Python

A collection of AI skills and agents specialized in Django backend development, providing expert guidance and code review.

A collection of AI agent skills and subagents for Sentry's internal development workflows, following the open Agent Skills format.

A Claude Code plugin marketplace providing AI-assisted skills for security research, vulnerability detection, and audit workflows.

A framework for creating multi-agent AI applications that can act autonomously or work alongside humans.

A standalone Python framework for orchestrating autonomous AI agents that collaborate to tackle complex tasks.

A framework for programming language models with Python instead of prompting, enabling modular AI systems with automatic prompt optimization.

A framework for building agents and LLM-powered applications by chaining together interoperable components and integrations.

A Python agent framework for building production-grade GenAI applications with type safety, observability, and extensibility.

A multi-agent LLM framework for financial trading that simulates real-world trading firms with specialized AI agents for market analysis and decision-making.

A Python library that provides reliable, validated JSON outputs from any LLM using Pydantic models.

An open-source framework for building LLM-powered applications with data ingestion, indexing, and retrieval capabilities.

An intelligent memory layer for AI agents that enables personalized interactions by remembering user preferences and learning over time.

A modular PyTorch library for state-of-the-art diffusion models to generate images, audio, and 3D molecular structures.

A high-performance serving framework for large language models and multimodal models, delivering low-latency and high-throughput inference.

A model-definition framework for state-of-the-art machine learning models across text, vision, audio, and multimodal tasks.

A web UI and optimization library for running and fine-tuning open-source AI models locally with 2x faster training and 70% less VRAM.

A high-throughput, memory-efficient inference and serving engine for large language models (LLMs).

A Python library for accelerator-oriented array computation and program transformation, designed for high-performance numerical computing and machine learning.

A multi-backend deep learning framework that enables effortless model development across JAX, TensorFlow, PyTorch, and OpenVINO.

A deep learning framework to pretrain and finetune any AI model on any hardware with zero code changes.

A Python package for tensor computation with GPU acceleration and dynamic neural networks built on a tape-based autograd system.

A reliable PyTorch implementation of reinforcement learning algorithms for research and industry.

An end-to-end open source platform for machine learning with a comprehensive ecosystem of tools and libraries.

A high-performance gradient boosting library with best-in-class handling of categorical features and support for CPU/GPU training.

A Python library for feature engineering and selection with scikit-learn compatible transformers.

An open-source, in-memory platform for distributed and scalable machine learning with support for a wide range of algorithms and big data technologies.

A fast, distributed gradient boosting framework based on decision tree algorithms for ranking, classification, and other ML tasks.

An open-source query engine for AI analytics that builds self-reasoning agents across live data sources without ETL.

A Python toolkit for causal and probabilistic reasoning using graphical models like Bayesian Networks and Structural Equation Models.

A Python library for generating high-quality synthetic tabular data using GANs, diffusion models, and large language models.

A scalable, portable, and distributed gradient boosting library for efficient machine learning across multiple languages and platforms.

A Python library for topic modeling, document indexing, and similarity retrieval with large corpora.

A comprehensive Python library for natural language processing, providing modules, datasets, and tutorials for NLP research and development.

Industrial-strength Natural Language Processing library for Python, featuring pretrained pipelines for 70+ languages and production-ready training.

A Python NLP library from Stanford for tokenization, sentence segmentation, NER, and dependency parsing across 60+ languages.

A comprehensive collection of Chinese NLP resources, datasets, tools, and pre-trained models for developers and researchers.

A ready-to-use OCR Python library supporting 80+ languages and popular writing scripts like Latin, Chinese, Arabic, and Cyrillic.

A differentiable computer vision library for PyTorch, providing geometric vision and image processing algorithms for AI workflows.

Pre-built CPU-only OpenCV packages for Python, providing easy installation via pip without manual compilation.