Ruflo
An agent meta-harness for Claude Code and Codex.
📖 RuFlo Explained — Build an AI Team That Plans, Remembers, Tests, and Improves A 14-chapter guide: from the basic idea to a first useful task, then memory, agent teams, plugins, cost and verification.
Agent = Model + Harness. The model writes; the harness gives it tools, memory, loops, sandboxes, and controls so it can actually work. 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 machines, and enterprise security guardrails. So agents don't just run, they collaborate.
One npx ruflo init gives Claude Code a nervous system: agents self-organize into swarms, learn from every task, remember across sessions, and — with federation — securely talk to agents on other machines without leaking data. You keep writing code. Ruflo handles the coordination.
Self-Learning / Self-Optimizing Agent Architecture
User --> Ruflo (CLI/MCP) --> Router --> Swarm --> Agents --> Memory --> LLM Providers
^ |
+---- Learning Loop <-------+
New to Ruflo? You don't need to learn 314 MCP tools or 26 CLI commands. After
init, just use Claude Code normally — the hooks system automatically routes tasks, learns from successful patterns, and coordinates agents in the background.
📖 Background — where the name comes from
Claude Flow is now Ruflo — named by
rUv, who loves Rust, flow states, and building things that feel inevitable. The "Ru" is the rUv. The "flo" is working until 3am. Underneath, powered byCognitum.Oneagentic architecture, running a supercharged Rust-based AI engine, embeddings, memory, and plugin system.
Quick Start
There are two different install paths with very different surface areas. Pick based on what you need (#1744):
| Claude Code Plugin | CLI install (npx ruflo init) |
|
|---|---|---|
| What it gives you | Slash commands + a few skills + agent definitions per-plugin | Full Ruflo loop — 98 agents, 60+ commands, 30 skills, MCP server, hooks, daemon |
| Files in your workspace | Zero | .claude/, .claude-flow/, CLAUDE.md, helpers, settings |
| MCP server registered | Only if ruflo-core is installed (it ships its own .mcp.json) — most other plugins don't |
Yes |
| Hooks installed | No | Yes |
| Best for | Try a single plugin's commands without committing to the full install | Production use — everything works as documented |
Path A — Claude Code Plugins (lite, slash commands only)
# Add the marketplace
/plugin marketplace add ruvnet/ruflo
# Install core + any plugins you need
/plugin install ruflo-core@ruflo
/plugin install ruflo-swarm@ruflo
/plugin install ruflo-rag-memory@ruflo
/plugin install ruflo-neural-trader@rufloThis adds slash commands and agent definitions. ruflo-core (installed above) does register its own MCP server on install — its tools are callable as mcp__plugin_ruflo-core_ruflo__* (e.g. mcp__plugin_ruflo-core_ruflo__memory_store), not the bare memory_store/swarm_init/agent_spawn names the CLI-track scaffold uses. Other plugins generally don't ship their own MCP server. For the full loop with the CLI-track tool names, use Path B below.
