Ruflo
RAPR CLI connectorAgent WorkflowsAdvanced multi-agent orchestration for swarms, shared memory, MCP workflows, and delegated AI automation.
Ruflo package details
RAPR CLI connector scope
This is RAPR-authored connector guidance for a command-line tool the user installs locally. The upstream CLI remains governed by its own license and terms. This package contains RAPR-authored CLI usage guidance, install commands, and agent instructions. It does not bundle the upstream CLI binary. Users can also go directly to the public upstream source linked on this page.
How to get started
Install RAPR AI
Download and install RAPR AI on your computer
Find in Marketplace
Open RAPR AI, go to Packages, and browse the marketplace
Install from Marketplace
Click Install. RAPR sets up the wrapper package, connector guidance, or skill instructions for this listing.
Ruflo
Coordinate advanced multi-agent workflows with Ruflo, an open-source orchestration platform for Claude Code, Codex, Cursor, and MCP-compatible environments. Ruflo is best for users who need delegated specialists, shared memory, swarms, and autonomous workflow coordination.
What you can do
- Spawn swarms: Coordinate planner, coder, reviewer, tester, security, and DevOps agents.
- Delegate work: Break complex tasks into specialist roles with explicit boundaries.
- Use MCP workflows: Connect Ruflo to MCP-compatible clients and tools.
- Share memory: Experiment with persistent context across agent runs.
- Automate pipelines: Build multi-step workflows with routing, retries, review, and stop conditions.
Prerequisites
npm install -g ruflo
ruflo init
Verify the CLI before running swarms:
ruflo --help
ruflo status
Example Requests
- "Initialize Ruflo for this repo and show me the MCP setup."
- "Spawn a small swarm to review the auth module."
- "Design a Ruflo workflow for planning, coding, review, and tests."
- "Audit whether Ruflo is adding too much token overhead."
- "Set safe boundaries for a multi-agent coding workflow."
Ruflo can increase context and token usage. Start with small bounded swarms, confirm persistent memory before enabling it, and review generated commands before execution.