A Rust client SDK for LiveKit, enabling real‑time video/audio/data streaming, room management, and hardware‑accelerated encoding across desktop and mobile platforms.

A package providing interfaces to simulate robots in the Webots 3D simulator using ROS2 messages, services, and actions.

A unified framework for robot learning that provides a collection of MuJoCo-simulated environments and tasks exposed via the OpenAI-Gym API.

A high-performance embedded autopilot system for autonomous vehicles that uses model-based design to enable rapid control system development and auto-code generation.

A parallel and differentiable robotics kinematics library for PyTorch that provides fast forward and inverse kinematics and Jacobian calculations.

A ROS 2 LiDAR SLAM system that converts sensor bags into Autoware-compatible map bundles, including point clouds and auto-generated lanelet2 files.

A C++ library implementing Optimal Reciprocal Collision Avoidance (ORCA) to enable thousands of independent robots or agents to navigate a shared space without collisions or communication.

A pure-Python library for computing the inverse kinematics of any robot, supporting URDF and MuJoCo MJCF imports and an accelerated JAX backend.

An open-source ecosystem of Chinese pre-trained foundation models and a supporting framework for natural language understanding, generation, and multimodal tasks.

A production-oriented suite of ComfyUI nodes for vision-language models, providing structured detection, segmentation, and adaptive video reasoning with VRAM optimizations.

A collection of optimized Docker images for WhisperX, providing pre-bundled ASR models for fast and efficient speech-to-text transcription with word-level timestamps.

A tiny JavaScript library that enables users to control websites through voice commands using speech recognition.

An AI-powered tool that uses OpenAI-Whisper and Edge TTS to automatically generate captioned TikTok videos with natural-sounding voiceovers.

A ComfyUI custom node integration for VoxCPM, a tokenizer-free TTS system that enables expressive speech generation, natural language voice design, and advanced voice cloning.

A suite of AI-powered tools that automatically enhance Anki flashcards with AI-generated images, mnemonics, and explanations to improve learning efficiency.

A gallery of interactive AI samples for Windows developers to explore local AI models and export them as C# Visual Studio projects.

A native macOS application for running Stable Diffusion and FLUX.2 Klein locally on Apple Silicon, optimized for high performance and low memory usage via Core ML.

A blazing-fast, C++26-powered terminal coding agent that uses local RAG and a multi-model orchestrator to provide a lightweight, vendor-agnostic alternative to Claude Code.

An advanced framework for the development and evaluation of recommendation systems, covering the full pipeline from data preprocessing to production deployment.

A ComfyUI extension that prevents image artifacts and over-saturation by automatically rescaling CFG and provides tools to accelerate generation speed.

An on-device face recognition and liveness detection SDK for Android that enables private, offline biometric identity verification and attribute analysis.

A QA dataset and benchmarking tool designed to evaluate the ability of RAG pipelines to retrieve and reason across multiple documents and metadata.

An open-source persistent memory infrastructure for AI agents that uses a knowledge graph of markdown files to implement cognitive forgetting and recursive retrieval.

PathML is an open‑source Python library (also available as a Docker image) that streamlines the whole‑slide pathology workflow: loading diverse slide formats, applying scalable preprocessing (stain normalisation, tiling, GPU transforms), converting data to PyTorch tensors, building cell‑level graphs, and running deep‑learning or ONNX models. It aims to lower the barrier to AI‑driven computational pathology and is already used in many high‑impact biomedical publications.

A centralized collection of LangChain integrations for Google's Generative AI, Gemini API, and Vertex AI services.

An agentic finance toolkit that enables AI agents to manage wallets, execute payments, and perform investment strategies using blockchain infrastructure.

A programming language designed for LLMs to write, featuring structural references instead of variable names and mandatory SMT-proven contracts to ensure correctness.

Functionary is a language model specialized in interpreting and executing functions and plugins, supporting parallel tool calls and a built-in code interpreter.

TorchX is a universal job launcher for PyTorch applications that allows users to launch jobs across Kubernetes, Slurm, Docker, and local environments.

An AI-as-a-Service platform to create and deploy RAG systems, agents, and inference endpoints via a REST API with a full management dashboard.

A Unity plugin that integrates ZED cameras' depth sensing, spatial mapping, and object detection capabilities into the Unity engine for AR/MR development.

A natural language image search tool that allows users to find specific images in local folders using text or image queries powered by OpenAI's CLIP.

An interactive simulation platform for household activities that allows researchers to train embodied AI agents and generate synthetic video data via a Python API.

A multi-image viewer designed for efficient comparison, filtering, and stitching of large image datasets, featuring parallel zooming and automated figure generation.

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

Unbody is an open-source backend infrastructure project designed to provide a comprehensive data management and indexing system for AI applications.

An open-source extension of the AWS CDK that provides well-architected infrastructure patterns for quickly deploying generative AI solutions on AWS.

An automated evaluation framework for text-to-image and text-to-video models that uses multimodal LLMs to score visual-text alignment.

A diffusion-based generative model for creating cell-type specific synthetic regulatory DNA sequences of 200bp.

A fast and efficient method for fine-tuning text-to-image diffusion models to learn new concepts from a few images with minimal storage overhead.

A specialized framework for generating high-quality, privacy-preserving synthetic tabular data using statistical models, GANs, and LLMs.

A comprehensive, high-performance machine learning framework for the JVM that provides tools for traditional ML, deep learning, LLMs, and an agentic data science IDE.

A command-line tool for creating container-based AI/ML development environments using a simple Python declaration instead of complex Dockerfiles.

A high-performance, Rust-based embedding pipeline that streamlines the ingestion, chunking, and indexing of multimodal data into vector databases without requiring PyTorch.

AdalFlow is a PyTorch-like library for building and auto-optimizing LLM workflows, including chatbots, RAG, and agents, by replacing manual prompting with automated textual gradient descent.

GPTeam is a multi-agent simulation where AI agents collaborate, communicate, and move through a simulated world to achieve common goals.

A lightweight Python framework for building multi-agent LLM applications, enabling agents to collaborate via message exchange and tool integration.

skrl is a modular Reinforcement Learning library implemented in PyTorch, JAX, and NVIDIA Warp that supports a wide variety of environment interfaces for training agents.