An open-source SDK for building and deploying AI agents as modular, scalable services with built-in HTTP servers and dynamic agent-to-agent communication.

A Google Cloud-based solution that automates marketing content generation, trend analysis, and data querying using Vertex AI and Google Workspace integration.

A generative AI utilization platform developed by the Digital Agency of Japan that allows government officials to quickly and safely deploy specialized AI applications.

XCube is a generative model for high-resolution sparse 3D voxel grids that uses hierarchical latent diffusion and VDB data structures to create detailed 3D objects and large-scale scenes.

A framework for Energy-Based Transformers (EBTs) that enables scalable reasoning and System 2 Thinking across text, image, and video modalities.

Liquid is a unified autoregressive multimodal generator that integrates visual comprehension and image generation into a single LLM without needing external visual embeddings.

A Python library for modeling multivariate distributions and generating synthetic numerical data using copula functions.

A node-based workflow engine for advanced semantic prompt routing and multi-LLM orchestration, allowing users to create complex, context-aware AI agents.

A serverless AI chatbot implementation using LangChain.js and Azure, enabling Retrieval-Augmented Generation (RAG) to answer queries based on enterprise documents.

JoyVASA is a diffusion-based framework that animates human and animal portraits using audio, decoupling facial identity from motion to enable high-quality, long-form video generation.

An AI-powered frontend engine that lets developers generate, iterate, and refine React components directly within their IDE using special JSX components and props.

A PHP library for Generative AI and vector databases, providing a unified interface to integrate LLMs and vector stores into PHP applications.

An SDK for embedding an intelligent layer into web applications that enables the real-time generation of business logic and UI components.

Voost is a unified Diffusion Transformer that enables high-quality bidirectional virtual try-on and try-off, allowing users to add or remove garments from images of people.

A Python library for simulating and visualizing a wide variety of one-dimensional and two-dimensional stochastic processes.

PixelSmile is a fine-grained facial expression editing tool that allows users to change emotions in images of humans and anime characters while preserving their identity.

A WebGPU-powered platform for real-time rendering of Gaussian Splatting variants and 3D meshes directly in the browser using ONNX Runtime.

VistaDream is a training-free framework that reconstructs high-quality 3D scenes from a single-view image by ensuring consistency across generated novel views.

Ditto is a framework for generating high-quality synthetic video editing data to train Editto, a state-of-the-art instruction-based video editing model.

A plug-and-play framework for Diffusion Transformers that enables the generation of longer videos and higher-resolution images through positional embedding extrapolation.

ConsisID is a tuning-free, DiT-based text-to-video generation model that uses frequency decomposition to maintain consistent human identity across generated video frames.

A training-free iterative framework for long story visualization that maintains semantic consistency across up to 100 frames using a global reference cross-attention module.

A PyTorch implementation of Mean Flows and Improved Mean Flows for high-quality, one-step image generation.

MagicTime is a metamorphic video generation pipeline designed to create realistic time-lapse videos that depict significant physical transformations based on text prompts.

A CLI tool to estimate VRAM usage, benchmark performance, and generate training recipes for fine-tuning LLMs on consumer GPUs using LoRA and QLoRA.

A synthetic data generation and evaluation framework that creates high-quality training datasets for agentic LLMs using real tool execution and topic graph mapping.

An end-to-end computer vision platform that uses active learning and smart annotations to build and deploy optimized AI models with minimal data.

A comprehensive platform for hosting, deploying, and fine-tuning LLMs using containerized images and an OpenAI-compatible API.

A Python library that enables patch-based inference for YOLO models to improve the detection of small objects in large images through image tiling and result consolidation.

A runtime stack for YOLOv5 that simplifies object detection deployment by embedding pre- and post-processing into the model graph for various hardware accelerators.

A Pythonic serverless interface that allows ML developers to run and scale workloads on Kubernetes clusters directly from their local environment with near-instant startup times.

A columnar file format by Meta designed for large, wide datasets, optimizing storage and access for machine learning training tables and feature engineering.

VIAME is an open‑source computer‑vision toolkit that provides detection, tracking, annotation, search and many other image/video processing capabilities through a modular, multi‑language pipeline framework. It ships with desktop and web GUIs, command‑line tools, pre‑built binaries and Docker images, and can be extended via C++, Python or MATLAB plugins.

A suite of tools for optimizing machine learning models for deployment and execution using techniques like quantization and pruning.

A collection of high-quality, standardized baselines and templates for researchers to benchmark uncertainty and robustness in deep learning models.

A PyTorch-based unified benchmark for semi-supervised learning, providing implementations of 14 algorithms and 15 tasks across CV, NLP, and Audio classification.

A high-performance automatic differentiation plugin for LLVM and MLIR that synthesizes fast gradients for optimized code, including GPU kernels and parallel programs.

A library of training tools and utilities for PyTorch users to streamline the model training process.

A general-purpose probabilistic programming system in Julia that enables programmable Bayesian inference and gradient-based training of generative models.

An open-source tool for analyzing and cleaning large-scale image and video datasets by identifying duplicates, outliers, and mislabels.

An AI datastore for schemas, BLOBs, and predictions that provides tools for human supervision and multi-modal data labeling.

A Python library for building Gaussian process models using TensorFlow and TensorFlow Probability for fast, GPU-accelerated inference.

PyKEEN is a Python package for training and evaluating knowledge graph embedding models, providing a comprehensive library of built-in datasets and models.

A Python library and low-code framework for building computer vision models on satellite, aerial, and drone imagery using PyTorch.

A deep learning runtime and REST server that provides a unified API for training and inference across images, text, and tabular data.

A Python library and CLI for managing NVIDIA DGX Cloud Lepton, enabling developers to deploy endpoints, run batch jobs, and call cloud workloads as native Python functions.

An open-source library built on Apache Spark that provides scalable, distributed APIs for machine learning tasks including text analytics, vision, and anomaly detection.

A high-performance serving system for machine learning models designed to manage model lifetimes and provide versioned inference via gRPC and HTTP in production environments.