A unified shell environment for AI-driven development that integrates AI coding agents, git diffs, and task trackers into a single multi-pane terminal interface.

A high-performance operator library implemented in Triton that enables LLM training and inference to run across diverse AI accelerators using PyTorch APIs.

A collection of pipelines for LLM development that streamlines synthetic data generation, training, and evaluation across local workstations and large-scale GPU clusters.

A collection of utilities, notebooks, and serving components for working with IBM's Granite Time Series Foundation Models for forecasting.

A Python SDK for deploying local AI agents to Amazon Bedrock AgentCore, providing serverless infrastructure, enterprise security, and integrated tools like memory and code execution.

A high-performance inference and serving platform for local LLMs featuring an OpenAI-compatible API, multi-GPU/multi-node support, and aggressive KV cache compression.

A Go library for running and fine-tuning ONNX transformer pipelines, enabling Hugging Face compatible inference and training natively in Golang.

A specialized plugin for Claude Code and other AI assistants that provides 26 specialist agents and 51 skills to help developers build bug-free Elixir and Phoenix applications.

A library of optimized neural network kernels for Arm Cortex-M processors that maximizes performance and minimizes memory footprint for on-device AI.

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 session log viewer and efficiency analyzer for Claude Code that transforms raw JSONL logs into readable, interactive conversations.

An open-source desktop control console that provides a visual workspace and unified management for local AI coding agents.

A CLI and companion app that orchestrates the deployment and connectivity of a complete local LLM stack, including backends, frontends, and supporting AI services.

A self-hosted mission-execution backend that provides isolated Linux workspaces for autonomous AI agents to run code and execute tasks securely.

A multi-model orchestration policy for Claude Code that routes repetitive coding tasks to cheaper models while reserving frontier models for planning and final judgment.

An MCP memory layer for AI agents that provides persistent, structured graph storage with semantic retrieval and LLM-powered deduplication.

A local-first shared memory system for AI agents and on-device models that stores searchable memory in a single file on disk without requiring a hosted vector DB.

A high-performance, scalable LLM library written in JAX and Python for pre-training and post-training large models on Google Cloud TPUs and GPUs.

A collection of modern, TypeScript‑typed JavaScript packages (`@huggingface/hub`, `@huggingface/inference`, `@huggingface/mcp-client`, etc.) that let you create repos, upload files, and call Hugging Face inference APIs (chat, text‑to‑image, translation, streaming, custom endpoints) from browsers, Node, Deno or Bun.

A dataset and Python toolkit for developing and benchmarking machine learning models to detect and classify undesirable events in offshore oil wells.

A Python-based starter toolkit for deploying and operating scalable, secure AI agents on Amazon Bedrock AgentCore using any open-source framework.

TileDB is a universal storage engine for dense and sparse multi-dimensional arrays, enabling efficient storage and access for complex data science workloads.

A multi-provider gateway that allows coding agents to use various LLM providers and local models via a unified proxy with automatic fallback routing.

A Windows automation plugin that integrates window management, screen capture, OCR, and YOLO detection into a unified API for scripting and desktop automation.

A browser-based Gomoku AI implemented using the Minimax algorithm and Alpha-Beta pruning, featuring adjustable difficulty and a comprehensive performance evaluation suite.

A CLI code search tool that uses structural awareness and cyclomatic complexity to rank results by relevance without requiring an index.

A reference implementation of the agentic registration protocol, enabling AI agents to authenticate with services on behalf of users via identity assertions and claim ceremonies.

An AI-native infrastructure that uses a universal metadata standard to enable the instant generation of enterprise software from text descriptions.

An open-source platform that transforms public GitHub Markdown files into modern, agent-ready documentation sites with built-in AI chat and MCP support.

A Python library for programmatically downloading, uploading, and loading Kaggle datasets, models, and competition resources into data science frameworks.

A high-performance quantum statevector and density matrix simulator that scales from laptops to supercomputers using GPU acceleration and distributed computing.

A production-grade GPU monitoring and management tool that ensures hardware efficiency and reliability for AI/ML workloads.

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

A unified Julia interface that brings together numerous local and global optimization packages into a single API, featuring integration with automatic differentiation.

An automated frontend JS reverse engineering framework that uses AI and JSRPC to turn real browsers into decryption engines and automatically deploys Flask and Burp Suite proxies.

A scalable sandbox environment management framework designed for agentic reinforcement learning, providing tools for building, deploying, and scheduling isolated runtimes.

A CLI tool that searches 19 package registries and community sites to find existing software projects similar to a dev-tool idea using semantic ranking and LLM summaries.

An AI-powered operations control plane that integrates natural language analysis with command execution and human approval for managing servers, network devices, and Kubernetes.

A framework for synthesizing synthetic data and AI feedback to create high-quality datasets for training and fine-tuning AI models.

A lightweight probabilistic programming library powered by JAX that provides fast Bayesian inference via MCMC and variational inference on GPU/TPU/CPU.

A repository of highly-optimized kernels for deep learning, providing low-precision matrix multiplication and convolution libraries for server-side inference and generative AI.

A versatile Bayesian Optimization package designed to efficiently find optimal hyperparameter configurations for machine learning algorithms.

A scalable framework for time series forecasting that allows any scikit-learn compatible machine learning model to be used for forecasting millions of series.

A set of lightweight skill contracts for AI coding that ensures long-term project boundaries, evidence-based results, and integrated project memory.

A C++ library for performing arbitrary optimizations on ONNX models, providing shared optimization passes to be reused across different backend implementations.

A persistent, searchable engineering memory system for AI coding agents that reduces redundant context-gathering and token usage by storing durable repository knowledge.

A compiler that converts ONNX models into standalone C code for efficient neural network inference on microcontrollers.

An AI-native network design tool that generates L1/L2/L3 topology diagrams and device tables from structured data or natural language workflows.