🔌 All 35 plugins
Core & Orchestration
| Plugin | What it does |
|---|---|
| ruflo-core | Foundation — server, health checks, plugin discovery |
| ruflo-swarm | Coordinate multiple agents as a team |
| ruflo-autopilot | Let agents run autonomously in a loop |
| ruflo-loop-workers | Schedule background tasks on a timer |
| ruflo-workflows | Reusable multi-step task templates |
| ruflo-federation | Agents on different machines collaborate securely |
Memory & Knowledge
| Plugin | What it does |
|---|---|
| ruflo-agentdb | Fast vector database for agent memory |
| ruflo-rag-memory | Smart retrieval — hybrid search, graph hops, diversity ranking |
| ruflo-rvf | Save and restore agent memory across sessions |
| ruflo-ruvector | ruvector — GPU-accelerated search, Graph RAG, 103 tools |
| ruflo-knowledge-graph | Build and traverse entity relationship maps |
Intelligence & Learning
| Plugin | What it does |
|---|---|
| ruflo-intelligence | Agents learn from past successes and get smarter |
| ruflo-graph-intelligence | Sublinear graph reasoning — PageRank, delta updates, complexity-aware execution (ADR-123) |
| ruflo-daa | Dynamic agent behavior and cognitive patterns |
| ruflo-ruvllm | Run local LLMs (Ollama, etc.) with smart routing |
| ruflo-goals | Break big goals into plans and track progress |
Code Quality & Testing
| Plugin | What it does |
|---|---|
| ruflo-testgen | Find missing tests and generate them automatically |
| ruflo-browser | Automate browser testing with Playwright |
| ruflo-jujutsu | Analyze git diffs, score risk, suggest reviewers |
| ruflo-docs | Generate and maintain documentation automatically |
Security & Compliance
| Plugin | What it does |
|---|---|
| ruflo-security-audit | Scan for vulnerabilities and CVEs |
| ruflo-aidefence | Block prompt injection, detect PII, safety scanning |
Architecture & Methodology
| Plugin | What it does |
|---|---|
| ruflo-adr | Track architecture decisions with a living record |
| ruflo-ddd | Scaffold domain-driven design — contexts, aggregates, events |
| ruflo-sparc | Guided 5-phase development methodology with quality gates |
| ruflo-metaharness | Grade your agent setup, scan tool configs for security risks, and track changes over time (guide) |
| ruflo-arena | Competitive ruliology — pit agent strategies against each other in tournaments, hill-climb and co-evolve the winners (ADR-147/148) |
DevOps & Observability
| Plugin | What it does |
|---|---|
| ruflo-migrations | Manage database schema changes safely |
| ruflo-observability | Structured logs, traces, and metrics in one place |
| ruflo-cost-tracker | Track token usage, set budgets, get cost alerts |
Extensibility
| Plugin | What it does |
|---|---|
| ruflo-agent | Run agents — local WASM sandbox (rvagent) + Anthropic Claude Managed Agents (cloud) |
| ruflo-plugin-creator | Scaffold, validate, and publish your own plugins |
Domain-Specific
| Plugin | What it does |
|---|---|
| ruflo-iot-cognitum | IoT device management — trust scoring, anomaly detection, fleets |
| ruflo-neural-trader | neural-trader — AI trading with 4 agents, backtesting, 112+ tools |
| ruflo-market-data | Ingest market data, vectorize OHLCV, detect patterns |
CLI Install
macOS / Linux / WSL / Git-Bash:
# One-line install (POSIX shells only — see Windows note below)
curl -fsSL https://cdn.jsdelivr.net/gh/ruvnet/ruflo@main/scripts/install.sh | bashAll platforms (including native Windows PowerShell / cmd):
# Interactive setup wizard — runs identically on every platform
npx ruflo@latest init wizard
# Quick non-interactive init
# npx ruflo@latest init
# Or install globally
npm install -g ruflo@latest💡 Windows users: the
curl ... | bashform needs a POSIX shell (Git-Bash, WSL, MSYS). Thenpx ruflo@latest init wizardline works natively in PowerShell and cmd. If you hit an'bash' is not recognizederror, use thenpxline instead — both end up running the same init flow.
