pyro: a scalable deep probabilistic programming library built on PyTorch
A deep probabilistic programming library built on PyTorch that allows users to create and scale universal probabilistic models for large datasets.
sonnet: a composable neural network abstraction library for TensorFlow 2
A TensorFlow 2 library from DeepMind that provides simple, composable abstractions for building neural networks for ML research.
cleanrl: a collection of high-quality single-file deep reinforcement learning implementations for research and prototyping
A Deep Reinforcement Learning library providing single-file, transparent implementations of popular algorithms to simplify research, debugging, and prototyping.
autogluon: an automated machine learning library for high-accuracy predictive modeling across multiple data modalities
An automated machine learning library by AWS AI that enables users to train and deploy high-accuracy models for tabular, image, text, and time series data with minimal code.
server: an open-source inference server that streamlines AI model deployment across multiple frameworks and hardware platforms
An open-source inference serving software that streamlines the deployment of AI models from multiple frameworks across cloud, data center, and edge devices.
amazon-sagemaker-examples: official example notebooks and a streamlined Python SDK for managing the end-to-end machine learning lifecycle on AWS
A collection of official example notebooks and the SageMaker-Core SDK to help developers build, train, and deploy machine learning models on Amazon SageMaker.
wandb: a comprehensive experiment tracking and visualization platform for machine learning pipelines
A machine learning experiment tracking and visualization platform that helps developers monitor hyperparameters and metrics across the entire ML pipeline.
kornia: a differentiable computer vision library for PyTorch providing over 500 differentiable image processing and geometric vision operators
A differentiable computer vision library for PyTorch that provides a rich set of image processing and geometric vision algorithms for AI workflows.
pytorch-grad-cam: a comprehensive collection of pixel attribution methods for explaining computer vision model predictions
A PyTorch library providing a comprehensive suite of Class Activation Map (CAM) methods to visually explain and diagnose computer vision model predictions.
tvm: an open machine learning compilation framework for universal model deployment and joint optimization
Apache TVM is an open machine learning compilation framework that optimizes and deploys models into minimum deployable modules using a Python-first approach.
fg-data-profiling: a one-line exploratory data analysis tool for comprehensive dataset profiling and quality alerts
A one-line Exploratory Data Analysis (EDA) tool that generates comprehensive profiling reports for pandas and Spark DataFrames, identifying data quality issues and patterns.
dlib: a modern C++ and Python toolkit for implementing machine learning algorithms
A modern C++ toolkit containing machine learning algorithms and tools for creating complex software to solve real-world problems.
burn: a unified Rust deep learning framework for seamless training and inference across diverse hardware
Burn is a unified tensor library and deep learning framework written in Rust that allows the same code to be used for both training and inference across diverse hardware.
tfjs: a hardware-accelerated JavaScript library for training and deploying machine learning models in the browser and Node.js
A hardware-accelerated JavaScript library for training and deploying machine learning models in the browser and Node.js.
ml-agents: a toolkit for training intelligent agents within Unity games and simulations
A toolkit that turns Unity games and simulations into environments for training intelligent agents using reinforcement and imitation learning.
recommenders: a comprehensive framework for prototyping and deploying classic and state-of-the-art recommendation systems
A comprehensive library of examples and best practices for building recommendation systems, providing a wide range of classic and deep learning algorithms for prototyping and production.
deepface: a hybrid face recognition and attribute analysis framework wrapping multiple state-of-the-art models
A lightweight Python framework for face recognition and facial attribute analysis that wraps multiple state-of-the-art models into a single, easy-to-use API.
Paddle: an industrial-grade deep learning platform with unified training and inference and automatic parallelism
An industrial deep learning platform providing a unified framework for training and inference, automatic parallelism, and support for scientific computing.
shap: a game theoretic framework for explaining the predictions of any machine learning model
A game theoretic framework for explaining the outputs of any machine learning model by attributing credit to input features using Shapley values.
fastai: a deep learning library that balances high-level productivity with low-level research flexibility
A deep learning library built on PyTorch that provides high-level components for rapid productivity and low-level components for research flexibility.
pytorch-lightning: a deep learning framework that automates PyTorch engineering to scale model training from CPU to multi-node GPUs
A deep learning framework that abstracts away the engineering boilerplate of PyTorch, enabling researchers to pretrain and finetune AI models at scale across various hardware.
netron: a visual viewer for neural network and machine learning model architectures
A visualizer for neural network and deep learning models that supports a wide variety of model formats including ONNX, TensorFlow, and PyTorch.
spaCy: an industrial-strength NLP library for advanced text processing and production-ready model training
An industrial-strength NLP library for Python and Cython that provides pretrained pipelines and neural network models for advanced text processing across 70+ languages.
mediapipe: a cross-platform framework for deploying customizable on-device machine learning pipelines
An open-source framework for building and deploying customizable on-device machine learning pipelines across mobile, web, desktop, and IoT devices.
gradio: a Python framework for rapidly building and sharing machine learning web demos without front-end code
An open-source Python library for quickly building and sharing web applications for machine learning models and APIs without requiring front-end development experience.
