDC).

collection. Collection of Hyperdimensional Computing Projects

torchhd. Torchhd is a Python library for Hyperdimensional Computing and Vector Symbolic Architectures

telescoping-lens.

REPA. [ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

problog. ProbLog is a Probabilistic Logic Programming Language for logic programs with probabilities.

AgentTorch. large population models

attention-gym. Helpful tools and examples for working with flex-attention

relativity-jax. General relativity with automatic differentiation in Jax.

JerichoWorld. Python

nrpy. NRPy: Python-Based Code Generation for Numerical Relativity... and Beyond!

torchdeq. Modern Fixed Point Systems using Pytorch

Sprites. Sprites video data used in the ICML 2018 paper

matmulfreellm. Implementation for MatMul-free LM.

react-game-engine. A lightweight Game Engine for the web (React) 🕹⚡🎮

broadcaster. Broadcast channels for async web apps. 📢

CFL. Python

resonator-networks. An implementation of Resonator Networks

WarpFactory. WarpFactory is a numerical toolkit for analyzing warp drive spacetimes.

EntropyEnigma. Official code for the ICML 2024 paper "The Entropy Enigma: Success and Failure of Entropy Minimization"

ThunderKittens. Tile primitives for speedy kernels

evaluation-pipeline-2024. The evaluation pipeline for the 2024 BabyLM Challenge.

pykan. Kolmogorov Arnold Networks

triton. Development repository for the Triton language and compiler

profiler-workshop. Example code for profiler workshop

evaluation-pipeline-2023. Evaluation pipeline for the BabyLM Challenge 2023.

pytorch-tvmisc. Totally Versatile Miscellanea for Pytorch

Learning-with-Holographic-Reduced-Representations. HTML

QDax. Accelerated Quality-Diversity

py-readability-metrics. 📗 Score text readability using a number of formulas: Flesch-Kincaid Grade Level, Gunning Fog, ARI, Dale Chall, SMOG, and more

multiple-input-multiple-output-nets. PyTorch Implementation of the paper "MIMONets: Multiple-Input-Multiple-Output Neural Networks Exploiting Computation in Superposition" published in NeurIPS 2023.

based. Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"

SDMContinualLearner. Jupyter Notebook

lm-evaluation-harness. A framework for few-shot evaluation of language models.

Triton-Puzzles. Puzzles for learning Triton

vllm. A high-throughput and memory-efficient inference and serving engine for LLMs

dspy. DSPy: The framework for programming—not prompting—language models

LWM. Large World Model -- Modeling Text and Video with Millions Context

FractalAI_old. Cellular automaton-based calculus for the masses

neural_networks_solomonoff_induction. Learning Universal Predictors

butterfly. Butterfly matrix multiplication in PyTorch

self-instruct. Aligning pretrained language models with instruction data generated by themselves.

tdmpc2. Code for "TD-MPC2: Scalable, Robust World Models for Continuous Control"

PhotoMaker. PhotoMaker [CVPR 2024]

SadTalker. [CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

zoology. Understand and test language model architectures on synthetic tasks.

flash-fft-conv. FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores

nas-without-training. Code for Neural Architecture Search without Training (ICML 2021)

audio2photoreal. Code and dataset for photorealistic Codec Avatars driven from audio

keops. KErnel OPerationS, on CPUs and GPUs, with autodiff and without memory overflows

alpaca_farm. A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.

clifford. Geometric Algebra for Python

barebones-hamux. Minimal library to construct Hierarchical Associative Memories (i.e., Super-powered Hopfield Networks). Research code designed to be easy to use.

fairchem. FAIR Chemistry's library of machine learning methods for chemistry

pfapack. Efficient numerical computation of the Pfaffian for dense and banded skew-symmetric matrices

llamafile. Distribute and run LLMs with a single file.

hnswlib. Header-only C++/python library for fast approximate nearest neighbors

dedalus. A flexible framework for solving PDEs with modern spectral methods.

pyclaw. PyClaw is a Python-based interface to the algorithms of Clawpack and SharpClaw. It also contains the PetClaw package, which adds parallelism through PETSc.

magpylib. Python package for computation of magnetic fields of magnets, currents and moments.

conceptnet5. Code for building ConceptNet from raw data.

poet. Paired Open-Ended Trailblazer (POET) and Enhanced POET

dream-textures. Stable Diffusion built-in to Blender

UBIKSolver. Upper Body IK is an implementation inspired by Mathias Parger's Master thesis.

outlines. Structured Outputs

home-robot. Mobile manipulation research tools for roboticists

copulae. Multivariate data modelling with Copulas in Python

opensimplex. This repo has been migrated to https://code.larus.se/lmas/opensimplex

peft. 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

infinigen. Infinite Photorealistic Worlds using Procedural Generation

RCDM. Visualizing representations with diffusion based conditional generative model.

whisper_real_time. Real time transcription with OpenAI Whisper.

audiocraft. Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

ggml. Tensor library for machine learning

AITemplate. AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

vector-quantize-pytorch. Vector (and Scalar) Quantization, in Pytorch

llmtools. Finetuning Large Language Models on One Consumer GPU in 2 Bits

AudioDec. An Open-source Streaming High-fidelity Neural Audio Codec

PySR. High-Performance Symbolic Regression in Python and Julia

cliffordlayers. Python

webvid. Large-scale text-video dataset. 10 million captioned short videos.

bark-with-voice-clone. 🔊 Text-prompted Generative Audio Model - With the ability to clone voices

