A local MCP server that connects ChatGPT to your local machine and allowed repositories, enabling the AI to read, search, and edit code directly.

A collection of official AI agent skills that provide AI coding assistants with specialized knowledge for building, deploying, and debugging Expo and React Native applications.

Science Skills is a set of plug‑in modules that extend the Google Antigravity AI assistant with ready‑to‑run workflows for genomics, structural biology, cheminformatics, literature search and related scientific tasks. Each module bundles prompts, helper scripts and references, installs needed dependencies via the `uv` manager, and can be enabled with a single `npx skills add` command. The collection is Apache‑2.0/CC‑BY licensed and designed for easy customization in a personal skills directory.

An open-source framework for building and deploying customizable on-device machine learning pipelines across mobile, web, desktop, and IoT devices.

OpenLake is an open‑source Rust storage engine that delivers sub‑millisecond, million‑IOPS access for LLM inference and training. It offloads KV‑cache, serves vector‑DB queries, and provides fast checkpoint/object storage via GPUDirect/ RDMA and an S3‑compatible API, enabling GPUs to stay busy and reducing overall compute cost.

llm‑d is an open‑source, CNCF‑sandbox project that adds production‑grade routing, KV‑cache tiering, and expert‑parallelism to existing LLM model servers (vLLM, SGLang). Delivered as Helm charts for Kubernetes, it lets organizations serve large language models at scale with lower latency and higher throughput across many accelerator types.

A local-first screen and audio recording tool that creates a searchable AI memory of your computer activity to provide context for AI agents.

Milvus is a high-performance, distributed vector database built for scaling AI applications that require efficient search and organization of massive amounts of unstructured data.

A zero-latency, zero-setup sandbox for running AI agents securely with fine-grained, per-command policies and isolated tool execution.

A reference implementation for autonomous vulnerability discovery and remediation that uses Claude to find, verify, and patch security bugs in source code.

An AI-guided workflow for creating editable scientific figures in Origin, ensuring scientific accuracy through human-in-the-loop data confirmation.

An open delivery harness for coding agents that turns AI-generated code into a structured software delivery loop with stateful tracking and context routing.

An open-source front-end quality system that turns best practices into a practical review workflow for humans and AI agents via a website and MCP server.

A WebAssembly binding for llama.cpp that enables running LLMs, multimodal models, and tool calling directly in the web browser using WebGPU and Wasm.

An open-source, real-time analytics and search database that provides fast SQL analytics and hybrid search across structured, text, and vector data.

A Git-native, persistent memory layer for AI agents based on the Open Knowledge Format (OKF), providing fast local search and version-controlled knowledge storage.

A vision-driven GUI agent for E2E testing that allows users to automate and verify user interfaces across web, mobile, and desktop using natural language instructions.

A scalable infrastructure for the fine-tuning, evaluation, and deployment of over 1,000 text and multimodal large models.

A universal morphing library for stroke-based icons that uses spring physics and mathematical alignment to create smooth transitions between any two icons.

An open-source toolkit for Answer Engine Optimization (AEO) and Generative Engine Optimization (GEO) that audits and improves a website's visibility and citability by AI answer engines.

A GPU-optimized library for training massive transformer models at scale, providing advanced parallelism strategies and optimized building blocks for distributed training.

A React design system for agentic interfaces that provides AI-specific UI components as source files, featuring an MCP server for AI-assisted installation.

Cloudflare Agents is a TypeScript SDK that turns Cloudflare Durable Objects into persistent, real‑time AI/agent workloads. It provides type‑safe RPC (`@callable`), WebSocket sync, scheduling, AI chat, tool‑calling, voice, email, payments (x402), workflows, and a full React hook library. Agents hibernate when idle and can be deployed at millions‑scale with zero idle cost.

A portable agent plugin that provides AI coding tools with expert SwiftUI best practices, modern API references, and a toolchain for analyzing performance traces.

A mobile and web client for Claude Code and Codex that allows developers to remotely monitor and control AI coding agents with end-to-end encryption.

A command-line interface for DingTalk Workspace that enables humans and AI agents to secure access and manage enterprise data through structured commands.

An inference library for running local LLMs on consumer GPUs featuring EXL3 quantization, parallel inference, and CPU offloading for large MoE models.

An open-source desktop SQL workspace supporting multiple databases with built-in AI text-to-SQL, SQL notebooks, and an MCP server for AI agent integration.

A plugin marketplace and discovery platform for Claude Code that provides curated agents, commands, and hooks to extend AI development workflows.

An open-source continuous inference research platform that tracks real-time performance gains of LLM inference frameworks across various high-end hardware.

A desktop AIOps agent for Windows and macOS that automates IT operations tasks like alert analysis and system inspection through natural language and toolchain integration.

A desktop and mobile UI for Claude Code, Cursor CLI, and Codex that provides a graphical interface for managing AI agent sessions.

A Chromium-based secondary browser designed for AI agents to use your real authenticated logins to automate web tasks locally and in parallel.

An open-source library for intelligent LLM routing that dynamically selects the most suitable model for each query to optimize inference cost and performance.

Rig is a Rust library that provides a unified, modular API for building LLM‑powered applications. It includes a ready‑made agent runtime (multi‑turn, streaming, tool‑calling), abstractions over 20+ model providers and 10+ vector‑store back‑ends, GenAI observability support, and optional recording/replay for testing. The crate works on native and WebAssembly targets and is used in production by companies such as St Jude, Neon, and Ryzome.

A library of context-providing skills for AI coding assistants to help them generate accurate, up-to-date code for the Gemini API and SDKs.

A high-performance CLI tool and visualization dashboard for tracking token usage and costs across multiple AI coding agents.

A token management tool for AI coding assistants that reduces API costs by compressing context waste and preventing data loss during session compaction.

An open-source database of AI model specifications, pricing, and capabilities accessible via a public API.

An experimental fork of Windows Terminal with native AI agent integration, allowing users to to interact with ACP-compatible agents directly within their shell context.

An AI-powered design review tool for KiCad that analyzes schematics and PCB layouts to catch bugs, simulate circuits via SPICE, and predict EMC risks.

A Claude Code skill for reverse engineering Android apps to extract HTTP APIs and recover original Kotlin class names from obfuscated binaries.

A management layer for AI coding agents that combines kanban planning with dedicated workspaces for agent execution, review, and app previewing.

A local-first desktop workspace for running multiple AI coding agents and shells in parallel, providing session persistence and unified management of MCP servers.

A remote desktop solution that delivers a full interactive graphical interface directly inside an SSH session without requiring additional ports or specialized clients.

A simulation framework for evaluating customer service agents across text and voice modalities, testing their ability to follow policies and use tools in real-world domains.

An optimization library for LLMs and visual generation models that uses specialized kernels and an efficient runtime to maximize inference throughput and minimize latency on NVIDIA GPUs.

A Chinese-enhanced version of the superpowers framework that provides 20 systematic work methodologies to help 26 different AI coding tools plan, debug, and review code more professionally.