A large-scale similar image search tool that uses feature point matching to find full images using a small cropped screenshot.

A macOS notch companion that provides real-time visual feedback, sentiment-based emotional reactions, and usage tracking for Claude Code and Codex activity.

An automated tool that downloads high-quality videos from multiple platforms and uses GPT to generate and burn in bilingual subtitles.

A suite of C++/Python utilities for processing and analyzing sensor and machine perception data from Project Aria AR glasses to support AI and machine perception research.

WelsonJS is a Windows‑only framework that lets you write console or GUI desktop apps with JavaScript (and TypeScript, CoffeeScript, etc.) using the built‑in Windows Script Host engine. It runs without extra runtimes, supports legacy Windows versions, bundles many libraries (jQuery, Monaco, React, ESENT DB, native Windows service APIs), and includes optional LLM integrations (ChatGPT, Gemini). Apps can be packaged as zip files, Inno Setup installers, or simple copy‑and‑run bundles, and a PowerShell bootstrap script can pull the runtime automatically.

An interactive, open‑source tutorial that teaches GPU programming in Mojo through hands‑on puzzles, complete with a `pixi`‑based environment, test harnesses, and community support.

An open-source alternative to Claude Artifacts and v0 that allows users to generate and securely execute AI-generated code across multiple frameworks like Next.js and Python.

A high-performance library for univariate time series forecasting that provides fast, scalable implementations of statistical and econometric models.

A collection of skills for Claude Code that enable AI agents to perform browser automation, UI testing, and deep web research via Browserbase.

An Android application that integrates ChatGPT, local VITS voice synthesis, and Live2D animation to create an immersive, character-based AI companion.

A real-time screen translation tool for Windows games that uses OCR and LLMs to translate on-screen text and audio into the user's language.

A management platform for Hermes Agent that provides a Kanban board and supervision tools to track, review, and schedule autonomous AI tasks.

A high-performance open-source 3D game engine written in C++ featuring advanced Vulkan rendering, hardware ray tracing, and built-in AI integration via an MCP server.

An agent skill that generates hand-drawn editorial illustrations in the Anthropic visual style, transforming abstract concepts into minimalist visual metaphors.

An intelligent terminal assistant for tmux that observes pane content and executes commands to act as a context-aware pair programmer.

An independent security agent for AI-written software that uses a deterministic engine and an investigation layer to find and verify security vulnerabilities.

A cluster configuration generator that provides validated, version-locked recipes to reliably deploy and validate GPU-accelerated Kubernetes clusters for AI workloads.

A collection of intermediate and advanced example applications for building voice and multimodal AI agents using the Pipecat framework.

A self-hosted AI agent orchestration platform that allows operations teams to visually design, manage, and audit agent workflows while engineers handle the system integrations.

A GPU-accelerated DataFrame library for tabular data processing that provides a pandas-compatible API and zero-code change acceleration for pandas, Polars, and Dask.

An open-source self-hosted ML platform that combines an AutoML engine, a control plane for experiment management, and a web UI for a complete train-to-deploy workflow.

DoWhy is a Python library for end‑to‑end causal inference. It lets you define a causal graph, automatically identifies the causal effect, estimates it with a variety of statistical methods, and runs refutation tests to check robustness. The library also supports graphical causal models for root‑cause analysis, counterfactuals, and interventional sampling. Install via `pip install dowhy` and follow the four‑step workflow (model → identify → estimate → refute).

An open-source enterprise data warehouse built in Rust that integrates analytics, vector search, and secure Python sandboxes for AI agent orchestration.

An MCP server and Chrome extension that gives AI agents access to a user's active browser session for real-time debugging, network inspection, and Lighthouse audits.

A Python package for uplift modeling and causal inference that estimates the causal impact of interventions on individual users to optimize targeting and personalization.

A collaboration tool for AI engineers and domain experts to build and curate high-quality datasets for NLP, LLMs, and multimodal models.

A PyTorch library from NVIDIA providing GPU-optimized modules for 3D deep learning, including differentiable rendering, physics simulation, and support for 3D Gaussian splats.

