# ruflo

Open-source agent meta-harness for orchestrating multi-agent swarms with Claude, adaptive memory, and RAG integration.

## Agent Decision Summary
- Risk level: elevated
- Source confidence: high
- Recommended workflows: Coding agent workflow, Connector or protocol layer, Memory or RAG workflow
- Permission surface: shell/files, memory, external services
- Agent JSON: https://www.openagent.bot/agents/ruflo.agent.json

## Summary
ruflo is an open-source meta-harness for orchestrating multi-agent swarms, primarily designed for Claude-based workflows. It features adaptive memory, self-learning swarm intelligence, RAG integration, and native integration with Claude Code and Codex CLI for coordinated autonomous workflows.


## Guide
### What it is
ruflo is an open-source meta-harness for orchestrating multi-agent swarms with Claude. It provides adaptive memory, swarm intelligence, and native Claude Code integration.

### Why it matters
ruflo addresses the growing need for multi-agent orchestration as teams deploy multiple Claude agents. Its swarm intelligence and adaptive memory features go beyond simple agent chaining.


### FAQ
- What is a meta-harness?
  - A meta-harness is an orchestration layer that manages multiple AI agents, coordinating their work, memory, and tool access.
- Does ruflo work with models other than Claude?
  - ruflo is primarily designed for Claude, with native Claude Code and Codex CLI integration.
- Is ruflo open source?
  - Yes, it is open source under the MIT license with 57K+ GitHub stars.
- What is swarm intelligence in ruflo?
  - Swarm intelligence allows multiple agents to learn from each other's outputs and adapt their behavior collectively.
## What It Does
ruflo is an open-source meta-harness for orchestrating multi-agent swarms with Claude. It provides adaptive memory, swarm intelligence, and native Claude Code integration.

## How To Evaluate
Evaluate ruflo by starting from the official sources, checking its repo interface surface, and running one narrow workflow before expanding scope. Recorded integrations include agents.

## Why It Matters
ruflo provides a higher-level orchestration layer for teams running multiple Claude agents in production. With 57K+ GitHub stars and active development, it fills the gap between single-agent tools and full agent platforms — particularly for Claude-specific multi-agent deployments.


## Best For
- Teams running Claude-based multi-agent workflows that need swarm coordination and adaptive memory
- Developers building autonomous agent systems with Claude Code and Codex CLI integration
- Engineers evaluating meta-orchestration layers for managing multiple AI agents

## Not For
- Single-agent use cases where a direct Claude API integration is sufficient
- Teams that prefer a model-agnostic orchestration framework over Claude-specific tooling

## What It Actually Does
- Workflow orchestration: ruflo surfaces workflow orchestration as a core capability in its published project metadata and source links.
  - Why it matters: This gives readers a starting point for evaluating whether the project fits their workflow before visiting the source repository or docs.

## Typical Use Cases
- Developer workflow: Use it as a candidate for developer workflow when the project facts, license, and official links match your deployment requirements.

## How It Compares
- When to choose ruflo: Compare it with nearby agents by looking at hosting model, integration surface, license, and whether the official docs show the workflow you need.

## Fit Matrix
- Coding agent workflow: strong. ruflo has multiple signals for coding agent workflow, including matching tags, capabilities, category, or positioning. Required check: Run a small repository change and inspect the diff, tests, and rollback path.
- Connector or protocol layer: strong. ruflo has multiple signals for connector or protocol layer, including matching tags, capabilities, category, or positioning. Required check: Connect one low-risk service, then inspect schemas, auth scope, errors, and logs.
- Memory or RAG workflow: strong. ruflo has multiple signals for memory or rag workflow, including matching tags, capabilities, category, or positioning. Required check: Create, update, retrieve, correct, and delete memory or retrieval objects with real data.
- Evaluation and observability: partial. ruflo has at least one signal for evaluation and observability, but should be checked against a real task before adoption. Required check: Add one repeatable test case and confirm results can run again in review or CI.
- Reusable skill workflow: partial. ruflo has at least one signal for reusable skill workflow, but should be checked against a real task before adoption. Required check: Run one skill end to end and check whether it produces evidence or structured output.
- Browser automation: weak. ruflo is not primarily positioned for browser automation in the current metadata. Required check: Run one non-sensitive website task and inspect clicks, waits, retries, and changed URLs.

## Evidence
- verified: ruflo is listed as open source. Source: License metadata: MIT
- verified: ruflo has a recorded GitHub repository: ruvnet/ruflo. Source: Resource facts and GitHub source link.
- inferred: ruflo supports these recorded deployment modes: cloud. Source: OpenAgent decision signal metadata.
- inferred: ruflo is tagged with workflow orchestration capabilities. Source: OpenAgent capability taxonomy.

## Missing Checks
- Dedicated docs link is missing.
- Repository freshness has not been recorded.

## Next Actions
- Inspect repository: https://github.com/ruvnet/ruflo
- Open Homepage: https://Cognitum.One

## Facts
- Category: agents
- Resource type: agent
- Open source: yes
- License: MIT
- Last verified: 2026-06-03
- GitHub repo: ruvnet/ruflo
- GitHub stars: 57619

## Capabilities
- workflow-orchestration

## Structured Use Case Tags
- developer-workflow

## Getting Started
- Review the repository: https://github.com/ruvnet/ruflo
- Homepage: https://Cognitum.One

## Links
- GitHub: https://github.com/ruvnet/ruflo
- Homepage: https://Cognitum.One

## Structured Outputs
- JSON: https://www.openagent.bot/agents/ruflo.json
- Markdown: https://www.openagent.bot/agents/ruflo.md
- Agent JSON: https://www.openagent.bot/agents/ruflo.agent.json
- Canonical: https://www.openagent.bot/agents/ruflo