# Multi - agent

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.

Agentis MCP is a flexible multi - agent framework for building powerful AI agents, supporting MCP server connection, and providing functions such as tool access, resource retrieval, and multi - agent workflow orchestration.

Digimon Engine is an open - source multi - agent, multi - player game framework focusing on AI - native game and intelligent metaverse development. It supports social and financial AI agents, provides an immersive game experience, and is committed to building an AI agent environment similar to that in 'Westworld'.

CrewAI Crew is a multi - agent AI system project based on the crewAI framework, aiming to complete complex tasks through configuration and collaboration.

Open Multi - Agent Canvas is an open - source multi - agent chat interface that supports managing multiple agents in dynamic conversations for travel planning, research, and general task processing.

KuzuDB MCP Server is a protocol server that provides access to graph databases, supporting web interface management, multi - agent coordination, automatic connection recovery, and AI - driven natural language query generation.

Haiku RAG is an intelligent retrieval - augmented generation system built on LanceDB, Pydantic AI, and Docling. It supports hybrid search, re - ranking, Q&A agents, multi - agent research processes, and provides local - first document processing and MCP server integration.

The OWL x WhatsApp MCP Server project is an application that integrates WhatsApp messaging functionality with a multi - agent collaboration framework. It enables AI agents to access, search, and send messages to WhatsApp data through the Streamlit interface and supports real - time web searches.

This project is an MCP server based on a multi - agent system. It analyzes and solves complex tasks by generating multiple agents with professional perspectives in parallel, supports multiple problem - solving strategies, and integrates the outputs of each agent to generate a final solution.

A multi - agent system laboratory project for educational purposes, simulating e - commerce and health consultation scenarios, demonstrating multi - agent collaboration, the use of the MCP protocol, and the integration of different LLM models.

NotHumanAllowed is a multi - agent cognitive dataset generation engine that conducts multiple rounds of deliberation through 38 professional AI agents, generating auditable reasoning trajectories and structured knowledge records for training next - generation AI systems.