MCP Server
# Add Ruflo as an MCP server in Claude Code
claude mcp add claude-flow -- npx ruflo@latest mcp startWhat You Get
| Capability | Description |
|---|---|
| 🤖 100+ Agents | Specialized agents for coding, testing, security, docs, architecture |
| 📡 Comms Layer | Zero-trust federation — agents across machines/orgs discover, authenticate, and exchange work securely |
| 🐝 Swarm Coordination | Hierarchical, mesh, and adaptive topologies with consensus |
| 🧠 Self-Learning | SONA neural patterns, ReasoningBank, trajectory learning |
| 💾 Vector Memory | HNSW-indexed AgentDB — measured ~1.9x faster at N=20k, ~3.2x–4.7x at N=5k vs brute force (recall@10 ~0.99); ANN wins above the crossover, ties/loses at small N. See audit + scripts/benchmark-intelligence.mjs |
| ⚡ Background Workers | 12 auto-triggered workers (audit, optimize, testgaps, etc.) |
| 🧩 Plugin Marketplace | 33 native Claude Code plugins + 21 npm plugins |
| 🔌 Multi-Provider | Claude, GPT, Gemini, Cohere, Ollama with smart routing |
| 🛡️ Security | AIDefence, input validation, CVE remediation, path traversal prevention |
| 🌐 Agent Federation | Cross-installation agent collaboration with zero-trust security |
| 🔬 MetaHarness | Audit your AI agent setup before you ship. Grade readiness (1-100), scan tool configs for security issues, snapshot the whole project to catch regressions over time, and find templates that match your repo. ruflo eject turns a ruflo project into a standalone agent toolkit with its own name. Full guide. |
| 💬 Web UI Beta | Multi-model chat at flo.ruv.io with parallel MCP tool calling and an in-browser WASM tool gallery |
| 🎯 RuFlo Research | GOAP A* planner at goal.ruv.io — plain-English goals → executable agent plans, with a live agent dashboard at /agents |
Web UI (Beta) — self-hostable, hosted demo at flo.ruv.io
RuFlo's web UI is a multi-model AI chat with built-in Model Context Protocol (MCP) tool calling. Talk to Qwen, Claude, Gemini, or OpenAI while RuFlo invokes the same MCP tools the CLI uses — agent orchestration, persistent memory, swarm coordination, code review, GitHub ops — directly from chat. No install, no API key needed to try it.
| What it is | Why it matters | |
|---|---|---|
| 🧠 | Any model, local or remote | 6 curated frontier models out-of-the-box — Qwen 3.6 Max (default), Claude Sonnet 4.6, Claude Haiku 4.5, Gemini 2.5 Pro, Gemini 2.5 Flash, OpenAI — via OpenRouter. Add your own: any OpenAI-compatible endpoint (vLLM, Ollama, LM Studio, Together, Groq, self-hosted). |
| 🦾 | ruvLLM self-learning AI | Native support for ruvLLM (lives in ruvnet/RuVector/examples/ruvLLM) — RuFlo's self-improving local model layer. Routes to MicroLoRA adapters, learns from your trajectories via SONA, and stays on your machine. Pair with the cloud models or run fully offline. |
| 🛠️ | ~210 tools, ready to call | 5 server groups (Core, Intelligence, Agents, Memory, DevTools) plus an 18-tool gallery that runs entirely in your browser — works offline. |
| 🔌 | Bring your own MCP servers | Click the MCP (n) pill in the chat input → Add Server and paste any MCP endpoint (HTTP, SSE, or stdio). Your tools join RuFlo's native ones in the same parallel-execution flow. Run a local MCP server on localhost:3000 and it just works. |
| ⚡ | Tools run in parallel | One model response can fire 4–6+ tools at the same time. The UI shows them as cards with a Step 1 — 2 tools completed badge so you can see exactly what ran. |
| 💾 | Memory that sticks | Say "remember my favorite color is indigo" and ask weeks later — RuFlo recalls it. Backed by AgentDB + HNSW vector search (measured ~1.9x–4.7x faster than brute force above the crossover, recall@10 ~0.99). |
| 📘 | Built-in capabilities tour | Click the question-mark icon in the sidebar — a "RuFlo Capabilities" modal opens with the full tool list, model strengths, architecture, and keyboard shortcuts. |
| 🏠 | Self-hostable | Web UI is shipped as Docker (ruflo/src/ruvocal/Dockerfile) with embedded Mongo. Deploy to your own Cloud Run / Fly / Kubernetes / docker-compose. The hosted flo.ruv.io demo is one option; running your own is fully supported. |
| 🚀 | Zero install to try | Open the hosted URL, pick a model, type a question. That's the whole onboarding. |
Try the hosted demo: https://flo.ruv.io/ — no account, no API key. Run your own: the source lives in ruflo/src/ruvocal/ with a multi-stage Dockerfile (INCLUDE_DB=true builds in MongoDB) and a cloudbuild.yaml for Google Cloud Run. See ADR-033 for the architecture and issue #1689 for the roadmap.
