A local MCP server that enables AI agents to safely control any desktop GUI across Windows, macOS, and Linux using a tiered perception system that prioritizes accessibility data over vision.

Mobile-GS is a real-time Gaussian Splatting framework designed to enable high-quality 3D scene rendering on mobile devices.

Nixtla offers a Python SDK to call TimeGPT, a large transformer model for zero‑shot time‑series forecasting and anomaly detection. The SDK handles API authentication, request/response handling, and optional plotting, and supports fine‑tuning, exogenous variables, multi‑series forecasts, and Snowflake deployment. The model itself is hosted (closed‑source) and accessed via an API key; the SDK is Apache‑2.0 open source.

A curated collection of reusable skills and playbooks for AI coding agents like Claude Code and Cursor, providing structured workflows for tasks like browser automation and codebase planning.

A cross-platform image super-resolution tool that uses AI to upscale images, supporting custom models and modern Nvidia GPUs.

A lightweight 8.3B parameter video generation model that enables high-quality text-to-video and image-to-video synthesis on consumer-grade GPUs.

A terminal coding agent that uses a four-layer compression system to drastically reduce LLM token usage and costs while maintaining performance.

A programming language embedded in C++ and Python designed for writing high-performance image and array processing code across diverse hardware architectures.

The Open Motion Planning Library (OMPL) is an open-source library providing over 40 sampling-based motion planning algorithms for robots to navigate state spaces and avoid obstacles.

A collection of simulation environments and demonstrations for Open-RMF, enabling interoperability and traffic management among diverse robot fleets in complex facilities.

A Photoshop plugin that integrates ComfyUI's AI capabilities directly into the Photoshop interface for a seamless AI-powered editing workflow.

A reinforced cognitive framework for end-to-end autonomous driving that combines a Vision-Language Model with a diffusion planner to generate safe, continuous trajectories.

A comprehensive collection of 328 custom ComfyUI nodes providing all-in-one tools for image, video, and audio generation with a focus on zero external dependencies.

FofaMap is a Python CLI that blends FOFA asset search with an AI‑driven agent. It can run classic FOFA queries, translate natural‑language requests into multiple queries, self‑reflect to improve results, grade evidence, export to XLSX/CSV/JSONL, and optionally generate a Nuclei scan plan that requires manual approval. It also provides a REST API and one‑click integration as a tool for AI coding assistants (Cursor, Claude, LM Studio, etc.).

BuildingAI is an enterprise-grade, no-code platform for creating intelligent AI agents and applications, featuring built-in RAG pipelines, model aggregation, and business billing systems.

A comprehensive marketplace and repository of Model Context Protocol (MCP) servers that allow LLMs to integrate with cloud services, databases, and third-party tools.

A prompt compilation kit for Claude Code that transforms vague image requests into professional, validated prompts for gpt-image-2.

An open-source Python SDK for federated learning that enables secure, privacy-preserving machine learning collaboration across distributed parties without sharing raw data.

A distributed attention mechanism designed for ultra-long context and heterogeneous mask training, offering linear scalability and high performance on H100 and B200 GPUs.

An AI-powered lightweight Kubernetes dashboard that simplifies cluster management through a visual interface, AI-assisted troubleshooting, and MCP-based tool execution.

A flexible Python library for implementing Reservoir Computing architectures like Echo State Networks for time-series prediction and classification.

A research platform for evaluating AI agents in dynamic, evolving environments using the Gaia2 benchmark to test multi-step reasoning and real-world adaptability.

WGAI is a Spring‑Boot + Vue web platform that bundles vision (OpenCV, YOLO, OCR, face ID), audio (speech‑to‑text, ChatGPT‑style dialogue), digital‑human avatars, and AGV navigation into an offline‑first, industrial‑grade AI management system. It offers online data annotation, model training, real‑time video/audio analysis, and system monitoring, with a UI for configuration and a public demo instance. The code is AGPL‑3.0 and support is mainly via a paid Chinese community.

