← 返回 Skills 市场

Ruflo

Name: Ruflo
Author: harryhihi

作者 Harryhihi · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ⚠ suspicious

总下载

当前安装

版本数

在 OpenClaw 中安装

/install ruflo

功能描述

Multi-agent AI harness for orchestrating 100+ agents across machines, with self-learning memory, federated comms & enterprise security

使用说明 (SKILL.md)

Ruflo — Multi-Agent AI Harness (OpenClaw)

Orchestrate 100+ specialized AI agents across machines, teams, and trust boundaries. Ruflo adds coordinated swarms, self-learning memory, federated communications, and enterprise security for multi-agent collaboration.

Source: C:\Users\Harry\Downloads\ruflo\ Original: https://github.com/ruvnet/ruflo License: MIT

本技能基於 GitHub 上的 ruvnet/ruflo 修改與封裝。

Overview

Ruflo is a multi-agent AI harness that supports:

Coordinated swarms — orchestrate agents across machines and trust boundaries
Self-learning memory — agents persist and improve knowledge over time
Federated communications — agents communicate across team and org boundaries
Enterprise security — RBAC, audit logging, encryption for production deployments

Structure

ruflo/
├── ruflo/              # Core library
├── scripts/            # Utility scripts
├── plugins/            # Agent plugins
├── docs/               # Documentation
├── tests/              # Test suite
├── bin/                # CLI binaries
├── data/               # Agent data / memory stores
├── verification/       # Verification tools
└── v3/                 # Version 3 components

Usage in OpenClaw

When the user asks about multi-agent coordination, swarm orchestration, or agent memory:

Reference the Ruflo core for agent orchestration patterns
Use scripts from scripts/ for common operations
Consult docs/ for architecture and deployment guidance

安全使用建议

Install only if you are comfortable with a skill that may retain context and coordinate across agents or systems. Before use, require explicit confirmation for memory, federation, scripts, plugins, or sharing with other agents, and avoid sensitive prompts unless retention and data-boundary controls are documented.

能力评估

ℹ Purpose & Capability

The stated purpose, multi-agent coordination with agent memory and federation, is coherent, but those capabilities can affect user data beyond a single local session.

⚠ Instruction Scope

The activation guidance appears broad for a skill with persistent or cross-agent behavior; use should be tied to explicit user intent before enabling orchestration, memory, scripts, plugins, or federation.

ℹ Install Mechanism

No executable install hook or malware signal was supplied, and VirusTotal telemetry is clean; the remaining concern is the runtime authority described by the skill instructions.

⚠ Credentials

Federated communications may cross machine, team, or trust boundaries, but the supplied artifact evidence does not show clear scoping, retention, or sharing limits.

⚠ Persistence & Privilege

Self-learning memory implies retention of user or task context over time, and the artifact evidence does not show an explicit consent, cleanup, or data-minimization model.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install ruflo
安装完成后，直接呼叫该 Skill 的名称或使用 /ruflo 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

Initial OpenClaw skill: Multi-agent AI harness wrapper. Based on ruvnet/ruflo (MIT).

元数据

Slug ruflo

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题

Ruflo 是什么？

Multi-agent AI harness for orchestrating 100+ agents across machines, with self-learning memory, federated comms & enterprise security. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 36 次。

如何安装 Ruflo？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install ruflo」即可一键安装，无需额外配置。

Ruflo 是免费的吗？

是的，Ruflo 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Ruflo 支持哪些平台？

Ruflo 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 Ruflo？

由 Harryhihi（@harryhihi）开发并维护，当前版本 v1.0.0。