A security auditing tool for AI agent skills that analyzes markdown-based skills to identify potential security risks and provide evidence-backed reports before execution.

A ComfyUI custom node pack that enables ultra-high-resolution (4K+) generation for Diffusion Transformers like FLUX and Qwen Image using training-free model patching and cascade refinement.

A native macOS AI desktop companion that acts as a unified control plane for multiple AI agents and terminals, integrating system diagnostics and cross-device task management.

A deep neural network for visual localization that determines an image's position and orientation by matching it to 2D public maps like OpenStreetMap.

A Python implementation of Recursive Language Models that analyzes large contexts by keeping data in a restricted REPL, reducing token usage and cost while improving correctness.

A full-stack starter template for AgentCore that provides a secured React frontend and AWS infrastructure to accelerate the deployment of AI agent applications.

A library that enables zero-copy, multi-host communication of JAX arrays, allowing JAX simulations to scale across entire CPU and GPU clusters.

A curated registry of Model Context Protocol (MCP) servers that allows developers to discover and deploy secure, containerized tools for AI assistants.

The official Python SDK for xAI's APIs, enabling developers to integrate text, image, and video generation and understanding into their applications.

KISS Sorcar is an open‑source, local‑first AI‑agent framework that runs a daemon (`kiss‑web`) and provides VS Code, web/mobile, and Python interfaces for issuing natural‑language tasks. It supports any LLM you configure (OpenAI, Anthropic, Gemini, local endpoints, etc.), mixes multiple models in one workflow, and includes 43 built‑in third‑party agents for messaging, email, smart‑home, and productivity services. Custom Python “extension agents” let you define prompts, tools, budgets, and safety hooks per task. All prompts stay on your machine; the system handles git worktree isolation, voice wake‑word, scheduled automations, and tool calling, making it a privacy‑focused, extensible personal AI assistant.

A GPU library built on Triton and CuteDSL that provides high-performance implementations of classical machine learning operators like k-means, PCA, and ANN search.

An enterprise-grade AI agent SaaS framework built on .NET 9 that integrates RAG, multi-agent collaboration, and multi-tenant architecture for building AI middle-platforms.

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

A high-performance C++ vector indexing library for similarity search, featuring specialized indexes for both sparse and dense vectors with Python and TypeScript bindings.

An integration library that allows JAX users to call custom Triton kernels for high-performance GPU operations within JAX programs.

A Swift library for integrating various AI APIs into apps with an optional secure proxy backend to protect API keys and manage rate limits.

A voice-driven AI interface that allows users to interact with diverse AI characters using a variety of LLM and TTS providers, supporting real-time conversations and local voice cloning.

An MCP server that gives LLMs read and write access to Airtable databases, enabling them to manage records, schemas, and comments.

A JavaScript/TypeScript SDK for the Qdrant vector search engine, providing REST and gRPC clients to manage and search vector data.

An MCP server that gives Claude private, local-first journaling and semantic search capabilities to maintain persistent memory across conversations.

A Unix-style CLI tool for managing AI coding agents across local, Docker, and remote hosts, providing a unified interface for deployment, monitoring, and state synchronization.

A centralized proxy and management platform for Model Context Protocol (MCP) services that allows users to discover, install, and monitor services from a single interface.

A collection of 40 specialized plugins for AI coding assistants that provide evidence-tracked guidance and tooling for SAP development across BTP, ABAP, and Fiori.

A Clang compiler plugin for C++ that provides automatic differentiation by transforming source code to generate functions for derivatives, gradients, and Hessians.

RxInfer.jl is a Julia library for fast, reactive Bayesian inference using factor‑graph message passing. It automatically exploits conjugate relationships for exact updates, supports non‑conjugate models, and can be deployed as a REST API via RxInferServer. Install with `] add RxInfer`, define models with the `@model` macro, and call `infer` to obtain posteriors.

py123d is a Python library that unifies many autonomous‑driving datasets (Argoverse 2, nuScenes, Waymo, nuPlan, etc.) by converting them to a fast, zero‑copy Apache Arrow format and exposing a single API for cameras, lidar, maps, and labels. It includes CLI tools for downloading and converting data, Hydra‑based pipelines, and an interactive 3‑D viewer. Install via `pip install py123d` (with optional extras for each dataset) and use the provided commands to fetch, convert, and visualise data.

An inference engine and compiler framework that converts ONNX models into deterministic static libraries for resource-constrained microcontrollers.

A Claude Code plugin that implements a structured knowledge-work loop to capture, store, and reuse project learnings in a persistent knowledge base.

A unified management app for AI coding agents that centralizes the configuration, extensions, and security auditing of multiple agents in one interface.

A PyTorch library for training neural networks with multiple losses, providing tools for scalarization and Jacobian descent to resolve optimization conflicts in multi-task learning.

A multi-agent AI framework for Claude Code that implements a spec-driven development workflow to turn ideas into shipped code via structured planning and parallel specialist agents.

An AI-powered novel writing system that ensures long-term narrative consistency by managing story elements as structured data and state snapshots rather than relying on LLM context windows.

A production-tested AI agent harness that implements SAFe methodology to coordinate multi-agent teams across various AI providers like Claude and Gemini.

A PyTorch implementation of Masked Autoencoders for spatiotemporal learning, enabling models to learn video representations by reconstructing masked video frames.

A port of Andrej Karpathy's llm.c to the Mojo language, demonstrating that Mojo can achieve C-like performance for low-level LLM training.

An Android chat application that provides a unified interface for interacting with cloud-based LLMs via OpenRouter and locally hosted models via Ollama, LM Studio, and others.

An AI-powered platform that automates the creation of novels, including text generation, consistent character illustrations, and video adaptations.

An open-source AI compiler stack for Tenstorrent hardware that enables the execution and training of models from PyTorch, JAX, and ONNX.

A foundation model for EEG decoding designed for clinical and Brain-Computer Interface (BCI) applications through a pretraining and fine-tuning pipeline.

Training pipelines and an inference engine for machine translation models that power local, client-side web page translation in the Firefox browser.

A layered canvas editor node for ComfyUI that enables image compositing, polygonal inpainting selection, and background removal within the browser.

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

A tool for building RAG applications by crawling websites or processing documents and deploying them to Vespa for hybrid search with an integrated chat UI.

A JAX-based library for second-order optimization of neural networks using the K-FAC optimizer and scalable curvature approximations.

A collection of evaluation metrics for music and audio generative models, providing tools to calculate Fréchet Distance, KL divergence, and CLAP scores for long-form stereo audio.

A set of Ubuntu packages and Docker images that bring current ROCm, PyTorch, llama.cpp, ComfyUI and related GPU‑tuning tools to the legacy AMD GFX906 (Vega 20/MI50) GPU.

WorldScore is an open‑source benchmark for evaluating world‑generation models (3‑D, 4‑D, video). It provides a dataset, generation adapters, a suite of spatial‑temporal metrics, and a public leaderboard. Users register their model via a small YAML config and a Python class, generate videos, run the evaluation script, and submit the resulting JSON score.

The official Svelte MCP server that allows AI models to interact with Svelte-related data and tools using the Model Context Protocol.