supervision: a model-agnostic computer vision toolkit for data handling and visualization
A comprehensive computer vision toolkit that provides model-agnostic building blocks for data loading, visualization, and dataset management.
qlib: an AI-oriented quantitative investment platform for the full pipeline from alpha seeking to order execution
An AI-oriented quantitative investment platform that provides a full ML pipeline for data processing, model training, and back-testing to create AI-driven trading strategies.
faceswap: a deep learning tool for recognizing and swapping faces in pictures and videos
A deep learning tool for recognizing and swapping faces in pictures and videos through an extract-train-convert pipeline.
tensorflow: an end-to-end open source platform for machine learning research and application deployment
An end-to-end open source platform for machine learning that provides a flexible ecosystem of tools and libraries for building and deploying ML-powered applications.
onecli: a secure credential injection gateway that prevents AI agents from accessing raw API keys
An open-source gateway that securely injects API credentials into AI agent requests, ensuring agents never see the real secret keys.
brightdata-mcp: an MCP server providing AI assistants with unblocked real-time web search and structured data extraction
An MCP server that gives AI assistants real-time, unblocked web access and structured data extraction to prevent outdated responses and bot-blocking.
vibe-coding-prompt-template: a structured AI workflow for shipping MVPs through prompt templates and agent-driven development
A structured AI workflow and prompt template system that guides users from initial idea research to a shipped MVP using AI coding agents.
xalpha: a fund investment management tool for portfolio analysis and real-time net value prediction
A fund investment management library that provides data acquisition, portfolio analysis, and net value prediction for funds and stocks.
pentestagent: an autonomous AI penetration testing framework with multi-agent orchestration and MCP integration
An AI-powered penetration testing framework that automates security assessments using autonomous agents, professional tools, and structured attack playbooks.
danghuangshang: a hierarchical multi-agent collaboration system that organizes AI agents into a structured court or corporate hierarchy
A multi-agent collaboration system based on the OpenClaw framework that organizes AI agents into a hierarchical government or corporate structure for efficient task delegation and execution.
open-terminal: a self-hosted API-driven terminal for AI agents to execute code and manage files in sandboxed or bare-metal environments
A lightweight, self-hosted terminal that provides AI agents and automation tools with a dedicated, API-accessible environment to run commands and manage files.
datachain: a context layer for unstructured data that turns cloud storage into versioned, typed datasets
A Python library that turns unstructured files in cloud storage into versioned, typed datasets that can be queried at warehouse speed without moving the data.
serenity-skill: a supply-chain research agent skill for identifying high-value investment targets in tech trends
An AI agent skill that implements a supply-chain research methodology to help investors identify high-value stocks and funds by finding critical bottlenecks in tech trends.
ralph-orchestrator: a hat-based orchestration framework for autonomous AI agent iteration and task completion
A hat-based orchestration framework that keeps AI agents in a loop of continuous iteration and validation until a software task is fully completed.
ai-crawler-py: a low-code AI web crawler that extracts structured data using natural language prompts and automated schemas
An AI-powered web crawler that uses natural language prompts to discover relevant pages and extract structured JSON or Markdown data from websites.
TuriX-CUA: a computer-use agent that automates desktop GUI actions across any application without requiring specific APIs
An open-source computer-use agent that automates desktop GUI actions across any application without requiring specific APIs.
skills: a browser automation CLI for AI agents with anti-bot bypass and human-in-the-loop handoff
A browser automation CLI for AI agents that bypasses anti-bot walls and provides token-efficient, indexed interactions for easier web navigation.
abtop: a TUI monitoring dashboard for tracking token usage and resource consumption across multiple AI coding agent sessions
A TUI monitoring dashboard for AI coding agents that tracks token usage, context windows, and rate limits across multiple active sessions.
qiushi-skill: a methodology-driven skill set for AI agents to improve strategic reasoning and problem-solving
A collection of AI Agent skills based on dialectical materialism and practical philosophy, providing structured methodology to improve an agent's reasoning and problem-solving.
loop-engineering: a framework for designing automated control systems that orchestrate AI coding agents
A framework and tooling suite for designing automated control systems that orchestrate AI coding agents, replacing manual prompting with recursive, goal-oriented loops.
opencode.nvim: a Neovim integration for OpenCode AI that enables context-aware pairing and side-by-side edit reviews
A Neovim plugin that integrates OpenCode AI to provide context-aware AI pairing and code edits directly within the editor.
all-agentic-architectures: a library of 35 production-grade agentic AI patterns with a unified API and comparative benchmarks
A Python library and runnable textbook providing 35 production-grade agentic AI patterns with a unified API and multi-provider support.
OB1: a unified persistent memory layer and open protocol for sharing context across multiple AI tools
An infrastructure layer that provides a unified, persistent memory database with vector search, allowing multiple AI tools and agents to share a single, consistent context of the user.
openclaw-mission-control: a centralized operations and governance platform for managing AI agent orchestration and approvals
A centralized operations and governance platform for OpenClaw that provides unified visibility, approval controls, and orchestration for AI agents across organizations.
memgraph: an in-memory graph database providing atomic GraphRAG and real-time connected context for AI agents
A high-performance, in-memory graph database that provides real-time connected context for GraphRAG, AI memory systems, and agentic workflows.