Awesome MCP › Agent Orchestration Platforms

paperclipai/paperclip

⭐ 112371 TypeScript added to this list on 2026-10-19 repository created 2026-03-02

Paperclip is an open-source orchestration platform for running teams of AI agents as if they were employees of a company: a user defines a business goal, hires agents into roles such as CEO, CTO, engineer, designer or marketer, assigns any LLM or agent harness to each role, and tracks tasks, budgets, skills, permissions and history from one dashboard. The project frames itself as the company around an individual agent, adding org charts, governance and goal alignment on top of raw agent execution rather than managing pull requests directly. A large part of the system is built around the Model Context Protocol: Paperclip implements MCP-based connections so its managed agents can reach external tools and brand-specific integrations, such as Calendly or Firecrawl, through auditable remote MCP connectors instead of ad hoc API keys. Its documentation covers MCP access governance, MCP discovery and performance tuning, a dedicated MCP CLI command, and ongoing plans for public MCP connectors and an expanded set of assistant MCP tools, including evaluation evidence used to judge connector quality before they are offered to agents. This makes Paperclip primarily an MCP client and host: a platform that discovers, qualifies and consumes third-party MCP servers on behalf of the agents it manages, rather than a server that exposes new MCP tools of its own. It ships both a CLI and a web UI, is written mostly in TypeScript, and targets teams that want to run several autonomous or semi-autonomous agents against real business goals while keeping visibility into cost and governance. A hosted Paperclip Cloud offering has an open waitlist alongside the self-hosted open-source version.

https://github.com/paperclipai/paperclip

agent orchestrationmcp clientmulti-agenttypescriptdashboardautomation

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.

rocketride-org/rocketride-server

Open-source visual AI pipeline builder with a C++ runtime and 100+ nodes for LLM and vector-database workloads, exposing pipelines to coding agents through an MCP server.