lobehub/lobehub
LobeHub is a platform that enables multi-agent collaboration and human-agent co-evolution by treating AI agents as units of work, providing tools to build, manage, and collaborate with AI agent teams seamlessly.
Awesome MCP › Agent Orchestration Platforms
Agent Orchestration Platforms
tinyhumansai/openhuman
OpenHuman is a local-first personal AI assistant with persistent Markdown memory, multi-agent workflow orchestration, and research tools, connecting to 100+ OAuth integrations and thousands of MCP servers.
assafelovic/gpt-researcher
GPT Researcher is an autonomous AI agent that conducts deep local and web research on any topic, generating detailed, unbiased reports with citations and supporting integration with the Model Context Protocol (MCP) for enhanced data sourcing.
deepset-ai/haystack
Haystack is an open-source AI orchestration framework for building production-ready LLM applications in Python, enabling modular pipelines and agent workflows with explicit control over retrieval, ...
activepieces/activepieces
Activepieces is an open-source AI automation platform providing an extensible MCP toolkit and over 280 MCP servers for AI agents, designed for both technical and non-technical users.
openai/swarm
Swarm is an educational framework by OpenAI for lightweight, scalable multi-agent orchestration using agents and handoffs, designed to explore and teach multi-agent coordination techniques.
superset-sh/superset
Superset is a desktop application designed to orchestrate and manage multiple CLI-based AI coding agents in parallel, using isolated Git worktrees for efficient, context-separated development.
VoltAgent/voltagent
VoltAgent is an open-source TypeScript framework for building and orchestrating autonomous AI agents with support for the Model Context Protocol (MCP) to enable standardized tool interactions and scalable multi-agent systems.
MervinPraison/PraisonAI
PraisonAI is a production-ready Multi AI Agents framework that provides a low-code solution for building and managing multi-agent LLM systems with a focus on simplicity, customization, and human-agent collaboration.
lastmile-ai/mcp-agent
mcp-agent is a lightweight, composable framework for building AI agents and orchestrating multi-agent systems using the Model Context Protocol in a model-agnostic way.
Upsonic/Upsonic
Upsonic is a reliability-focused AI agent framework that supports the Model Context Protocol (MCP) to enable trusted, scalable, and production-ready agent workflows with advanced verification and tool integration features.
strands-agents/sdk-python
Strands Agents is a Python SDK that enables building and running AI agents using a model-driven approach with native support for Model Context Protocol (MCP) servers and multiple AI model providers.
parcadei/Continuous-Claude-v3
Continuous Claude is a context management system for Claude Code that maintains persistent, learning-driven context across sessions, orchestrates multi-agent workflows, and executes MCP without context pollution.
heshengtao/super-agent-party
Super Agent Party is a next-generation middleware platform that upgrades LLM APIs to advanced Agent APIs with MCP support and enables one-click deployment to social platforms like QQ.
evilsocket/nerve
Nerve is a powerful Agent Development Kit for building, running, evaluating, and orchestrating LLM-based agents with native support for the Model Context Protocol (MCP) using declarative YAML and CLI tools.
rinadelph/Agent-MCP
Agent-MCP is a framework enabling coordinated multi-agent AI collaboration through the Model Context Protocol, facilitating efficient and specialized parallel development workflows in AI software projects.
strands-agents/tools
Strands Agents Tools is a versatile toolkit that equips AI agents with diverse capabilities through a model-driven approach, enabling them to perform complex tasks with minimal code.
mozilla-ai/any-agent
any-agent is a unified interface for using and evaluating multiple AI agent frameworks, supporting integration with Model Context Protocol tools and multi-agent systems.
Onelevenvy/flock
Flock is a workflow-based low-code platform for rapidly building chatbots, RAG applications, and coordinating multi-agent teams with integrated support for Model Context Protocol (MCP) tools.
avifenesh/awesome-slash
Awesome-slash is an AI-driven automation framework that orchestrates the entire software development workflow from task discovery to merged pull requests using multiple agents, plugins, and specialized skills integrated with Claude Code, OpenCode, and Codex CLI.
cuga-project/cuga-agent
CUGA is an open-source configurable generalist agent designed for enterprise use, supporting complex web and API task execution with OpenAPI and MCP integrations, composable architecture, and advanced reasoning modes.
heurist-network/heurist-agent-framework
Heurist Agent Framework is a modular AI agent framework supporting multi-platform interaction, advanced reasoning, tool integration, and MCP protocol for building sophisticated AI agents and agents-as-a-service.
