A collection of Python scripts for converting object detection dataset annotations between CSV, COCO, Pascal VOC, and Labelme formats.

Uni-MoE is a Mixture-of-Experts based omnimodal large model capable of understanding and generating across multiple modalities, including text, images, and speech.

An open-source agentic framework for building research agents using Schema-Guided Reasoning to combine structured reasoning with flexible tool selection.

An offline OCR library for Android that enables high-speed recognition of Chinese ID cards, driver's licenses, and passports without requiring an internet connection.

The core speech synthesis engine for VOICEVOX, provided as a C and Python library for easy integration into various applications.

A JAX library for building and sampling probabilistic graphical models, focusing on efficient block Gibbs sampling and energy-based models.

A PyTorch quantization backend for Optimum that reduces model size and memory usage by converting weights and activations to lower precision like int4 or float8.

A Rust crate that wraps the Ollama local‑model HTTP API, providing easy functions for text generation, chat (with history), streaming responses, model management, embeddings, and LLM‑tool/function calling via a macro‑based system.

A GPU-accelerated recommender framework designed for the efficient training and inference of large deep learning models with massive embedding tables.

A comprehensive and unified deep reinforcement learning library providing a modularized ensemble of DRL and MARL algorithms compatible with PyTorch, TensorFlow, and MindSpore.

Apache SystemDS is an open-source machine learning system that manages the end-to-end data science lifecycle from data preparation to model serving using a high-level language.

A high-performance library for small dense and sparse linear algebra operations that uses JIT code generation to optimize deep learning and HPC workloads across multiple CPU architectures.

A packaged version of the Segment Anything Model (SAM) that provides easy pip installation and extended support for video segmentation and cloud GPU integration.

A library for point cloud registration using probabilistic models, offering a more robust alternative to ICP for both rigid and non-rigid transformations.

A Sharded Data Parallelism framework by Yandex that optimizes LLM pre-training by reducing communication and memory overhead, offering up to 20% speedup over PyTorch FSDP.

EnsoAI is an Electron‑based desktop workbench that couples Git worktree management with persistent AI‑agent sessions (Claude, Gemini, Codex, etc.). It provides a built‑in Monaco editor, visual Git UI, 3‑way merge tool, and one‑click IDE bridging, enabling developers to work on multiple branches in parallel while each branch enjoys its own dedicated LLM context.

A TensorFlow framework for training neural networks using structured signals, such as graphs and adversarial perturbations, to improve accuracy with limited labeled data and increase robustness.

A Triton Inference Server backend that enables high-performance serving of TensorRT-LLM optimized models with support for in-flight batching and multi-GPU scaling.

MushroomRL is a modular Python library for reinforcement learning that provides a wide array of classical and deep RL algorithms and integrates with popular tensor libraries and benchmarks.

A ROS-based full-stack software framework for agile quadrupedal locomotion that integrates planning, control, and estimation for simulation and hardware.

A modern Java library for genetic and evolutionary algorithms that provides tools for optimization, genetic programming, and multi-objective search.

A PyGlove-powered library that enables object-oriented prompting, allowing developers to integrate natural language and structured Python objects for more predictable LLM outputs.

A comprehensive deep learning utility library and CLI tool providing visualization, annotation management, and deployment utilities for computer vision and 3D data.

A machine learning library for Ruby that provides a wide array of algorithms with an interface similar to Scikit-Learn.

A Julia package that integrates differential equation solvers into neural networks to enable the creation of physically informed scientific machine learning models.

A collection of hardware-aware efficient ConvNet models and tools, including FBNet and ChamNet, designed to optimize computer vision performance and latency on mobile devices.

TensorFlow‑Java provides Maven‑publishable Java/JVM bindings for TensorFlow, including low‑level JNI wrappers (`tensorflow‑core`), a high‑level neural‑network API (`tensorflow‑framework`), and an independent ndarray library. It supports Linux (x86_64, arm64) and macOS (Apple Silicon) binaries, with optional GPU builds, and integrates with standard Java build tools.

A comprehensive benchmark and framework for stereo matching that integrates 17 datasets and multiple state-of-the-art models for depth estimation.

A deep learning toolbox for predicting quantum-chemical properties of molecules and materials using atomistic neural networks.

hf‑mem is a lightweight Python CLI (and library) that estimates the RAM required to run any Hugging Face model that uses Safetensors or GGUF weights. It fetches only metadata via HTTP range requests, supports Transformers, Diffusers, Sentence‑Transformers, and can optionally estimate KV‑cache memory and MoE breakdowns. Installable as a standalone tool, a Hugging Face CLI extension, or an agent skill.

An AI-powered offensive security agent that automates privilege escalation to root access using an autonomous LLM-driven shell loop.

DiffMem is a production‑ready FastAPI service that gives LLM‑powered agents a Git‑backed, Markdown‑based memory. Each user lives on an isolated Git branch; the writer agent commits conversation updates, and a retrieval agent uses plain `git`/`grep` commands to fetch the current view or dive into history. The system needs only an LLM API key, runs on a tiny Linux box (Docker or Coolify), and optionally mirrors branches to a private GitHub repo for backup. It includes consolidation tools (dedupe, redistribute, link) to keep the “now” files compact and well‑linked.

An R interface to Keras that enables R users to prototype and train deep learning models using a high-level neural networks API.

A high-performance C# NLP library inspired by spaCy that provides fast tokenization, entity recognition, and embedding training for .NET applications.

A collection of Google Colab notebooks for preparing datasets and training Stable Diffusion LoRA models, including support for SDXL.

A modular AI agent framework that enables the creation of multi-platform agents with specialized Web3 intelligence and integrated RAG and Chain of Thought workflows.

Treelite is a universal model exchange and serialization format for decision tree forests, enabling C++ applications to store and exchange models on disk and network.

An open-source Java data mining framework focused on research in unsupervised methods for cluster analysis and outlier detection, featuring high-performance index structures for scalable benchmarking.

AgentForge is a low‑code Python framework for building, testing, and iterating AI‑driven autonomous agents. It uses declarative YAML files (Cogs) to compose agents, attach optional memory, and orchestrate multi‑agent workflows, while supporting OpenAI, Gemini, Claude, and local models via Ollama/LMStudio.

A code intelligence CLI tool that combines AST-based call graph analysis and hybrid semantic search to help developers and AI agents navigate large codebases.

An open-source platform for interactive learning that provides scalable individual feedback, automatic assessment, and optional LLM-powered tutoring for universities.

A package of trained U-net models for automated lung segmentation in CT scans, capable of handling severe pathologies and lobe-specific masking.

PhoBERT provides state-of-the-art pre-trained language models for Vietnamese based on the RoBERTa architecture, improving performance on various Vietnamese NLP tasks.

A Julia library for symbolic regression that searches for human-readable mathematical expressions to fit datasets, optimizing the trade-off between accuracy and complexity.

A multimodal AI agent framework for the Go language that enables developers to build complex AI workflows with pluggable models, tools, and memory.

A Python toolkit for Explainable AI (XAI) that provides tools for attribution, feature visualization, and concept extraction to help users understand complex neural network models.

A diffusion-based training framework for Text-to-Speech, Singing Voice Synthesis, and Singing Voice Conversion that supports multi-speaker training and efficient hardware utilization.

A Python framework for building memory-first AI agents that use persistent episodic, semantic, and procedural memory to recall experience and learn new skills over time.