Goal Planner UI — autonomous agents at goal.ruv.io
Turn high-level goals into executable agent plans. goal.ruv.io is RuFlo's hosted Goal-Oriented Action Planning (GOAP) front-end — describe an outcome in plain English and watch RuFlo decompose it into preconditions, actions, and an A* path through state space, then dispatch the work to live agents at /agents.
| What it is | Why it matters | |
|---|---|---|
| 🎯 | Plain-English goals | Type "ship the auth refactor with tests and a PR" — RuFlo extracts the success criteria, the constraints, and the implicit preconditions. No JSON, no DSL. |
| 🧭 | GOAP A* planner | Classic gaming-AI planning ported to software work: state-space search through actions with preconditions/effects to find the shortest viable path. Replans on the fly when state changes. |
| 🤖 | Live agent dashboard | goal.ruv.io/agents shows every spawned agent — role, current step, memory namespace, token budget, status. Click in to inspect trajectories, kill runaway workers, or reassign. |
| 🌳 | Visual plan tree | Goals render as collapsible action trees with progress, blocked branches, and rollbacks highlighted. See exactly why an agent picked a path — no opaque chain-of-thought. |
| ♻️ | Adaptive replanning | When an action fails or new info arrives, the planner re-runs A* from the current state instead of restarting. Failures become learning, not loops. |
| 🧠 | Shared memory + SONA | Plans, trajectories, and outcomes flow into AgentDB. Future plans retrieve past solutions via HNSW — the planner gets smarter with every run. |
| 🔗 | Wired to MCP tools | Every action node maps to a tool call (RuFlo's ~210 MCP tools, your custom servers, or shell). The planner schedules them in parallel where the dependency graph allows. |
| 🚀 | Zero install to try | Open goal.ruv.io, describe a goal, watch it run. Source lives in v3/goal_ui/ — Vite + Supabase, self-hostable. |
Try it: https://goal.ruv.io/ for goals · https://goal.ruv.io/agents for live agents. Run your own: clone the goal branch and cd v3/goal_ui && npm install && npm run dev.
Agent Federation — Slack for Agents
Your Agent --> [ Remove secrets ] --> [ Sign message ] --> [ Encrypted channel ]
Emails, SSNs, Proves it came No one reads it
keys stripped from you in transit
|
v
Their Agent <-- [ Block attacks ] <-- [ Check identity ] <------+
Stops prompt Rejects forgeries
injection
Audit trail on both sides.
Trust builds over time. Bad behavior = instant downgrade.
Slack gave teams channels. Federation gives agents the same thing — shared workspaces across trust boundaries, where agents on different machines, orgs, or cloud regions can discover each other, prove who they are, and collaborate on tasks.
The difference: some channels are trusted, some aren't. @claude-flow/plugin-agent-federation handles that automatically. Your agents join a federation, get verified via mTLS + ed25519, and start exchanging work — with PII stripped before anything leaves your node and every message auditable. Untrusted agents can still participate at lower privilege: they see discovery info, not your memory. As they prove reliable, trust upgrades. If they misbehave, they get downgraded instantly — no human in the loop required.
You don't configure handshakes or manage certificates. You federation init, federation join, and your agents start talking. The protocol handles identity, the PII pipeline handles data safety, and the audit trail handles compliance.
📘 Full user guide:
docs/federation/— setup, MCP tools, trust levels, circuit breaker, and the (opt-in) WireGuard mesh layer that ties packet-layer reachability to federation trust. ADR-111 deep-dive atdocs/federation/phase7-mesh-bringup.md.
