paperclipai/paperclip
Node.js server and React dashboard that runs teams of AI agents as a virtual company, connecting them to outside tools through governed remote MCP connectors.
Awesome MCP › Agent Orchestration Platforms
saigontechnology/AgentCrew
AgentCrew is a Python platform for building a team of specialised AI agents, each defined with its own system prompt, tool set and personality. Agents hand work to one another through an @AgentName mention, and the receiving agent continues with full context and its own instructions. The documentation describes typical roles such as an architect that weighs trade offs before code is written, a coder, a reviewer, a researcher that cross references sources and a browser operator that navigates web applications and fills forms. It offers four ways to work: a desktop graphical application for daily use, a console mode aimed at remote servers and keyboard driven workflows, a one shot job mode that takes an agent name, a task and file globs for CI and batch processing, and an A2A HTTP server that exposes agents to other applications and lets several instances form a network. Installation is a shell or PowerShell one liner or a pip install of the agentcrew-ai package, and Python 3.12 or newer is required. A wide range of model providers is supported: pay as you go keys for OpenAI, Anthropic, Google Gemini, Together AI, Fireworks, DeepInfra and CrofAI, subscription based access through OpenCode Go, ChatGPT Codex and GitHub Copilot with dedicated authentication commands, and fully local endpoints such as Ollama or llama.cpp for offline use. Keys come from environment variables or a JSON config file, and agents are declared in an agents.toml file or created interactively. Its relevance here is the tool layer: agents can be granted MCP tools, meaning external capabilities reached over the Model Context Protocol, and MCP servers form a documented configuration section alongside providers, agents, themes and plugins. MCP is one extensibility mechanism among several rather than the focus, which is multi agent orchestration and delegation.
https://github.com/saigontechnology/AgentCrew
Also in Agent Orchestration Platforms
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.
ruvnet/ruflo
Agent meta-harness that wraps Claude Code and Codex with 100+ specialized agents, coordinated swarms, persistent cross-session memory, and an MCP server so any MCP client can drive it.
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.