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

A method for improving LLM generalization during Supervised Fine-Tuning by dynamically rescaling token loss based on predicted probabilities, particularly effective for reasoning tasks.

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 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.

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.

An embeddable AI agent harness kernel written in Rust that provides the execution loop, memory, and coordination infrastructure for agent-powered applications.

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 fast and ergonomic machine learning library for Rust that provides a comprehensive suite of classical supervised and unsupervised learning algorithms.

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

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 framework for packaging, running, and tracking machine learning experiments across local environments, Kubernetes, and Google Cloud Platform.

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

Go bindings for llama.cpp that enable high-performance local LLM inference within Go applications using the GGUF format.

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.

A C++ library and file format for compressed 3D Gaussian splats that reduces file sizes by up to 10x compared to .ply files with minimal visual difference.

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

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.

A lightweight C++ neural network inferencing engine optimized for real-time systems and audio processing.

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.

An open source agent engineering platform for collaboratively tracing, evaluating, monitoring, and debugging AI agents.

A machine learning tool that automatically ranks strings extracted from binaries to help malware analysts quickly identify the most relevant information.

A Go-based protocol conversion and model routing proxy that unifies various AI provider APIs (Anthropic, Gemini, OpenAI) under a single OpenAI Responses API interface.

A framework for the Cline VS Code extension that manages large-scale project context and dependencies using a recursive, file-based tracking system and local LLM-assisted analysis.

A core Julia interface for defining and solving Markov Decision Processes (MDPs) and Partially Observable Markov Decision Processes (POMDPs) to handle decision-making under uncertainty.

A benchmark for Table-Augmented Generation (TAG), a paradigm for answering natural language questions over databases that require world knowledge or semantic reasoning.

NucliaDB is a hybrid AI search database that combines vector, full-text, and graph indexes to store and search unstructured data.

An extension of XGBoost that enables probabilistic modelling by predicting the full conditional distribution of targets instead of single point estimates.

An MCP server that uses Nano Banana Pro to automatically generate architecture diagrams, flowcharts, and sequence diagrams from codebases and system documentation.

A trustworthy evaluation framework for autonomous agents featuring 300 human-verified tasks and a strict Pass^3 metric to ensure consistent model performance.

A model interpretability method that explains neural network predictions using high-level human concepts rather than individual input features.

A comprehensive Julia package for reinforcement learning research that provides extensible components for implementing, benchmarking, and reproducing RL algorithms.

A neural texture compression SDK that compresses multiple PBR texture channels into a single neural set to reduce VRAM and bandwidth usage in 3D rendering.

A PyTorch library for maintaining Exponential Moving Average (EMA) versions of models to improve stability and performance, featuring post-hoc synthesis and target representation routing.

MOA is an open-source Java framework for real-time data stream mining and large-scale machine learning, providing a suite of algorithms and evaluation tools.

An MCP server that gives AI agents unfiltered access to a local shell and file system for autonomous coding, building, and running of software.

A backend for Triton Inference Server that enables serving Python-based machine learning models without requiring C++ code.

VPTQ is a post-training quantization method that uses vector quantization to compress LLMs to under 2 bits without retraining, enabling massive models to run on consumer hardware.

A Laravel package that automatically transforms Eloquent models into both JSON:API endpoints and MCP servers for AI agents from a single codebase.

A proxy that sits between AI agents and LLM APIs to compress conversation history in the background, preventing delays when context limits are are reached.

A tool for managing and deploying AI models via Docker, streamlining the process of pulling and serving LLMs using backends like llama.cpp and vLLM.

An efficient PyTorch library for differentiable optimization that supports explicit, implicit, and zero-order differentiation for bi-level optimization and meta-learning.

A community-driven automation framework for AI/ML research that enables reproducible and portable workflows across diverse hardware, software, and datasets.

A C++ and DPC++ library that provides hardware-accelerated machine learning routines for tabular data across CPUs, GPUs, and distributed systems.

An AI-powered document processing engine for ETL and RAG that transforms unstructured documents into high-quality data chunks for vector databases.

A high-performance semantic memory system for AI agents that introduces Git-like version control, hierarchical semantic paths, and cryptographic integrity to memory management.