PraisonAI is a production-ready multi-AI agent framework with self-reflection capabilities, designed to create AI agents to automate the solution of various problems from simple tasks to complex challenges. It simplifies the construction and management of multi-agent LLM systems by integrating PraisonAI agents, AG2, and CrewAI into a low-code solution, emphasizing simplicity, customization, and effective human-machine collaboration.

An advanced sequential thinking processing tool based on the Multi-Agent System (MAS), enabling in-depth analysis and problem decomposition by coordinating multiple specialized agents.

devtap is a tool that automatically bridges the output of build/development commands to AI programming sessions. It captures stdout/stderr and provides it to AI programming assistants via the MCP protocol, supporting multi-agent parallel sessions and cross-machine build scenarios.

The Swarms API is a REST API for building, deploying, and managing multi-agent systems. It supports multiple AI models and swarm architectures, providing functions such as real-time monitoring, batch processing, and task scheduling.

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.

An OpenAI agent server based on the MCP protocol, providing various professional agents (such as web search, file search, and computer operation) and a multi-agent coordinator, which can interact with clients (such as the Claude desktop application) through the MCP protocol.

Gaia-X is an enterprise-level AI application platform based on a new generation of AI paradigms. It solves the core pain points of enterprise AI products through an innovative technical architecture and provides core functions such as multi-agent collaboration, natural language RPA, and MCP protocol support.

Beads Village is a multi-agent MCP server for task coordination and file locking between AI agents. It combines Beads issue tracking and a built-in mail system, enabling multiple agents to collaborate in the same codebase without conflicts.

ThinkingCap is a multi-agent research server based on the model context protocol that can run multiple LLM providers in parallel and synthesize their responses to achieve comprehensive multi-angle analysis.

A multi-agent deep research system based on MCP, integrating LinkUp search, CrewAI coordination, and the Gemini large model, providing an interactive interface through Streamlit.

DAKB is a RAG-based multi-agent knowledge sharing platform that provides solutions for semantic search, cross-agent communication, and centralized skill management for enterprise team collaboration and large-scale research projects.

AI-Connect is a cross-machine AI programming assistant communication bridge system based on the MCP protocol, allowing Claude Code instances on different machines to perform point-to-point communication through the bridge server, supporting multi-agent collaboration, offline message storage, and project-based peer management.

A multi-agent debate framework based on the MCP protocol for code review and debate planning. It conducts code reviews by executing multiple AI agents (such as Claude and Codex) in parallel, uses a deterministic scoring system (P0/P1/P2 severity classification) and platform-specific rules, and finally merges the results to generate a review report.

A multi-model AI code review and analysis server based on the Model Context Protocol. It supports the parallel execution of code quality checks, security analysis, and multi-agent consensus reviews by multiple AI models such as OpenAI, Anthropic, and Google Gemini.

This is an MCP (Multi-Agent Conversation Protocol) server project based on the OpenAPI specification, supporting the Google Drive API and providing a full set of toolchains for development, testing, and publishing.

An autonomous multi-agent Security Operations Center built on the Archestra MCP platform, achieving alert classification, threat investigation, automated response, and compliance report generation through real MCP tool calls.

Intellistant is a high-performance multi-agent AI framework built on C++23, supporting MCP protocol tool calls and agent collaboration, designed for software development automation.

Enterprise-level multi-agent orchestration MCP server for coordinating professional agents in architecture, quality, cloud, and prompt to achieve autonomous software development, testing, and deployment, with self-healing, authentication, and analysis capabilities.

MCACP is an MCP server that can bridge any MCP client to any ACP coding agent, enabling the control of a multi-agent system from a single chat window, supporting agent installation, session management, and permission control.

AgentForgeMCP is a multi-agent collaboration platform that focuses on the collaborative work and task allocation among agents.