Ray is a unified framework for scaling Python and AI applications from a single laptop to a distributed cluster, providing a core runtime and specialized libraries for ML compute.

A review-first terminal diff viewer designed for agent-authored changesets, featuring interactive UI, inline AI annotations, and multi-file navigation.

An open-source context layer and metadata management platform that provides AI agents and users with the governed business semantics, lineage, and organizational memory needed to trust and use enterprise data.

A tiny, educational autograd engine that implements backpropagation over a scalar-based DAG to help users understand the internal mechanics of neural networks.

A local-first AI workspace that consolidates multi-agent chat, coding, and visual workflows into a single desktop or web console.

An open-source MCP server that connects AI agents and IDEs to enterprise databases through prebuilt generic tools or a customizable framework for secure, structured data access.

An array framework by Apple machine learning research optimized for machine learning on Apple silicon, featuring a unified memory model and familiar NumPy/PyTorch-like APIs.

A local model gateway for Cursor that lets users connect their own API keys and model providers while preserving agentic features like tool calling and MCP.

An automated screenshot and preview video generator for App Store and Google Play that integrates with coding agents to create professional store assets.

A DeepSeek Harness plugin that provides comprehensive visual insights and management tools for an AI agent's context window, token usage, and tool activity.

An MCP server that connects Google Search Console to AI assistants, enabling natural language analysis of SEO data, indexing audits, and sitemap management.

An open-source platform for building durable, long-running AI workflows and agents in TypeScript with built-in retries, observability, and elastic scaling.

A KV cache management layer for LLM inference that reduces TTFT and improves throughput by making KV caches persistent and reusable across requests and engines.

An MCP server that enables AI agents to automate native iOS and Android apps across simulators, emulators, and real devices using a platform-agnostic interface.

MTPLX is a macOS‑only app and CLI that runs large language models (Qwen, Gemma, etc.) on Apple Silicon using multi‑token prediction (speculative decoding). It delivers 1.5‑2× faster generation while keeping exact model outputs, offers auto‑tuning, a GUI dashboard, and an OpenAI‑compatible local API, plus tools to convert custom checkpoints into MTPLX‑ready models.

An open-source AI engine that lets you run LLMs, vision, voice, and image models locally on any hardware with drop-in OpenAI-compatible APIs.

A tile-based system for writing memory-safe, data-race-free GPU kernels in idiomatic Rust, utilizing JIT compilation via CUDA Tile IR.

A high-performance web scraping and crawling engine that converts URLs into clean markdown or structured JSON for AI agents and LLMs.

An official inference framework for 1-bit (ternary) LLMs that enables fast, energy-efficient, and lossless inference on CPUs and GPUs.

A collection of AI agent skills for Codex and Claude Code that automates the end-to-end production of polished Three.js browser games, from asset generation to QA.

n8n‑MCP is a Model Context Protocol server that exposes the full n8n node catalogue (≈2.7 k nodes) as an API. AI models can search nodes/templates, fetch detailed schemas and docs, validate configurations, and even create or update real workflows on a n8n instance. It can be used as a hosted SaaS service or self‑hosted via Docker, and includes safety guidance for AI‑driven workflow editing.

A terminal emulator designed for running multiple AI coding agents simultaneously, featuring integrated Git diffs, token cost tracking, and multi-session management.

A fast, keyboard-first file manager for Linux desktops that combines spatial Miller-column navigation with fuzzy search and rich file previews.

A comprehensive tool for extracting and downloading images, videos, and post information from Xiaohongshu, featuring a TUI app, browser scripts, and API/MCP server modes.

An open, event-based protocol that standardizes how AI agents connect to user-facing applications, enabling real-time interaction and generative UI.

A TypeScript/React library for building production-grade AI chat interfaces with composable primitives and support for multiple AI backends.

A comprehensive, multilingual learning map and tutorial series that teaches users how to build full-stack AI applications through AI-assisted "vibe coding."

A toolkit that provides AI coding agents with the tools, knowledge, and guardrails needed to build, deploy, and manage applications on AWS.

An MCP server that provides AI assistants with real-time market data, technical analysis tools, and backtesting capabilities for stocks, crypto, and forex.

An open-source, event-driven orchestration platform for data, AI, and infrastructure workflows that unifies scheduled and real-time automation using a declarative YAML interface.

A local-first issue board that integrates into the Codex AI agent, allowing the AI to autonomously track and update project tasks.

A professional API gateway that turns a pool of Codex accounts into a unified, observable, and schedulable OpenAI/Anthropic-compatible service.

A plugin and MCP server that streams live Figma document data to AI tools, bypassing official API rate limits to enable seamless design-to-code workflows.

An autonomous offensive security framework that automates bug bounty hunting and vulnerability research using an AI agent or MCP server integration.

A secure agent that connects private or localhost MCP servers to OpenAI-hosted products like ChatGPT and Codex without exposing them to the public internet.

An iOS uploader for Google Photos that spoofs device profiles to enable unlimited storage and provides advanced bulk upload tools.

A KV cache library that brings virtual memory abstraction to LLM serving, enabling elastic and demand-driven GPU memory sharing across multiple models.

The official CLI for the MiniMax AI Platform, enabling text, image, video, speech, and vision generation from the terminal or within AI agents.

A local AI-powered PR review and management tool that uses isolated git worktrees to analyze, fix, and manage GitHub pull requests using Claude or Codex.

Navop是一个用Rust和GPUI构建的原生桌面工作区，将数据库管理、SSH/SFTP、远程桌面、监控和AI代理整合在一起，减少开发者使用多个工具带来的切换成本，并支持通过ACP和MCP连接外部AI代理。

A curated registry of design system skill files that provide AI coding agents with specific UI rules, tokens, and accessibility constraints to ensure consistent, high-quality design implementation.

A CLI tool that enables AI coding agents to verify their own work by running tests against live applications and fixing bugs based on failure bundles.

A Python package for generating text and fine-tuning large language models on Apple silicon using the MLX framework.

A desktop reverse engineering tool for HarmonyOS and Android apps that combines static analysis, device mirroring, and an AI agent for security research.

A unified framework to evaluate generative language models on a large number of standard academic benchmarks, serving as the backend for the Open LLM Leaderboard.

A multi-agent offensive-security framework that turns existing AI coding agents into automated zero-day hunters for authorized security testing.

An open-source, datacenter-scale orchestration layer that coordinates multiple inference engines across GPU clusters to maximize throughput and minimize latency for LLMs and multimodal models.

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