A PyTorch‑based library that provides reference and Hugging Face‑compatible implementations of Transformer models optimized for Apple’s Neural Engine, delivering up to 10× faster inference and 14× lower memory on A14/M1‑class devices.

A text preprocessing library that provides tokenization, detokenization, normalization, and truecasing tools for NLP datasets.

An asymmetric and adaptive refinement of the GRPO reinforcement learning algorithm that uses four independent clipping boundaries to prevent entropy collapse and improve generalization in LLM reasoning tasks.

An acceleration framework for large-scale unsupervised outlier detection that optimizes training and prediction for ensembles of heterogeneous models.

An autonomous task execution system for Claude CLI that monitors usage windows and automatically runs predefined tasks from a Markdown file.

A toolkit for evaluating RAG chat applications by benchmarking generated answers against ground truth data using GPT-based and code-based metrics.

A log analysis tool that collapses millions of noisy log lines into a few typed patterns, providing LLM-optimized output and local-first processing.

A library that makes custom Docker containers compatible with Amazon SageMaker, simplifying the process of training machine learning models in isolated environments.

A VSCode extension and proxy that allows users to switch AI models in GitHub Copilot Chat instantly without reloading the editor.

An open-source benchmarking platform for image and video diffusion models that automates prompt sweeps, metric calculation, and reproducible run logging.

A Python library and CLI tool that automates the discovery of Cloudflare Turnstile sitekeys and generates valid tokens via the Peak API to bypass security challenges.

LeoAI is an open‑source, Spring‑Boot based red‑team platform that merges a dual Java/PHP Puppet remote‑execution runtime with LLM‑driven AI agents (via LangChain4j). It offers a web UI for host management, interactive shells, file/database tools, scanning, proxy/tunnel handling, in‑memory shell generation for many Java containers, a searchable “Skill” prompt library, traffic obfuscation, team collaboration, and audit logging. Deployable as a single executable JAR (SQLite DB) or via Docker, it supports multiple LLM providers and is licensed under GPL‑v3.

faer is a pure Rust linear algebra library that provides low-level routines and high-level wrappers for portable and high-performance mathematical computations.

An automated account registration tool for Grok (x.ai) that uses temporary emails and browser patches to bypass Cloudflare Turnstile.

Python bindings for the Ceres Solver that enable non-linear least squares optimization and factor graph implementation for bundle adjustment and pose graph optimization.

A command-line interface for Hono developers and AI agents that integrates documentation search, server management, and bundle optimization.

A Streamlit component that adds an interactive sketching canvas using Fabric.js, enabling users to draw shapes and annotations and return the data to Streamlit.

A comprehensive collection of deep learning and machine learning implementations in C++ and Python, covering basic math foundations, classic ML algorithms, and modern frameworks like YOLO and RAG.

A collection of tools and SDKs for implementing and validating attestation in NVIDIA Trusted Computing and confidential computing environments.

A comprehensive software development kit that bundles headers, bindings, and loaders for developing cross-platform OpenCL applications.

A reconciliation-based coding agent that prevents context rotting by using fresh contexts and file-system memory to iteratively align a codebase with a specified goal.

A Kubernetes usage accounting tool that tracks CPU, Memory, and GPU resources to reveal hidden system overhead and enable precise per-namespace cost allocation.

A low-code AI application development platform that enables users to build, orchestrate, and deploy complex AI workflows and agents using a visual interface.

A Python library for developing and comparing multi-objective multi-agent reinforcement learning algorithms through a standardized API and a set of benchmark environments.

A bridging layer that enables AI agents to control and edit Unreal Engine 5.3+ in real time, featuring AST-based validation to prevent hallucinations and deep integration with Blueprints, VFX, and rigging.

A modular TensorFlow-based deep reinforcement learning framework for research and practice, providing flexible components to build and deploy RL agents.

A Python library for tensor learning that provides tools for tensor decomposition and algebra with seamless support for multiple backends like PyTorch, TensorFlow, and JAX.

A framework for building MCP servers that automatically converts Python files into server capabilities, reducing boilerplate and providing built-in authentication and telemetry.

An optimization toolkit for Continual AI that provides specialized algorithms and visualization tools to prevent catastrophic forgetting and improve model stability.

A modular Python library for Deep Reinforcement Learning that provides implementations of algorithms like DDPG and Double Q-learning.

A transformer model architecture (T6) that uses Tensor Product Attention to improve performance and reduce KV cache size for more efficient LLM inference.

A collection of engineering tools for high-stakes decision frameworks, featuring LLM evaluation for finance, data provenance, and risk-portfolio prototyping.

An AI-oriented code-processing framework that uses a Universal Abstract-Syntax-Tree (UniAST) to provide LLMs with precise, structured coding context for better AI-assisted programming.

A full-stack AI framework built entirely in Java that provides a complete pipeline from low-level tensor computation to LLMs, AI agents, and embodied intelligence.

An MCP server that enables LLMs to control iOS simulators through natural language commands for app management and UI testing.

A lightweight LLM scheduling framework that reduces prefill overhead by reusing KV caches for frequently accessed external knowledge across LLM systems.

A Godot engine plugin that integrates AI assistants into the editor to help with coding, scene editing, and project management via local or remote LLMs.

A resumable indexer that aggregates Polymarket market metadata and on-chain trade data into a queryable DuckDB database.

A fast framework for fine-tuning similarity learning models to specialize pre-trained models for semantic search, recommendations, and anomaly detection.

A Python module for the parallel optimization of expensive black-box functions, designed to find global minima for tasks like hyperparameter tuning.

UQpy is a general purpose Python toolbox for modeling and quantifying uncertainty in physical and mathematical systems.

A Python toolbox for optimization on Riemannian manifolds that supports automatic differentiation for non-Euclidean geometric optimization.

A library for creating easy, chainable preprocessing pipelines for pandas DataFrames to streamline data cleaning and feature engineering.

A lightweight C++ wrapper for OpenCL that reduces boilerplate code and the complexity of device selection, memory management, and kernel execution.

A collection of software tools for molecular dynamics simulations that integrates various interatomic potentials and tight-binding quantum mechanics, including machine-learning-based GAP potentials.

An AutoML framework that uses a declarative JSON-AI syntax to automatically generate and customize machine learning pipelines, reducing boilerplate code for data preparation and data science workflows.

A communication framework built on NCCL that allows users to execute custom, hyper-optimized collective communication algorithms for multiple accelerators to improve distributed AI performance.

A Go-based toolkit for automatically fixing malformed JSON output generated by LLMs, ensuring it becomes valid and parseable.