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
keta1930/mcp-agent-graph
Agent-Graph is a multi agent system built around context engineering that combines agents, graph based workflows, long term memory and Model Context Protocol integration behind a visual development experience. It runs as a FastAPI backend with a prebuilt frontend, using Docker Compose for MongoDB and MinIO and uv or pip for the Python service, and it requires Python 3.11 or newer plus a few gigabytes of memory and disk. Administrators log in with credentials from the environment file and other users register with an invitation code; API documentation and a health endpoint are served next to the web interface. The core objects are agents that pursue goals with tools and memory, graphs that orchestrate several agents as nodes and edges for predictable multi stage tasks, models that speak the OpenAI compatible API for both text and vision, a memory layer split into short term conversation context and long term stores for user preferences and agent knowledge, a prompt center for reusable templates with categorisation and cross project references, and projects that group conversations around shared files. Workflow features include a drag and drop graph editor supporting linear, parallel, conditional and nested layouts, subgraph nesting so an entire graph can act as a single node, handoffs that let a node choose the next node for branching and iterative loops, and scheduled tasks driven by cron expressions with concurrent instances and execution history. MCP is the main extension mechanism: the platform connects to external tools and data sources such as databases, APIs, file systems and cloud services through MCP servers, and a built in MCP Builder helps create those connections alongside tools for agent creation, graph design, prompt generation, task management, sub agent delegation, file handling and memory queries. Team features cover invitation codes, member management and three permission roles. Documentation is published separately in English and Chinese.
https://github.com/keta1930/mcp-agent-graph
Also in 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.