# ruvnet/ruflo

🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

Repository: https://github.com/ruvnet/ruflo
Canonical: https://ross.abutalabs.com/products/ruflo
Homepage: https://Cognitum.One
Language: TypeScript
License: MIT
License Family: permissive
Topics: claude-code, swarm, agentic-ai, agentic-framework, agentic-workflow, autonomous-agents, codex, mcp-server, multi-agent, ai-assistant, multi-agent-systems, swarm-intelligence, agents, ai-skills, skills, npm, typescript, ai-agents, harness, dsh-plugin
Last push: 2026-08-26T06:56:09+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 32
- inputs: {"age_days": 457, "days_push": 7, "days_rel": 9, "gap_med": 0.0, "n_releases_24m": 171}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 69486, forks 8306 (observed 2026-08-28T04:12:20.929943+00:00)

## What it is
Ruflo is an open-source agent meta-harness for deploying multi-agent swarms and coordinating autonomous AI workflows, with adaptive memory, self-learning, and RAG integration. It integrates natively with Claude Code, Codex, Hermes, and other coding agents via MCP and plugin systems.

## Use cases
- orchestrate multiple AI agents on a task
- build a multi-agent swarm for coding workflows
- add RAG memory to my AI agents
- connect Claude Code to an MCP server
- automate autonomous agent workflows
- build a conversational AI assistant with agent coordination

## When to choose
- you want to coordinate many LLM agents as a swarm
- you use Claude Code, Codex, or Hermes and want agent orchestration
- you need adaptive memory and RAG built into an agent framework
- you want an npm/TypeScript-based agentic harness

## When to avoid
- you need a simple single-agent chatbot with no orchestration
- you require a Python-first agent stack
- you want a fully managed commercial platform rather than a self-run harness
- your project is unrelated to LLM agents

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, rag, mcp, chatbot, workflow-automation, cli
- domain: large-language-models, developer-tools
- platform: cli, cross-platform
- tags: multi-agent, swarm-intelligence, claude-code, codex, agentic-workflow, mcp-server, self-learning, adaptive-memory, ai-agents, retrieval-augmented-generation, automation, nodejs, typescript

## Member repositories
- ruvnet/ruflo (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:20.929943+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:16:23.222376+00:00, confidence not recorded.
  - readme: https://github.com/ruvnet/ruflo (fetched 2026-08-28T04:12:20.929943+00:00, sha 6a7f08bef92c)
  - homepage: https://Cognitum.One (fetched 2026-08-28T17:51:17.332506+00:00, sha 3efbfcfb7296)
- Data as of 2026-08-30T08:39:29.467469+00:00.