A portable ncnn-based implementation of the Z-Image generator that enables high-performance image generation, inpainting, and ControlNet support on any Vulkan-capable GPU.

A Python library that allows users to call the local OCR model built into the WeChat Windows client to perform text recognition on images.

An implementation of Vision Mamba, a bidirectional state space model for efficient visual representation learning that is significantly faster and more memory-efficient than traditional Vision Transformers.

A web-based chat application that uses RAG to answer questions about PostgreSQL database rows using hybrid search and OpenAI function calling.

A cloud-native reference application demonstrating multi-agent AI orchestration and standardized AI tooling integrated into a microservices architecture.

Pixio is a vision encoder optimized for dense prediction tasks like depth estimation and semantic segmentation, achieved through enhanced pixel reconstruction pre-training.

A PyTorch-based library providing state-of-the-art neural network potentials for molecular simulations and the tools to train them.

A PyTorch reimplementation of SRGAN that uses generative adversarial networks to produce photo-realistic 4x upscaled images with recovered fine textures.

An Android app that turns images and videos into a searchable personal knowledge base using on-device processing and automatic media grouping.

Tilus is a tile-level GPU kernel programming language that enables high-performance, low-precision computation with explicit control over shared memory and registers.

A framework for constrained nonlinear optimization designed for scientific machine learning, uncertainty quantification, and AI, offering fine-grained control over solver workflows.

A Ruby framework for building LLM-powered systems that allows developers to coordinate tools, data queries, and AI providers through a unified, composable architecture.

An AI-powered pipeline and analysis platform that extracts insights from large volumes of conversational data, featuring an LLM-driven chat interface and automatically generated KPI dashboards.

A framework for evaluating and comparing open-source AutoML systems using standardized environments and curated datasets to ensure reproducible research.

A collection of GPU-accelerated machine learning solvers that act as a drop-in replacement for scikit-learn, providing Python and R APIs for faster model training.

An integration library that allows JAX users to call custom Triton kernels for high-performance GPU operations within JAX programs.

An Android SDK for secure identification document scanning and data extraction using machine learning and native C++ libraries.

An enterprise-grade multimodal AI middleware that provides a unified API layer for managing multiple model providers, RAG, and agent runtimes with centralized routing and governance.

A Python package for supervised and unsupervised short text categorization, providing tools for text representation, topic modeling, and neural network classification.

A PyTorch library for efficiently computing the Hessian eigendecomposition, trace, and spectral density of neural networks without the quadratic memory bottleneck.

An AI agent runtime framework that integrates chat, RAG, and agentic loops to enable professional automation tasks across desktop and mobile platforms.

A web-based GUI for Ollama and other local LLM providers that allows users to chat with self-hosted models via a privacy-focused interface.

An AutoML technology for tabular data that synthesizes high-quality machine learning pipelines by learning from a corpus of human-written solutions.

A low-cost sensor-fusion SLAM system for ground vehicles that integrates RGB-D, IMU, wheel odometry, and GNSS to ensure robust localization in challenging corner cases.

A multi-agent orchestration platform that coordinates 39 AI specialists across various coding runtimes to manage software development via structured Express and Standard workflows.

A comprehensive toolkit providing a unified interface to over 90 metrics for evaluating the quality, intelligibility, and technical properties of speech and audio.

A Julia package for data-driven structural estimation and identification of differential equations, allowing users to automatically discover mathematical models from data.

A tool for running and customizing real-time, interactive generative AI video pipelines using autoregressive diffusion models and a composable architecture.

A high-performance MCP management system built with Rust that orchestrates Model Context Protocol services for AI agents and applications.

The official Node.js client library for the DeepL API, enabling developers to integrate high-quality text and document translation into their applications.

A collection of Python tools for building graph-enhanced Generative AI applications using hierarchical lexical graphs and structured knowledge graphs.

A scalable PyTorch reinforcement learning framework accelerated by Lightning Fabric that decouples RL algorithms from their environments for greater flexibility.

Crust is an open‑source, locally‑run proxy that sits between AI coding assistants and LLM providers. It inspects every tool call (file reads, shell commands, network requests) and blocks actions that could expose secrets or harm the host. The gateway works as an HTTP proxy, MCP/ACP stdio wrapper, or Docker container, and includes 42 built‑in security rules, 51 DLP patterns, and a plugin system for custom policies. It runs entirely on the user’s machine, stores logs encrypted in the OS keyring, and offers iOS integration via a Swift package.

A binocular vision system for camera calibration, disparity mapping, and 3D reconstruction using algorithms like ELAS and ADCensus.

A PyTorch-native toolbox for discrete and continuous wavelet transforms that provides GPU acceleration and gradient support for signal and image processing.

A toolkit for developing and deploying TFLite models to mobile devices, providing tools for metadata management, automatic API generation, and optimized task libraries.

A set of Expo modules that wrap Google's MLKit native libraries, enabling on-device machine learning features like face and object detection in Expo apps.

A high-quality, low-bitrate speech codec that compresses audio into discrete tokens, optimized for use in downstream tasks like text-to-speech.

A command-line tool to execute .prompt files, allowing users to treat LLM prompts as versionable artifacts and automate AI workflows via the shell.

A PyTorch-based parallel training system designed to scale deep learning recommendation models up to 100 trillion parameters on commodity hardware.

3D-R1 is a generalist 3D Vision-Language Model that enhances spatial reasoning and scene understanding through synthetic CoT data and reinforcement learning.

A native Rust client for Qdrant, enabling high-performance vector search and database management within Rust applications.

A Python package for automated LLM compression that uses advanced quantization techniques like QEP and AutoBit to reduce model size and VRAM usage.

PE3R is a perception-efficient 3D reconstruction system that converts 2D images into semantically understood 3D scenes using zero-shot generalization.

A Keras and TensorFlow framework for text processing that supports rich text layout information for sequence labeling and text classification.

An open-source software suite for the variational optimization of deep-learning molecular wave functions to simulate electronic ground and excited states.

A collection of practical notebooks for fine-tuning and optimizing audio AI models, including ASR and audio captioning, using the Hugging Face ecosystem.

A multi-task deep learning framework for real-time 2D and 3D human pose estimation and action recognition.