DeepSpeedExamples. Example models using DeepSpeed

bark. 🚀 BARK INFINITY GUI CMD 🎶 Powered Up Bark Text-prompted Generative Audio Model

bark. 🔊 Text-Prompted Generative Audio Model

neuralprocesses. A framework for composing Neural Processes in Python

AnimatedDrawings. Code to accompany "A Method for Animating Children's Drawings of the Human Figure"

consistency_models. Official repo for consistency models.

dreamerv3. Mastering Diverse Domains through World Models

segment-anything. The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

encodec. State-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.

human_body_prior. VPoser: Variational Human Pose Prior

smplx. SMPL-X

toml. Python lib for TOML

ffmpeg-python. Python bindings for FFmpeg - with complex filtering support

CondensedMovies. Story-Based Retrieval with Contextual Embeddings. Largest freely available movie video dataset. [ACCV'20]

pytorchvideo. A deep learning library for video understanding research.

diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

FlexLLMGen. Running large language models on a single GPU for throughput-oriented scenarios.

nestedtext. Human readable and writable interchange format for structured data.

music21. music21: a Toolkit for Computer-Aided Musical Analysis and Computational Musicology

watchdog. Python library and shell utilities to monitor filesystem events.

python-twitch-stream. Python-twitch-stream is a simple lightweight library, which you can use to send your python video to twitch and react with the chat in real time.

PyLivestream. Pure Python FFmpeg-based live video / audio streaming to YouTube, Facebook, Periscope, Twitch, and more

aeneas. aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment)

whispercpp.py. Python bindings for whisper.cpp

langchain. The agent engineering platform.

rembg. Rembg is a tool to remove images background

PhySO. Physical Symbolic Optimization

lightning-hydra-template. PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡

TTS. 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Wav2Lip. This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020. For HD commercial model, please try out Sync Labs

symbolicgpt. Symbolic regression is the task of identifying a mathematical expression that best fits a provided dataset of input and output values. In this work, we present SymbolicGPT, a novel transformer-based language model for symbolic regression.

NSCL-PyTorch-Release. PyTorch implementation for the Neuro-Symbolic Concept Learner (NS-CL).

automatic_prompt_engineer. Python

pymetalog. Public repo for the pymetalog project

s4. Structured state space sequence models

trlx. A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

OpenELM. Evolution Through Large Models

alpaca-py. The Official Python SDK for Alpaca API

cramming. Cramming the training of a (BERT-type) language model into limited compute.

hamux. Hierarchical Associative Memory User Experience

OpenVR-InputEmulator. An OpenVR driver that allows to create virtual controllers, emulate controller input, manipulate poses of existing controllers and remap buttons. A client-side library that communicates with the driver via shared-memory is also included.

pyopenxr. Unofficial python bindings for OpenXR access to VR and AR devices

pyopenvr. Unofficial python bindings for Valve's OpenVR virtual reality SDK

pyribs. A bare-bones Python library for quality diversity optimization.

hivemind. Decentralized deep learning in PyTorch. Built to train models on thousands of volunteers across the world.

google-research. Google Research

tradier-python. Tradier API client implemented in python

modern-srwm. Official repository for the paper "A Modern Self-Referential Weight Matrix That Learns to Modify Itself" (ICML 2022 & NeurIPS 2021 Deep RL Workshop) and "Accelerating Neural Self-Improvement via Bootstrapping" (ICLR 2023 Workshop)

mesh-transformer-jax. Model parallel transformers in JAX and Haiku

client-python. The official Python client library for the Massive.com REST and WebSocket API.

py_vollib. Python

einops. Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

mutransformers. some common Huggingface transformers in maximal update parametrization (µP)

mup. maximal update parametrization (µP)

vicreg. VICReg official code base

evojax. Jupyter Notebook

equinox. Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

treex. A Pytree Module system for Deep Learning in JAX

elegy. A High Level API for Deep Learning in JAX

yo-mama. Yo Mama Jokes JSON

accelerate. 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

cloob. Python

ray. Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

stable-baselines3. PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

modin. Modin: Scale your Pandas workflows by changing a single line of code

long-range-arena. Long Range Arena for Benchmarking Efficient Transformers

stylegan2-pytorch. Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement

neural-tangents. Fast and Easy Infinite Neural Networks in Python

hydra. Hydra is a framework for elegantly configuring complex applications

CLIP. CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

antialiased-cnns. pip install antialiased-cnns to improve stability and accuracy

soft-brownian-offset. Soft Brownian Offset

bullet3. Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.

v2-periphery. 🎚 Peripheral smart contracts for interacting with Uniswap V2

kale. Kubeflow’s superfood for Data Scientists

web3.py. A python interface for interacting with the Ethereum blockchain and ecosystem.

Astar. The dApp hub for blockchains of the future

uscc. JavaScript

vyper. Pythonic Smart Contract Language for the EVM

brownie. A Python-based development and testing framework for smart contracts targeting the Ethereum Virtual Machine.

lambda-networks. Implementation of LambdaNetworks, a new approach to image recognition that reaches SOTA with less compute

lambda.pytorch. PyTorch implementation of Lambda Network and pretrained Lambda-ResNet

metaflow. Build, Manage and Deploy AI/ML Systems

dreamerv2. Mastering Atari with Discrete World Models

dreamer. Dream to Control: Learning Behaviors by Latent Imagination

RecBole. A unified, comprehensive and efficient recommendation library

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

deap. Distributed Evolutionary Algorithms in Python