Kungfu is an open‑source CLI/TUI that records LLM‑agent tasks (Work) outside the chat, enabling seamless hand‑off between agents, crash recovery, and auditable logs. It works with any Codex/Claude/OpenCode‑style agent, provides a mock agent for demos, and is released under Apache‑2.0 in Alpha.

A ROS 2 integration for nvblox that enables real-time 3D scene reconstruction and 2D costmap generation for vision-based obstacle avoidance in robots.

An extension of Open3D that provides tools, pretrained models, and pipelines for 3D machine learning tasks like semantic segmentation and object detection.

Vald is a cloud-native, distributed fast approximate nearest neighbor (ANN) search engine designed for searching through billions of dense feature vectors.

An SDK to wrap machine learning models as web servers that connect to Label Studio to automate labeling through pre-annotations and interactive predictions.

A high-performance infrastructure for multi-dimensional sparse attention, implementing Neighborhood Attention to reduce the computational cost of self-attention for 2D and 3D data.

A benchmark framework for evaluating and comparing data-driven and traditional numerical global weather forecasting models using scalable evaluation code and cloud-optimized datasets.

vibecosystem is an open‑source package that expands Claude Code into a self‑organising AI development team. It ships 138 specialised agents, 296 reusable skills, 74 TypeScript hooks and 20 behavioural rules. After a one‑line install you can ask Claude Code to “add a feature” and the swarm of agents will plan, code, review, test and learn automatically. Profiles let you enable only the agents you need to save tokens, and a `vibeco` CLI plus a web dashboard give stats, health checks and token‑cost tracking. All data stays locally in `~/.claude/`; no telemetry is sent. The project also supports Cursor, Codex CLI and OpenCode via dedicated install scripts.

A modified GPT-2 model designed to predict the progression and timing of human diseases based on patient health trajectories from the UK Biobank.

A marketplace of LSP server definitions that lets Claude Code (Anthropic’s AI coding assistant) provide IDE‑like features—go‑to‑definition, hover, find‑references, etc.—for dozens of languages. Install Claude Code ≥ 2.1.50, run `npx tweakcc --apply` to patch it, add the marketplace via `/plugin marketplace add Piebald‑AI/claude‑code‑lsps`, then install the underlying language‑server binaries (rust‑analyzer, pyright, clangd, etc.) as instructed. The repo includes validation scripts to keep the marketplace JSON in sync with the `.lsp.json` configs.

An open-source AI toolkit for fashion technology providing a unified interface for virtual try-on, image/video generation, and multimodal understanding.

A multi-agent collaboration system for open-domain research that transforms queries into citation-grounded relational schemas to ensure comprehensive and traceable information retrieval.

A runtime for Recursive Language Models that allows LLMs to solve complex, adaptive workflows by writing and executing Python code in a sandboxed REPL.

A Pokemon Showdown battle-bot that uses a search engine to play single battles across multiple generations of the game.

A ComfyUI wrapper for Apple's SHARP model that enables monocular 3D Gaussian Splatting from a single image in under one second.

A macOS menu bar app that uses AI to generate, build, and export native SwiftUI applications from simple text descriptions.

A PyTorch-based library that combines deep perceptual models with physics-based optimization for robot learning, providing tools for Lie groups, filtering, and second-order optimization.

A durable execution runtime for Laravel that allows long-running PHP workflows to persist state and resume after failures or restarts.

A highly configurable, zero-code enterprise management system that allows businesses to build custom CRM, MES, and WMS applications with an integrated AI assistant.

NVIDIA DCGM‑Exporter is a Go‑based service that reads GPU telemetry from NVIDIA’s DCGM and exposes it as Prometheus metrics. It runs as a Docker container, a systemd service, or a Helm‑deployed pod, supports TLS/auth, custom metric sets, IPv6, remote hostengine connections, and optional HPC‑job or container labels. Ideal for AI/ML platform monitoring, Kubernetes GPU clusters, and HPC environments.

A lightweight, self-hosted real-time NVIDIA GPU monitoring dashboard that supports single-machine or multi-node cluster tracking.