LLM Multi Agent

大模型多智能体

Focus on Multi-Agent Applications in Large Models

A2A----Ushering in a New Era of Agent Interoperability

This blog post introduces Google's A2A (Agent to Agent) framework, an open standard and protocol designed to enable seamless interoperability between intelligent agents.

OpenManus Technical Analysis - Architecture and Implementation of an Open-Source Agent Framework

OpenManus is an open-source agent framework designed to enable users to perform complex tasks through simple instructions, featuring a modular architecture with core components like the Agent Layer, Tool Layer, and LLM Interaction Layer. It supports tasks such as programming, web browsing, and file processing, offering a flexible and extensible platform for building AI agents, with future plans to enhance planning capabilities, expand tool sets, and improve user experience.

AI Agent

This blog is a brief summary of the Agent application section in the paper "Agent AI： Surveying the Horizons of Multimodal Interaction" by Professor Fei-Fei Li et al.

Agentic AI：The Key to Unlocking a New Era of Intelligence

A summary of OPENAI's paper "Practices for Governing Agentic AI Systems," discussing the potential benefits of Agentic AI and how to maintain its safety.

AutoGen

An Open-Source Programming Framework for Agentic AI.

LangChain

LangChain is a framework for developing applications powered by large language models.

MCP

MCP is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications. Just as USB-C provides a standardized way to connect your devices to various peripherals and accessories, MCP provides a standardized way to connect AI models to different data sources and tools.