An Android library for intelligent image cropping and perspective correction of documents, ID cards, and business cards using OpenCV and TensorFlow.

An AI-native multi-agent development platform built on Kotlin Multiplatform that integrates coding, review, and research agents across IDEs and multiple devices.

A pure-Go natural language processing library for English text that provides tokenization, part-of-speech tagging, and named entity recognition.

Jittor is a high‑performance deep‑learning framework that JIT‑compiles the entire computation graph and uses meta‑operators to generate specialised CUDA/C++ kernels. It offers a PyTorch‑like Python API, supports CPU and GPU back‑ends (CUDA, ROCm, Hygon), and includes a model zoo for vision, rendering, geometric learning, and reinforcement learning.

A multi-agent system that coordinates specialized AI agents to generate professional deliverables like slide decks, research reports, and videos from a single terminal prompt.

A production-ready Reinforcement Learning library from Meta for building modular AI agents capable of handling complex, real-world environments with sparse feedback and dynamic action spaces.

A PyTorch domain library providing sparsity and parallelism primitives for training and deploying large-scale recommender systems with massive embedding tables sharded across multiple GPUs.

An efficient singing voice conversion project that enables high-quality AI voice changing with significantly lower hardware requirements and faster training times than traditional SVC models.

A differentiable rendering framework that extracts triangular 3D models, materials, and lighting from multi-view images through joint optimization.

Apache Mahout is a scalable machine learning environment featuring Qumat, a Python library that provides a unified API for quantum computing backends and GPU-accelerated data encoding.

A PyTorch library for visualizing class activation maps (CAM) to explain and debug the predictions of convolutional and transformer-based vision models.

A collection of PyTorch optimizers that eliminate the need for learning rate schedules and predefined stopping times, enabling faster and more flexible model training.

An open-source framework for machine learning and computations on decentralized data, enabling global model training while keeping training data local to clients.

A toolkit for causal reasoning and "what-if" analysis using Bayesian Networks to identify causal relationships and estimate the impact of interventions.

A library of scikit-learn-style transformers for encoding categorical variables into numeric values using a wide variety of supervised and unsupervised techniques.

TensorFlow Extended (TFX) is a production-scale ML platform that provides a framework for building and orchestrating automated machine learning pipelines.

A browser-based neural network inference engine that runs ONNX models directly in the web browser using WebGPU, WebGL, and WebAssembly.

An open-source platform for evaluating and comparing machine learning and AI algorithms at scale through standardized leaderboards and submission interfaces.

PyCUDA is a Python wrapper for Nvidia's CUDA API that enables high-performance parallel computation on GPUs with automatic memory management and C++ speed.

ClawManager is an open‑source, Kubernetes‑native control plane that lets operators provision, govern, and collaborate on AI‑agent workspaces (OpenClaw, Hermes, OpenCode, DeepSeek Harness). It bundles a React UI, Go backend, MySQL state, and a set of services (AI Gateway, Northbound API, Security Protection) to provide one‑click runtime creation, model‑access auditing, reusable resource injection, team‑based task decomposition, and layered security monitoring. Deployable on k3s or full Kubernetes clusters, it targets platform teams that need scalable, policy‑driven AI agent infrastructure.

A GPU-accelerated implementation of the FIt-SNE algorithm that provides massive speedups for visualizing high-dimensional data compared to CPU-based methods.

An open-source multi-agent AI assistant that allows users to build autonomous AI teams and companies to execute complex tasks across desktop, web, and mobile platforms.

A repository of reference (unoptimized) implementations for the MLPerf Training benchmark suite, covering vision, language, recommendation, and graph models. Each benchmark includes model code, Dockerfiles, dataset scripts, and a training‑run script that measures time to reach target quality. Intended for benchmark submissions, hardware evaluation, and learning, but not for real‑world performance.

A Python library for ensembling bounding box predictions from multiple object detection models using methods like Weighted Boxes Fusion (WBF) and NMS.

A Python package providing a suite of scikit-learn compatible interpretable machine learning models, such as rule sets and sparse linear models, to replace black-box models.

An autonomous data labeling agent framework that allows AI agents to independently learn data processing skills based on a ground truth dataset.

torchdistill is a PyTorch‑based library that lets you run knowledge‑distillation experiments (teacher‑student training) by writing only a YAML configuration. It provides many modern KD losses, a forward‑hook manager for extracting intermediate features, and example scripts for vision and NLP tasks. Install via `pip install torchdistill` and cite the associated papers when used in research.

A lightweight PyTorch toolkit combining Monte Carlo Tree Search and Deep Reinforcement Learning to standardize and accelerate research in MCTS-based decision-making algorithms.

An automatic distributed deep learning system that simplifies large-scale AI model training by providing automated fault tolerance, auto-scaling, and rapid checkpoint recovery on K8s and Ray.

A PyTorch implementation of AlphaFold 3 for predicting the 3D structures of biomolecular interactions, including comprehensive tools for PDB dataset curation.

A robust forced-aligner built on Kaldi that aligns speech audio with text transcripts to provide precise word-level timing.

CodeGPT is a Go‑based CLI that uses LLM APIs (OpenAI, Azure, Gemini, Anthropic, Ollama, Groq, OpenRouter) to automatically generate Conventional‑Commit messages and brief code‑review summaries. It can install a Git `prepare‑commit‑msg` hook, supports custom prompts, language translation, streaming output, and flexible configuration (API keys, providers, proxy, diff context, etc.). Installable via Homebrew, Chocolatey, script, binary, or `go install`.

LucidDreamer is a system for domain-free generation of 3D Gaussian Splatting scenes from a single image and a text prompt.

A command-line translator for Chinese and English that combines dictionary services and LLMs, featuring a built-in free LLM proxy and AI agent integration.

A collection of deep learning synthetic data generators that learn from real single-table data to create high-fidelity synthetic versions.

A PyTorch Lightning-powered library of self-supervised methods for unsupervised visual representation learning, providing a unified environment to train and compare SOTA visual models.

A TensorFlow-based project that trains an AI agent to drive Mario Kart 64 by learning from human gameplay recordings.

An AI code assistant providing context-aware completions and chat to accelerate software development while ensuring data privacy and security.

A C++20 library for numerical computing that brings NumPy-like tensor expressions to NVIDIA GPUs and CPUs, featuring JIT kernel fusion for maximum performance.

A CNN-based Korean morphological analyzer developed by Kakao that uses machine learning to split text into morphemes for NLP preprocessing.

A hardware-accelerated, differentiable molecular dynamics library built on JAX for simulating materials and small-scale interactions.

A source-to-source compiler for PyTorch that optimizes models for training and inference through a Pythonic intermediate representation and extensible transformation plugins.

A unified playground for implementing and evaluating KV cache compression, retrieval, merging, and quantization methods to optimize long-context LLM inference memory usage.

A .NET library providing comprehensive bindings for the Ollama API, enabling C# developers to easily integrate local and remote AI models into their applications.

A Python SDK for Milvus, providing a programmatic interface to manage and search high-dimensional vector embeddings in the Milvus vector database.

A ROS-Industrial meta-package that provides the necessary configurations and descriptions to control and simulate Universal Robots hardware using ROS.

A collection of text processing classes and ops for TensorFlow that enables consistent preprocessing in the TensorFlow graph for both training and inference.

A Python module for survival analysis built on scikit-learn that allows researchers to connect covariates to event times while handling censored data.