A multi-controlnet platform for Physical AI that transforms video modalities (like depth and segmentation) into high-fidelity training data for robots and autonomous vehicles.

A Python library for building scripted agents and reinforcement learning bots for Pokemon Showdown.

A unified runtime for MCP servers that aggregates multiple servers into one process and provides a progressive discovery workflow to prevent agent context sprawl.

OGhidra is a genuine open‑source project that adds large‑language‑model assistance to the Ghidra reverse‑engineering platform. It lets users ask natural‑language questions, runs AI‑driven analysis (function renaming, malware pattern detection, report generation), and supports both local Ollama models and cloud APIs while keeping binaries private.

A Python SDK for the Piper robot arm that processes CAN bus data frames into custom data types for easier hardware control and monitoring.

A CLI coding agent optimized for reliability with small and local LLMs, featuring robust context management and support for a wide range of model providers.

A security skills framework and ruleset that embeds secure-by-default practices into AI coding agents to prevent vulnerabilities during code generation and review.

Flow‑Next is a plugin for coding agents (Claude Code, OpenAI Codex, Cursor, etc.) that turns a change request into a durable spec, then automatically drives planning, implementation, adversarial review, live QA and PR creation, recording all evidence in the repository.

A runtime security framework for AI agents and coding assistants that prevents prompt injection, secret leaks, and destructive actions through policy-based enforcement.

The official Ruby SDK for the Model Context Protocol, enabling developers to build MCP servers and clients that expose tools, prompts, and resources to AI hosts.

An Android accessibility service that provides real-time UI element data and remote control APIs for UI testing and automation.

A lightweight library for Energy-Based Joint-Embedding Predictive Architectures used to learn representations for prediction and planning across images and video.

An open-source, self-hosted AI agent for companies that integrates with workplace tools to gather context, analyze data, and execute tasks across systems.

An MCP server that integrates the LINE Messaging API, allowing AI agents to send messages and manage LINE Official Accounts.

TinyMPC is a Model-Predictive Control solver designed to run efficiently on resource-constrained microcontrollers for real-time robotics control.

AI Agent Skills is an npm‑based CLI/TUI that ships a curated library of ~115 AI‑agent “skills” (prompt‑code bundles) organized into shelves (frontend, backend, mobile, workflow, agent‑engineering, marketing). It lets you browse, search, install, and manage both local “house‑copy” skills and upstream metadata‑only skills. You can also bootstrap a personal library with `init-library`, add or catalog new skills, vendor copies, sync updates, and generate documentation. Works with any Agent‑Skills‑compatible agent (Claude, Cursor, Gemini, etc.) and supports multiple install targets. Ideal for developers or teams who want a tidy, searchable toolbox of reusable agent capabilities.

A ComfyUI custom node package that uses GVHMR to extract 3D human motion and SMPL skeletal parameters from video.

An open-source platform for building and managing agentic software and AI workflows, turning recurring business processes into durable, controlled automations.

An open-source, self-hosted AI model registry for enterprise inference that serves as a private Hugging Face replacement to accelerate model distribution and secure air-gapped environments.

ScreenCoder is a multi-agent system that transforms UI screenshots and design mockups into production-ready HTML/CSS code using visual understanding and layout planning.

A pi provider extension that integrates Cursor models into the pi agent runtime using the @cursor/sdk, preserving Cursor's native agent loop and features.

A free, open-source collaborative web application for developing and editing OWL 2 and OBO ontologies.

A lightweight, high-performance embedded rule engine for Go that allows dynamic orchestration of business logic through component-based rule chains.

A powerful meme management plugin for AstrBot that enables AI bots to intelligently send, automatically collect, and semantically retrieve memes during conversations.

A self-hosted codebase understanding tool that combines AI-powered natural language querying with fast cross-repository search and IDE-level code navigation.