Federation capabilities
| Capability | How it works | |
|---|---|---|
| 🔒 | Zero-trust federation | Remote agents start untrusted. Identity proven via mTLS + ed25519 challenge-response. No API keys, no shared secrets. |
| 🛡️ | PII-gated data flow | 14-type detection pipeline scans every outbound message. Per-trust-level policies: BLOCK, REDACT, HASH, or PASS. Adaptive calibration reduces false positives. |
| 📊 | Behavioral trust scoring | Formula (0.4×success + 0.2×uptime + 0.2×threat + 0.2×integrity) continuously evaluates peers. Upgrades require history; downgrades are instant. |
| 📋 | Compliance built-in | HIPAA, SOC2, GDPR audit trails as compliance modes. Every federation event produces a structured record searchable via HNSW. |
| 🤝 | 9 MCP tools + 10 CLI commands | Full lifecycle: federation_init, federation_send, federation_trust, federation_audit, and more. |
Example: two teams sharing fraud signals without sharing customer data
# Team A: initialize federation and generate keypair
npx claude-flow@latest federation init
# Team A: join Team B's federation endpoint
npx claude-flow@latest federation join wss://team-b.example.com:8443
# Team A: send a task — PII is stripped automatically before it leaves
npx claude-flow@latest federation send --to team-b --type task-request \
--message "Analyze transaction patterns for account anomalies"
# Team A: check peer trust levels and session health
npx claude-flow@latest federation statusSee issue #1669 for the complete architecture, trust model, and implementation roadmap.
# Claude Code plugin
/plugin install ruflo-federation@ruflo
# Or via CLI
npx claude-flow@latest plugins install @claude-flow/plugin-agent-federationClaude Code: With vs Without Ruflo
| Capability | Claude Code Alone | + Ruflo |
|---|---|---|
| Agent Collaboration | Isolated, no shared context | Swarms with shared memory and consensus |
| Coordination | Manual orchestration | Queen-led hierarchy (Raft, Byzantine, Gossip) |
| Memory | Session-only | HNSW vector memory with sub-ms retrieval |
| Learning | Static behavior | SONA self-learning with pattern matching |
| Task Routing | You decide | Intelligent routing (89% accuracy) |
| Background Workers | None | 12 auto-triggered workers |
| LLM Providers | Anthropic only | 5 providers with failover |
| Security | Standard | CVE-hardened with AIDefence |
Architecture overview
User --> Claude Code / CLI
|
v
Orchestration Layer
(MCP Server, Router, 27 Hooks)
|
v
Swarm Coordination
(Queen, Topology, Consensus)
|
v
100+ Specialized Agents
(coder, tester, reviewer, architect, security...)
|
v
Memory & Learning
(AgentDB, HNSW, SONA, ReasoningBank)
|
v
LLM Providers
(Claude, GPT, Gemini, Cohere, Ollama)
Documentation
Four docs for four audiences:
| Doc | When to read it |
|---|---|
| Status | See what currently works — capability counts, test baselines, recent fixes, what's next. The is-it-ready doc. |
| User Guide | Daily reference — every command, every config flag, every plugin. The how-do-I doc. |
| MetaHarness Guide | How to grade your agent setup, scan tool configs for security, detect changes between runs, and eject a project into a standalone agent toolkit. The audit-my-setup doc. |
| Benchmarks | v3.8.0 SOTA matrix vs LangGraph / AutoGen / CrewAI on darwin-arm64 + linux-x64. ruflo wins cold start, single turn, RSS by 1.3×–1953×. The is-it-fast doc. |
| Verification | Cryptographically prove your installed bytes match the signed witness — ruflo verify. The trust-but-verify doc. |
| Team Gateway Checklist | Before-merge gates, dual-mode handoff, memory namespace sharing, and witness manifest entry per merge. The safer-team-workflows doc. |
Benchmark internals (for reproduction): sota-workload-spec.md · SOTA-PROGRESS.md · raw matrix JSON: darwin · linux
User Guide section index:
| Section | Topics |
|---|---|
| Quick Start | Installation, prerequisites, install profiles |
| Core Features | MCP tools, agents, memory, neural learning |
| Intelligence & Learning | Hooks, workers, SONA, model routing |
| Swarm & Coordination | Topologies, consensus, hive mind |
| Security | AIDefence, CVE remediation, validation |
| Ecosystem | RuVector, agentic-flow, Flow Nexus |
| Configuration | Environment variables, config schema |
| Plugin Marketplace | Browse and install plugins |
Support
| Resource | Link |
|---|---|
| Documentation | User Guide |
| Issues & Bugs | GitHub Issues |
| Enterprise | ruv.io |
| Community | Agentics Foundation Discord |
| Powered by | Cognitum.one |
License
MIT - RuvNet
