An MCP server that enables AI agents to control macOS applications and system functions by executing AppleScript and JavaScript for Automation (JXA) scripts.

A lightweight PyTorch library for differentiable 3D rotation manipulation, providing mappings between rotation representations and utilities for rotation regression.

A suite of rerankers featuring pointwise, pairwise, and listwise models to improve the accuracy of search and retrieval systems.

A Jax-based proof-of-concept implementation of Stable-Baselines3, providing high-performance reinforcement learning algorithms with a consistent API.

A security-hardened ComfyUI extension that adds LLM-assisted nodes, a remote admin console, an automation HTTP API, and chat-platform connectors (Discord, Telegram, WhatsApp, etc.) so ComfyUI can be operated remotely and safely.

A skill pack and MCP server that provides AI coding agents with real-world product screenshots, UI references, and growth research to enable evidence-based design.

A customizable, Rust-based statusline for Claude Code that displays real-time session cost, context usage, and API limits.

A local-first AI terminal operator that converts natural language intent into governed, reviewable, and reversible system actions with built-in safety guardrails.

A stand-alone implementation of NumPy dtype extensions for machine learning, providing support for bfloat16, 8-bit floats, and narrow integers.

A cognitive memory database that implements biological memory primitives like Hebbian learning and temporal decay to provide AI agents with persistent, evolving memory.

A PyTorch implementation of the SLAYER framework for training multilayer spiking neural networks using backpropagation to learn synaptic weights and axonal delays.

A production-ready governance framework for enterprise AI agents that implements safety guardrails, compliance-as-code, IAM, and human-in-the-loop escalation.

A transparent cognitive sandbox and digital pet simulation that allows users to learn neuroscience by raising a neural network they can see and trace in real time.

Ivy is a transpiler that allows developers to convert machine learning code, models, and libraries between frameworks such as PyTorch, TensorFlow, JAX, and NumPy.

LMFlow is an extensible Python toolbox for fine‑tuning large language models. It supports full‑parameter training, LoRA, the memory‑efficient LISA algorithm, QLoRA quantization, and a suite of speed‑up tricks (FlashAttention‑2, DeepSpeed, vLLM, SGLang). After training, it provides simple scripts for chat‑style inference and optional Gradio/Flask deployment. The library is designed for Linux/Colab environments and offers optional extras for multimodal models, distributed reward‑model inference, and more.

A collection of NVIDIA-maintained utilities for PyTorch that streamline mixed precision and distributed training through optimized CUDA extensions.

A scikit-learn compatible neural network library that wraps PyTorch, enabling the use of scikit-learn's pipelines and grid search with PyTorch models.

A multimodal data augmentation library that provides over 100 transforms for audio, image, text, and video to improve AI model robustness against real-world internet data.

A Python framework that transforms deep neural networks into optimized CUDA/HIP C++ code for high-performance inference serving on NVIDIA and AMD GPUs.

A gradient-free optimization platform for minimizing functions, particularly useful for hyperparameter tuning in machine learning.

An AI-native multi-agent development platform built on Kotlin Multiplatform that integrates coding, review, and research agents across IDEs and multiple devices.

A visual, interactive ML model-understanding tool that supports text, image, and tabular data to help developers debug and interpret model predictions.

A production-ready Reinforcement Learning library from Meta for building modular AI agents capable of handling complex, real-world environments with sparse feedback and dynamic action spaces.

A tool to convert TensorFlow, Keras, TensorFlow.js, and TFLite models to the ONNX format for cross-platform compatibility and deployment.

An open-source deep learning framework for time series forecasting, classification, and anomaly detection featuring a wide array of state-of-the-art models.

Apache Mahout is a machine learning environment featuring Qumat, a Python library that provides a unified API for quantum circuits and GPU-accelerated data encoding for quantum ML.

An open-source framework for machine learning and computations on decentralized data, enabling global model training while keeping training data local to clients.

TensorFlow Extended (TFX) is a production-scale ML platform that provides a framework for building and orchestrating automated machine learning pipelines.

A browser-based neural network inference engine that runs ONNX models directly in the web browser using WebGPU, WebGL, and WebAssembly.

An open-source platform for evaluating and comparing machine learning and AI algorithms at scale through standardized leaderboards and submission interfaces.

PyCUDA is a Python wrapper for Nvidia's CUDA API that enables high-performance parallel computation on GPUs with automatic memory management and C++ speed.

A GPU-accelerated implementation of the FIt-SNE algorithm that provides massive speedups for visualizing high-dimensional data compared to CPU-based methods.

An optimizing compiler for deep learning algorithms that treats ML models as instructions to automatically build explainable, resource-aware pipelines.

A Python package providing a suite of scikit-learn compatible interpretable machine learning models, such as rule sets and sparse linear models, to replace black-box models.

A lightweight PyTorch toolkit combining Monte Carlo Tree Search and Deep Reinforcement Learning to standardize and accelerate research in MCTS-based decision-making algorithms.

An automatic distributed deep learning system that simplifies large-scale AI model training by providing automated fault tolerance, auto-scaling, and rapid checkpoint recovery on K8s and Ray.

A neural network framework for Elixir that provides high-level APIs for model creation and training, powered by Nx for numerical acceleration.

A privacy-preserving machine learning library that uses fully homomorphic encryption (FHE) to enable inference and training on encrypted data using scikit-learn-like APIs.

A source-to-source compiler for PyTorch that optimizes models for training and inference through a Pythonic intermediate representation and extensible transformation plugins.

A .NET library providing comprehensive bindings for the Ollama API, enabling C# developers to easily integrate local and remote AI models into their applications.

A collection of text processing classes and ops for TensorFlow that enables consistent preprocessing in the TensorFlow graph for both training and inference.

A Python module for survival analysis built on scikit-learn that allows researchers to connect covariates to event times while handling censored data.

A memory-optimized Batch Normalization layer for PyTorch that reduces GPU memory usage by up to 50% during training by combining BN and activation into an in-place operation.

An open-source standalone MCP host that enables developers to build and deploy AI agents by connecting LLMs with MCP servers.

A tool for computing shareable, comparable, and reproducible BLEU and other translation metrics, automating test set management and tokenization.

A scalable dataloading library for PyTorch that introduces stateful loading for mid-epoch checkpointing and composable iterators for data preprocessing.

A self-hosted search gateway for AI agents that aggregates multiple search providers into a single Perplexity-compatible API with automatic fallback for high reliability.

A PyTorch-based library that brings Hugging Face Transformer architectures to sequential and session-based recommendation systems, supporting rich tabular input features and GPU acceleration.