Open-source protocol suite standardizing LLM, Vector, Graph, and Embedding infrastructure across LangChain, LlamaIndex, AutoGen, CrewAI, Semantic Kernel, and MCP. 3,330+ conformance tests. One protocol. Any framework. Any provider.

The first AI-native CLI for trading crypto, stocks, forex, and derivatives.

A simple OIDC / OAuth Identity Provider (IdP) server for your tailnet.

MCPMark is a comprehensive, stress-testing MCP benchmark designed to evaluate model and agent capabilities in real-world MCP use.

A curated list of AI tools, libraries, and resources for economics research, teaching, and policy analysis. Maintained by the OpenEcon team.

MCP tool: let you point at DOM elements for your favorite agentic coding tool. Let AI see what you see.

Open-source terminal SSH manager and SSH config editor in Rust. Live tunnel monitoring with throughput, channel events and per-client roster. Fuzzy search hundreds of hosts, sync from 16 clouds, transfer files, manage Docker and Podman over SSH, sign short-lived Vault SSH certs and expose an MCP server for AI agents.

Create agentic AI workflows in ROBLOX Studio

一键给Claude Code 提高智商，包含生产级 agents、skills、hooks、commands、rules 和 MCP 配置

Asking yours data in a natural language way through pre-modeling (data models and semantic models).

Any AI, replaces Claude Code, Cursor, OpenClaw. Over 18 LLM providers (Claude, OpenAI, Gemini, Ollama, Zai, HF, Qwen) wired into a native Mac app that writes code, builds Xcode projects, bumps versions, manages git, automates Safari, use AppleScript, JS or Accessibility, extend Agent! w/ MCP Servers, run tasks from your iPhone via Messages.

RenderDocMCP

Workflow orchestration CLI with MCP endpoint support and multi-agent dashboard

just-prompt is an MCP server that provides a unified interface to top LLM providers (OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama)

A MCP Server for Azure AI Foundry: it's now moved to cloud, check the new Foundry MCP Server

Give your AI agents persistent memory.

Unified Java AI toolkit with multi-model access and agent tooling, distinguished by built-in MCP gateway, RAG workflows, and coding-agent capabilities.

The open-source memory operating system for AI agents. Persistent memory, semantic search, loop detection, agent messaging, crash recovery, and real-time observability.

An MCP Multimodal AI Agent with eyes and ears!

🤖🕰️ An MCP server that gives language models temporal awareness and time calculation abilities. Teaching AI the significance of the passage of time through collaborative tool development.

Python toolkit to build graph-enhanced GenAI apps with hierarchical lexical graphs and hybrid retrieval.

🌋 Build AI agents that seamlessly combine LLM reasoning with real-world actions via MCP tools — in just a few lines of TypeScript.

AI-powered E2E testing for 10 platforms. 253 MCP tools. Zero config. Works with Claude, Cursor, Windsurf, Copilot. Test Flutter, React Native, iOS, Android, Web, Electron, Tauri, KMP, .NET MAUI — all from natural language.

Code search MCP for Claude Code. Make entire codebase the context for any coding agent. Embeddings are created and stored locally. No API cost.