Chen-zexi/open-ptc-agent
Open PTC Agent is an open source implementation of Programmatic Tool Calling (PTC) with MCP, enabling efficient and powerful code execution workflows for large language models in a secure sandbox environment.
strands-agents/sdk-typescript
Strands Agents SDK for TypeScript is a model-driven, type-safe framework for building and running AI agents with native support for the Model Context Protocol (MCP) and multiple model providers.
HKUDS/AnyTool
AnyTool is a Universal Tool-Use Layer that enhances AI agents by providing fast, scalable, and intelligent tool orchestration through smart context management and adaptive MCP tool selection.
truffle-ai/saiki
Saiki is a customizable AI agent runtime that leverages the Model Context Protocol (MCP) to enable natural language control and orchestration of computers, applications, and services through multiple interfaces including CLI and web UI.
mario-andreschak/FLUJO
FLUJO is an open-source platform that integrates Model-Context-Protocol (MCP) server management, multi-model AI workflows, and secure API key handling into a unified workflow orchestration and chat interface environment.
Azure-Samples/azure-ai-travel-agents
Azure AI Travel Agents is an enterprise application that leverages multiple AI agents orchestrated via the Model Context Protocol (MCP) to enhance travel agency operations with scalable, cloud-native AI services.
dcSpark/shinkai-local-ai-agents
Shinkai is an open-source platform that enables quick creation of collaborative AI agents supporting Model Context Protocol, local and remote AI, and crypto payments through a no-code interface.
corespeed-io/zypher-agent
Zypher Agent is a minimal yet powerful framework for creating production-ready AI agents with full control over tools, providers, and execution flow, featuring native support for the Model Context Protocol (MCP).
puppyone-ai/DeepWideResearch
Open Deep Wide Research is an open-source, MCP-compatible agentic RAG system that offers granular control over data sources, reasoning depth, and information breadth to optimize response quality, speed, and cost across various scenarios.
Abiorh001/mcp_omni_connect
MCPOmni Connect is a universal CLI client and intelligent AI agent system that connects to multiple Model Context Protocol (MCP) servers, enabling advanced autonomous task execution, tool orchestration, and resource management across diverse AI models and transport protocols within the MCP ecosystem.
dodufish/PIXRA
PIXRA is a reliability-focused AI agent framework that integrates the Model Context Protocol to enable production-ready, scalable, and trustworthy AI workflows with advanced verification and multi-agent capabilities.
keta1930/mcp-agent-graph
Multi agent platform with a visual graph editor, long term memory and MCP integration that connects agents to external tools, databases and APIs, deployed as a FastAPI backend with Docker services.
weam-ai/weam
Self-hosted open source AI workspace for teams with multi-provider chat, shared prompt and agent libraries, built-in RAG, and MCP integrations such as Gmail, Slack and Google Drive.
saigontechnology/AgentCrew
Python multi agent platform with desktop, terminal, job and HTTP modes where specialised agents hand off tasks to each other and can be given external tools over the Model Context Protocol.
vortezwohl/Autono
Autono is a ReAct-based highly robust autonomous agent framework that supports adaptive decision making, multi-agent collaboration, and integration with the Model Context Protocol (MCP) for flexible and efficient task execution.
Ejb503/multimodal-mcp-client
A modern voice-controlled AI client leveraging Model Control Protocol (MCP) and Google Gemini to enable multimodal, voice-first AI workflows and extensible AI orchestration.
juspay/neurolink
A TypeScript SDK presenting one interface over more than twenty LLM providers, with MCP client support, voice, RAG, memory and document processing.
RedDotRocket/AgentUp
A configuration-driven Python framework for building portable AI agents, with scope-based access control over the MCP servers and tools an agent may reach.
eschnou/OpenGPA
Self-hosted Java general-purpose agent built on Spring AI, doing ReAct multi-step reasoning with pluggable actions, RAG over a pgvector store, web browsing and MCP as one of its tool integrations.
subeshb1/agenite
TypeScript framework for building AI agents with typed tools, pluggable LLM providers, generator-based execution and middleware, including an @agenite/mcp client package for connecting agents to MCP servers.
intelligentnode/Intelli
Python framework for chatbots and multi-agent flows across many model providers, with an optional MCP extra that lets flows call MCP servers, plus calculator and dataframe server samples.