An open-source registry for MCP servers, AI agents, skills, and prompts that centralizes discovery, management, and deployment of AI building blocks.

RISE is a self-improving robot policy framework that uses a compositional world model to train robot policies through imaginary rollouts, reducing the need for real-world hardware interactions.

An intelligent agent-powered document search platform that enables users to upload, process, and query documents through a chat interface using RAG.

Google DeepMind’s TAP‑Net repository offers datasets, pretrained models (TAPIR, BootsTAPIR, TAPNext/Next++), training code, and Colab/real‑time demos for the “Tracking Any Point” task—precise point‑level video tracking useful for vision research and robot imitation.

A PyTorch library providing a high-level API for image semantic segmentation, featuring 12 architectures and over 800 pretrained encoders.

An AI-powered penetration testing automation framework that orchestrates security tools and multi-agent AI to perform adaptive security assessments and evidence-backed reporting.

A Kubernetes-native distributed AI platform for scalable LLM fine-tuning and training across multiple frameworks like PyTorch, JAX, and DeepSpeed.

A CLI tool for launching and managing LLM inference workloads on NVIDIA DGX Spark systems without requiring Slurm or Kubernetes.

A collection of modern, TypeScript‑typed JavaScript packages (`@huggingface/hub`, `@huggingface/inference`, `@huggingface/mcp-client`, etc.) that let you create repos, upload files, and call Hugging Face inference APIs (chat, text‑to‑image, translation, streaming, custom endpoints) from browsers, Node, Deno or Bun.

A pluggable multi-object tracking framework that provides a unified interface for integrating various detectors and trackers for both axis-aligned and oriented bounding boxes.

A deep probabilistic programming library built on PyTorch that allows users to create and scale universal probabilistic models for large datasets.

OpenLoomi is an open‑source, cross‑platform desktop “attention agent” that continuously gathers context from your work tools (email, chat, issue trackers, docs) into a searchable, encrypted memory. It surfaces reminders and lets you ask an LLM for help directly inside messaging apps. The runtime is agent‑agnostic, offering Skills and Plugins that integrate with Claude Code, Codex, OpenCode, Hermes, OpenClaw, etc. Installable via simple binaries, it emphasizes local‑first privacy and works out‑of‑the‑box.

MemoryOS is a memory management system for AI agents that uses a hierarchical storage architecture to maintain short, mid, and long-term personalized memory for more coherent interactions.

A collection of reference implementations and tutorials for building generative AI systems, RAG pipelines, and agentic workflows using the NVIDIA software ecosystem and NIM microservices.

A collection of code samples and demonstrations for the Agent2Agent (A2A) protocol, designed to enable interoperability and communication between different AI agents.

A Python library for building scalable synthetic data pipelines, providing bulk inference and structured output tools to curate high-quality datasets for post-training.

An inference engine and deployment platform that enables users to run computer vision models and complex visual workflows on any hardware, from edge devices to the cloud.

MagenticLite is an agentic application from Microsoft AI Frontiers that automates browser and local file system tasks using efficient, small-scale AI models.

Electric is a real-time sync engine for Postgres that handles partial replication and data delivery, enabling developers to build apps and AI agents with live local data.

An open-source control plane that turns AI agent logic into production-ready REST APIs with built-in scaling, observability, and cryptographic identity.

An end-to-end autonomous AI research engine that automates the process from ideation to LaTeX paper production by executing real GPU experiments to ensure data authenticity.

A command-line tool designed for AI agents to fetch, discover, and extract structured data from the web, replacing the need for fragile parsing scripts and raw HTML dumps.

A framework for analyzing large-scale single-cell perturbation experiments, providing tools to harmonize data and analyze how cells respond to genetic, drug, or environmental stimuli.

A robotic intelligence stack for the Unitree Go2 that enables autonomous navigation, dynamic obstacle avoidance, and semantic scene understanding using the Odin1 sensing module.

A starter template for building AI applications with LangChain.js and Next.js, featuring implementations for streaming chat, RAG, and agentic workflows.

An AI-powered learning coach that integrates with Claude Code and Codex to accelerate technical mastery through spaced repetition, personalized syllabi, and active practice.

Millet is an offline‑first Python tool that records dual‑channel audio from any meeting app, transcribes it with WhisperX (or MLX Whisper), diarises speakers via pyannote‑audio, and generates AI‑written summaries and professional PDFs. It offers three summarisation presets—high‑quality (cloud), confidential (TEE‑protected GLM‑5.3), and alternative (Kimi)—and supports multilingual transcription, voice‑print speaker recognition, structured markdown/YAML front‑matter, and optional Git sync. Linux is required for audio capture; macOS can run only the post‑capture steps.

A Terraform and OpenTofu skill for AI agents that eliminates hallucinations and reduces token usage through a failure-mode-first diagnostic workflow.

A real-time engine for AI agents on the JVM that provides streaming transports, enterprise governance, and durable session management for production-grade agent services.

LitServe is a Python-based framework for building custom inference servers, allowing developers to define their own logic for batching, routing, and orchestration for models, agents, and RAG pipelines.

A collection of plugins and configuration settings for AI coding tools like Claude Code and Cursor to reduce over-engineering and eliminate AI-generated buzzwords.

A CLI tool that allows AI agents to control Chrome via simple shell commands, enabling browser automation without complex configuration or API keys.

A collection of reusable agent skills in the SKILL.md format that transforms complex professional workflows into installable packages for AI agents.

AIMET is Qualcomm’s open‑source toolkit for quantizing and compressing PyTorch/ONNX models, enabling fast, low‑memory inference on edge devices with minimal accuracy loss.

A Python package that adapts the Segment Anything Model (SAM) for geospatial data, enabling easy segmentation of satellite imagery using text, points, or boxes.

A visual annotation tool for AI agents that captures element selectors, CSS, accessibility data, and DevTools edits to streamline UI bug fixing.

A multi-subscription extension for the pi coding agent that enables automatic rate-limit rotation and failover across multiple AI provider accounts.

Neural Kernel Surface Reconstruction (NKSR) is a method for creating high-quality 3D implicit surfaces from large-scale, sparse, and noisy point clouds, capable of handling millions of points in seconds.

A lightweight compatibility layer that enables developers to write dataframe-agnostic code by providing a unified API for libraries like pandas, Polars, and PyArrow.

A Python library for automated data analysis and monitoring that uses deep learning to detect sensitive PII/NPI data across various file formats.

A set of ComfyUI nodes that perform image-to-image diffusion on large images using a tiled approach to improve detail and reduce hardware requirements.

Ix is a system intelligence tool that parses codebases into a persistent graph of symbols and relationships, allowing humans and AI agents to query structure instead of searching text.

A feature-rich AI assistant app for Android that offers multi-provider support, RAG-based memory, and built-in code execution engines.

A no-code GUI and framework for fine-tuning large language models, enabling users to experiment with hyperparameters and advanced training techniques without coding.

An open-source LLM load balancer and serving platform that enables self-hosted inference, deployment, and scaling of LLMs on private infrastructure.

OpenVINO AI Plugins for GIMP adds on‑device AI features (super‑resolution, semantic segmentation, and many Stable‑Diffusion variants including FastSD) to GIMP 3, using Intel OpenVINO for CPU/GPU/NPU inference. Install via the provided Windows/Linux guides, load a model in GIMP, then generate or edit images directly in the editor.

A type-safe Python client generator for the Chrome DevTools Protocol (CDP) that automatically creates bindings from official specifications.

An anime scene search engine that identifies the specific anime, episode, and timestamp of a screenshot using image vector search.