A PyTorch implementation of the SASRec model for sequential recommendation, providing a self-attentive approach to predict user item interactions.

A reinforcement learning framework for training AI agents to play Pokemon Red, featuring coordinate-based exploration rewards and live training broadcasts.

A lightweight C++17 library providing STL-like generic data structures for the GPU to enable flexible and reliable data management in custom kernels.

A set of tools and models for inspecting sparse circuit models, featuring a Streamlit dashboard for visualizing task-specific circuits found through pruning.

A fast and generic Julia implementation of the AlphaZero algorithm that enables training AI agents for combinatorial games using self-play on standard desktop hardware.

A lightweight CLI tool for managing Claude AI custom commands, project-specific configurations (CLAUDE.md), and MCP servers.

A plugin for the DeepSeek Harness web interface that enables workspace path references via an @-mention system, allowing users to easily point AI agents to specific files and directories.

A research‑level router preset for DeepSeek Harness that automatically classifies the first user request and injects the appropriate persona and tool set (spec/react/weak) for the DeepSeek V4 model. It runs as a zero‑dependency Cord‑is plugin, integrates with the dsh‑super‑injector for hot‑reloading, and provides CLI diagnostics. Currently in development (v1.19.1, Aug 2026).

A Python implementation of a Genetic Algorithm to solve the Vehicle Routing Problem with Time Windows (VRPTW), supporting Solomon's benchmark problems and custom data.

A monitoring and detection system for Ollama services that tracks availability, response times, and TPS performance via a modern web interface.

A unified compute and graphics host API and C++ device language that enables same-source programming for CUDA, Metal, OpenCL, Vulkan, and CPU.

A Python library that enables developers to use Airbyte connectors directly in Python for data movement and ETL pipelines without needing the full Airbyte platform.

A lightweight, high-performance WebAssembly runtime that provides a secure sandbox for running LLMs, microservices, and plug-ins across edge devices and servers.

A decentralized application SDK for browsers that integrates wallet identity, private/shared databases, encrypted file storage, and real-time communication tools into a single API.

A data and evaluation toolkit for non-intrusive load monitoring (NILM) that provides tools for dataset conversion, preprocessing, and performance metrics.

A single-binary Kubernetes dashboard with multi-cluster management and AI integration for automated troubleshooting and resource monitoring.

A cross-platform C/C++ library for detecting detailed CPU hardware information, such as instruction sets and cache topology, to enable performance optimizations.

A utility library that extends Python's core functionality with features inspired by Ruby and Haskell, providing enhanced data structures and functional programming tools.

A customizable interaction layer that maps AI IDE actions to various hardware devices and voice commands to streamline AI-assisted coding workflows.

A collection of AI-powered command-line tools for coding workflows, including terminal chat, automated code editing, and context-aware refactoring.

An open-source documentation platform that converts Markdown and MDX into professional docs sites with built-in AI chat and OpenAPI API references.

An MCP server that allows AI coding agents to interact with a running Ruby on Rails application's runtime, database, and logs during development.

A web GUI for tmux optimized for AI agent TUIs, allowing users to manage and interact with agent sessions across desktop and mobile devices.

A secure command-line interface that gives AI agents access to a growth stack for querying marketing data, managing ad campaigns, and automating SEO work.

A library and set of tools that use data analytics (like Google Analytics) to predict which pages a user will visit next and prefetch them to improve web performance.

A privacy-first toolkit that automates prompt construction and context management for developers using web-based AI chatbots for coding.

A native desktop GUI client for Elasticsearch, OpenSearch, DynamoDB, and MongoDB that features an AI agent for natural language querying.

A unified API gateway providing stable access to OpenAI, Claude, Gemini, and other major LLMs for enterprises and developers without requiring foreign accounts.

A Python package for balancing biased data samples using weighting methods to ensure a sample accurately represents a target population.

A differentiable tokamak core transport simulator built in JAX for fast forward modelling, trajectory optimization, and controller design in fusion research.

Atlas is a decentralized coordination layer that allows AI agents across different blockchain ecosystems to discover each other, negotiate tasks, and settle payments.

A recommender system for GitHub repositories that suggests new projects to users based on their starred repositories.

An operating system for AI computers that simplifies the deployment and management of AI infrastructure on owner-controlled hardware across NVIDIA, AMD, and Intel accelerators.

A CLI tool that aggregates directories, source code, and web pages into a single Markdown file optimized for LLM ingestion, featuring code compression and token counting.

A toolkit for decrypting and analyzing the safety filters and guardrails used by Apple Intelligence generative models to reveal how content is filtered across different regions.

A workflow layer for AI coding CLIs that adds specialized skills, project knowledge bases, and verification gates to ensure agents complete tasks reliably.

A Git-native control plane that turns Markdown files into repeatable, version-controlled AI agent workflows with built-in behavioral evaluations.

An executable prompt template file format for Generative AI that decouples prompt engineering from application code across multiple languages and model providers.

A PyTorch library for Conditional Flow Matching, providing simulation-free training for continuous normalizing flows to enable fast generative modeling of images, tabular data, and biological dynamics.

A Python SDK for PromptLayer that enables prompt versioning, tracing, and monitoring for LLM applications and agents across multiple AI providers.

A Python library providing a standardized API and benchmark environments for developing and comparing multi-objective reinforcement learning algorithms.

An open-source web application for AI model security assessments that uses probes to test for vulnerabilities and jailbreaks before deployment.

A CLI tool and SDK for running AI agents in isolated, ephemeral microVMs with network allowlisting and secure secret injection via MITM proxy.

A CLI tool that allows users to instantly switch between different Anthropic-compatible AI providers and local backends for the Claude Code CLI.

A CLI tool that integrates BMAD-METHOD planning and Ralph autonomous implementation to move AI-assisted projects from initial analysis to autonomous TDD coding.

An MCP server that provides AI-driven semantic code search for AI clients, using Windsurf's Devstral API to iteratively find relevant code snippets via local commands.

A ComfyUI extension that accelerates Diffusion Transformer (DiT) models through intelligent caching, providing 1.4x to 2.0x speedups for image and video generation.

An MCP server that turns large codebases into searchable, hierarchical feature graphs using RAG, AST parsing, and spectral clustering for high-accuracy AI coding context.