# Agent framework

This project demonstrates how to integrate a Model Context Protocol (MCP) server with multiple LLM agent frameworks, including Google ADK, LangGraph, OpenAI Agents, and Pydantic - AI. It connects different LLM providers through a standardized interface and uses Logfire for tracking and visualization.

AWorld is a multi - agent system framework aiming to bridge the gap between theoretical MAS capabilities and practical applications, providing a full - set solution from single - agent to multi - agent collaboration/competition. The project supports scenarios such as browser/mobile operations and GAIA benchmark testing, adopts a client - server architecture, integrates a rich toolchain, and includes performance evaluation and training functions.

MCPAdapt is an open - source project aiming to seamlessly integrate the tools of over 650 MCP servers into various agent frameworks, enabling developers to easily use these tools in their agent workflows.