ruvnet/ruflo

Project overview

Ruvnet/ruflo adds an execution and coordination layer around Claude Code and OpenAI Codex, providing specialized agents, coordinated swarms, self-learning memory, and zero-trust federation. It targets developers and enterprise teams who need multi-agent collaboration on complex software tasks.

Project type

MCP · AI Agent · RAG

Use cases

Coding & Development · Automation

Deployment

Refer to project documentation

License

MIT

Best for

• Developers, AI engineers, and enterprise teams who interact via CLI and need to coordinate multiple specialized agents with shared memory and federation.

Key capabilities

• Coordinate multiple specialized agents as a team using hierarchical, mesh, and adaptive topologies with consensus.
• Zero-trust federation allowing agents across different machines and organizations to discover, authenticate, and exchange work securely.

Limitations and risks

• The Claude Code plugin path does not register the MCP server, making memory_store, swarm_init, and agent_spawn unavailable to Claude.
• Federated communications across trust boundaries carry inherent security and privacy risks despite the zero-trust architecture.

Getting started

• Run `npx ruflo@latest init wizard` to use the interactive setup wizard and one-line npx install command for an easy initialization process.

Evidence and sources

• GitHub project description: The leading agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learni…
• README: Ruflo is the harness — the execution layer around Claude Code and Codex that adds 100+ specialized agents, coordinated swarms, self-learning memory, federated comms across machine…
• README: [](https://www.npmjs.com/package/ruflo)
• Release: v3.30.2 — doctor memory functional checks (#2677 checks 1-3)
• README: 🐝 **Swarm Coordination** | Hierarchical, mesh, and adaptive topologies with consensus

Reviewed at: 2026-07-17T06:10:39Z