Awesome MCP › Agent Orchestration Platforms

ruvnet/ruflo

⭐ 81287 TypeScript added to this list on 2026-11-09 repository created 2025-06-02

Ruflo (formerly Claude Flow) is an agent meta-harness that sits around Claude Code and Codex, giving them tools, memory, coordination loops and guardrails rather than being a model itself. Installing it with `npx ruflo@latest init` adds specialized agents, hooks, persistent memory and an MCP server to a project, and Claude Code picks these up on its next start. The harness organizes agents into swarms that self-organize around a task, learn from outcomes through a local vector-based trajectory memory, and can federate across machines so agents on different hosts coordinate without leaking data between them. Beyond the Claude Code plugin route, Ruflo exposes itself as a standalone MCP server (`npx ruflo@latest mcp start`), so any MCP-capable client, Codex included, can drive its hundreds of tools and dozens of CLI commands without per-project setup. A terminal UI (`npx ruflo tui`) and an optional desktop shell (ruOS) provide visual views of swarms, missions and agent activity, and ruOS itself is reachable over MCP at a hosted endpoint. The project also ships a companion vector-memory tool (RuVector) for persistent, graph-aware agent memory that other agents can query. Ruflo originated as Claude Flow, first committed in June 2025, and documents its lineage and architecture (CLI/MCP to router to swarm to agents to memory to LLM providers) openly in its docs. It targets developers already using Claude Code or Codex who want multi-agent coordination, learned task routing and shared memory without hand-rolling an orchestration layer themselves.

https://github.com/ruvnet/ruflo

agent-orchestrationclaude-codecodexmcp-serverswarmmemorycli

Also in Agent Orchestration Platforms

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.

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.

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.