A Go-based tool to parse GGUF model metadata and estimate memory usage and performance without requiring full file downloads.

An MCP-based plugin for Unreal Engine that exposes over 1,400 editor actions to AI assistants using a namespace-dispatch pattern to minimize context window usage.

A language model architecture that eliminates matrix multiplication operations to improve efficiency, specifically designed for neuromorphic hardware and compatible with Hugging Face.

A high-performance Go library for multilingual text segmentation and NLP, providing efficient word cutting for languages like Chinese, Japanese, and English.

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.

OpenDeRisk is an open‑source, multi‑agent AI platform that automates root‑cause analysis for software incidents. It ingests the large OpenRCA dataset, lets specialized agents (SRE, Code, Report, Visual, Data) collaborate, and presents a visual evidence chain through a web UI. Installable via a single curl script or from source with the uv package manager, it supports quick‑start usage, flame‑graph assistance, and conversational data analysis.

NeuralGCM is a Python library for building hybrid machine learning and physics-based atmospheric models for weather and climate simulation.

A tool for automating the and evaluation of multiple LLMs, prompts, and inference parameters via Ollama to find the optimal configuration for a specific task.

A humanoid teleoperation system combining an RL-based loco-manipulation policy with a low-cost isomorphic exoskeleton cockpit for precise full-body control.

A high-performance C++ automatic differentiation library providing forward and reverse mode AD with low runtime overhead for performance-critical systems.

An AI-powered content production pipeline that automates data collection from social platforms and uses a 6-step editorial workflow to generate high-quality, human-like articles.

FlexTok is a system for resampling images into 1D token sequences of flexible length, allowing images to be represented as sequences that can be truncated while still enabling image reconstruction.

A governed, local-first agent runtime for Python that provides strict permission controls, persistent memory, and tool connectivity via MCP/ACP.

GPTLink is a PHP and Vue-based framework for quickly deploying a professional AI chat website with an integrated admin console and monetization features.

A PyTorch framework for deep learning R&D that removes training loop boilerplate to accelerate experimentation and reproducibility.

An IntelliJ-based IDE plugin that uses LLMs to automatically generate commit messages from git diffs.

A REST API-based management platform for LLM assets, providing tools for organization, storage, and distribution of models and datasets.

An automated AI pipeline that extracts engaging highlights from long videos and livestreams, providing transcription, AI analysis, and automatic clip generation with subtitles and covers.

An AI-powered bioinformatics research assistant that brings computational biology tools and literature search into messaging apps like WhatsApp and WeChat.

A high-performance TensorFlow Lite library for React Native that enables efficient on-device AI inference using zero-copy ArrayBuffers and GPU acceleration.

SoniTranslate is a web application for translating videos into different languages with synchronized audio, combining transcription, translation, and voice dubbing in one interface.

JTokkit is a zero‑dependency Java library that reproduces OpenAI’s tokenisation algorithms (e.g., cl100k_base) for fast, accurate token counting and conversion on the JVM. It offers a thread‑safe API, Maven/Gradle distribution, and extensibility for custom encodings, all under an MIT license.

An any-to-any generative foundation model for Earth Observation that enables multimodal geospatial data generation and environmental monitoring.

A subtitle translation tool that lets users connect their own translation API keys to translate .srt, .vtt, and .ass files cheaply and efficiently.

A web UI and API for Cloudflare D1 serverless SQL databases that includes a natural language to SQL translation feature.

A Raycast extension for quickly looking up words and translating text across 48+ languages using various translation services and LLMs.

A Python client library that wraps all Databricks REST APIs, handling authentication (PAT, Azure, GCP, OIDC), retries, pagination, and long‑running operations, enabling programmatic control of clusters, jobs, Unity Catalog, and other Lakehouse resources.

A matrix-free linear operator library for Python that enables scalable algebra and optimization for large-scale inverse problems in signal and image processing.

A motion profile generator for FRC robots that uses Bézier curves and AD* pathfinding to create and manage autonomous movement routines.

A developer-focused toolkit for Julia that provides standardized interfaces and reusable functionality for creating new GPU array types across different hardware backends.

An image analysis toolkit that provides a simplified interface to the Insight Segmentation and Registration Toolkit (ITK) for image segmentation and registration.

An unofficial API wrapper for Yahoo Finance that provides programmatic access to stock quotes, historical data, and company fundamentals via a TypeScript library, CLI, and AI agent skills.

A modular toolbox for implementing and running large-scale agent-based transport simulations to analyze mobility and traffic flow.

A lightweight system tray app for macOS and Windows that tracks real-time token usage and costs for AI coding tools by parsing local session logs.

A macOS utility that displays visual status indicators for Claude Code and Codex agents next to the MacBook notch, monitoring activity via system processes and transcript files.

A comprehensive development framework for building AI-powered agents and applications integrated into Microsoft Teams.

A high-performance numerical solver suite for a wide variety of differential equations, supporting scientific machine learning and GPU acceleration.

A Python package for compiling and analyzing quantum algorithms to simulate fermionic systems and quantum chemistry on quantum computers.

A CUDA Tile kernel library providing tutorials and examples for tile-based GPU programming to optimize deep learning operators and LLM inference.

A simulation environment for unmanned surface vehicles in marine environments, designed for prototyping autonomous maritime robotics solutions.

An IO-aware, batched K-Means clustering implementation using Triton GPU kernels that enables fast, memory-efficient clustering of massive and high-dimensional datasets.

An AI-powered low-code platform based on TailwindCSS and Drupal that enables rapid drag-and-drop creation of responsive, multi-language web applications and UIs.

A spatio-temporal metric-semantic SLAM system that enables robots to map dynamic environments by reasoning about both short-term movements and long-term scene changes.

A beginner-friendly open-source client for Ollama and other OpenAI-compatible APIs that allows users to manage and chat with local and cloud-hosted AI models.

Ark is a Kubernetes-native framework for building and hosting portable, provider-agnostic AI agents using a declarative approach to avoid vendor lock-in.

A unified agent gateway that enables Cursor IDE and Claude Code CLI to route requests across multiple AI backends like Antigravity, Codex, and AWS Kiro.

A visual configuration platform based on LangGraph that allows users to build complex AI agents using a drag-and-drop interface with customizable state variables for precise logic control.

tslearn is a Python library that brings scikit‑learn‑style machine‑learning tools to time‑series data, offering preprocessing, classification, clustering, regression, and similarity metrics, all compatible with standard scikit‑learn pipelines.