mcp-use is the easiest way to interact with mcp servers with custom agents

Browser extension to enable MCP in claude.ai

The hypermedia framework.

Lightweight framework for building Agents with memory, knowledge, tools and reasoning.

The TypeScript AI agent framework. ⚡ Assistants, RAG, observability. Supports any LLM: GPT-4, Claude, Gemini, Llama.

Header-only portable implementations of common Intel intrisics, including cryptographic instructions.

Agent File (.af): An open file format for serializing stateful AI agents with persistent memory and behavior. Share, checkpoint, and version control agents across compatible frameworks.

Rogue programming language. Ergonomic, object-oriented, high-level, multi-platform, compiles to C.

Playwright MCP server

Virtual TCP/IP stack that can run anywhere 🌐 📚

OpenAPI 3.0 Specification for the Box APIs

A Wasm-first VFS

Build and deploy AI Agents on Cloudflare

Ignition is a powerful CLI tool for building, managing, and running WebAssembly functions using Extism. Think of it as "Docker for WebAssembly functions"

A Model Context Protocol (MCP) server implementation for the OpenLedger API. This server provides structured context to AI models according to the MCP specification.

An open-ended eval framework for mcp.run tools

A Conversational Speech Generation Model

Powershell SDK for Microsoft Graph

Anthropic node support for MCPX

Executable GenAI prompt templates

Automatable GenAI Scripting

The most reliable AI agent framework that supports MCP.

Build effective agents using Model Context Protocol and simple workflow patterns

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

OPEN COMPOSABLE, ISOLATED, EXTENDABLE TASK LIBRARY

🔩 Serverless for stateful backends