[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-2":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":9,"totalLinesOfCode":9,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":9,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":9,"rankLanguage":9,"license":9,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":22,"hasPages":22,"topics":24,"createdAt":9,"pushedAt":9,"updatedAt":45,"readmeContent":46,"aiSummary":47,"trendingCount":16,"starSnapshotCount":16,"syncStatus":4,"lastSyncTime":48,"discoverSource":49},2,"ruflo","ruvnet\u002Fruflo","ruvnet","🌊 The leading agent meta-harness for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning swarm intelligence, RAG integration, and native Claude Code \u002F Codex Integration",null,"https:\u002F\u002Fgithub.com\u002Fruvnet\u002Fruflo","TypeScript",58966,6776,398,441,0,135,1122,9808,735,45,false,"main",[25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44],"claude-code","swarm","agentic-ai","agentic-engineering","agentic-framework","agentic-rag","agentic-workflow","anthropic-claude","autonomous-agents","codex","mcp-server","model-context-protocol","multi-agent","ai-assistant","ai-tools","huggingface","multi-agent-systems","swarm-intelligence","agents","claude-code-skills","2026-06-12 02:00:06","\u003Cdiv align=\"center\">\n\n[![Ruflo Banner](ruflo\u002Fassets\u002Fruflo-small.jpeg)](https:\u002F\u002Fflo.ruv.io\u002F)\n\n[![Try the UI Beta — flo.ruv.io](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F_Try_the_UI_Beta-flo.ruv.io-6366f1?style=for-the-badge&logoColor=white&logo=svelte)](https:\u002F\u002Fflo.ruv.io\u002F)\n[![Goal Planner — goal.ruv.io](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F_Goal_Planner-goal.ruv.io-8b5cf6?style=for-the-badge&logoColor=white&logo=react)](https:\u002F\u002Fgoal.ruv.io\u002F)\n[![Live Agents — goal.ruv.io\u002Fagents](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F_Live_Agents-goal.ruv.io%2Fagents-10b981?style=for-the-badge&logoColor=white&logo=react)](https:\u002F\u002Fgoal.ruv.io\u002Fagents)\n\n[![Star on GitHub](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fruvnet\u002Fclaude-flow?style=for-the-badge&logo=github&color=gold)](https:\u002F\u002Fgithub.com\u002Fruvnet\u002Fclaude-flow)\n[![MIT License](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-yellow?style=for-the-badge)](https:\u002F\u002Fopensource.org\u002Flicenses\u002FMIT)\n[![Claude Code](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FClaude%20Code-Plugin-D97757?style=for-the-badge&logoColor=white&logo=anthropic)](https:\u002F\u002Fgithub.com\u002Fruvnet\u002Fclaude-flow)\n[![Codex Plugin](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FCodex-Plugin-412991?style=for-the-badge&logoColor=white&logo=data%3Aimage%2Fsvg%2Bxml%3Bbase64%2CPHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9IjAgMCAyNCAyNCI%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%2BPC9zdmc%2B)](https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002F@claude-flow\u002Fcodex)\n[![🕸️ RuVector Graph Ai](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FRuVector_Agentic-DB-06b6d4?style=for-the-badge&logoColor=white&logo=graphql)](https:\u002F\u002Fgithub.com\u002Fruvnet\u002Fruvector)\n\n# Ruflo\n\n**Multi-agent AI orchestration for Claude Code**\n\n\u003C\u002Fdiv>\n\nOrchestrate 100+ specialized AI agents across machines, teams, and trust boundaries. Ruflo adds coordinated swarms, self-learning memory, federated comms, and enterprise security to Claude Code — so agents don't just run, they collaborate.\n\n### Why Ruflo?\n\n> Claude Flow is now Ruflo — named by [`rUv`](https:\u002F\u002Fruv.io), who loves Rust, flow states, and building things that feel inevitable. The \"Ru\" is the rUv. The \"flo\" is working until 3am. Underneath, powered by [`Cognitum.One`](https:\u002F\u002Fcognitum.one\u002F?RuFlo) agentic architecture, running a supercharged Rust based AI engine, embeddings, memory, and plugin system.\n\n\n### What Ruflo Does\n\nOne `npx ruvflo 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.\n\n```\nSelf-Learning \u002F Self-Optimizing Agent Architecture\n\nUser --> Ruflo (CLI\u002FMCP) --> Router --> Swarm --> Agents --> Memory --> LLM Providers\n                          ^                           |\n                          +---- Learning Loop \u003C-------+\n```\n\n> **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.\n\n---\n\n![Ruflo Plugins](.\u002Fruflo-plugins.gif)\n\n## Quick Start\n\nThere are **two different install paths** with very different surface areas. Pick based on what you need (#1744):\n\n| | **Claude Code Plugin** | **CLI install (`npx ruflo init`)** |\n|---|---|---|\n| 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 |\n| Files in your workspace | **Zero** | `.claude\u002F`, `.claude-flow\u002F`, `CLAUDE.md`, helpers, settings |\n| MCP server registered | **No** (`memory_store`, `swarm_init`, etc. unavailable to Claude) | Yes |\n| Hooks installed | No | Yes |\n| Best for | Try a single plugin's commands without committing to the full install | Production use — everything works as documented |\n\n### Path A — Claude Code Plugins (lite, slash commands only)\n\n```bash\n# Add the marketplace\n\u002Fplugin marketplace add ruvnet\u002Fruflo\n\n# Install core + any plugins you need\n\u002Fplugin install ruflo-core@ruflo\n\u002Fplugin install ruflo-swarm@ruflo\n\u002Fplugin install ruflo-autopilot@ruflo\n\u002Fplugin install ruflo-federation@ruflo\n```\n\nThis adds slash commands and agent definitions only. The Ruflo MCP server is NOT registered, so `memory_store`, `swarm_init`, `agent_spawn`, etc. won't be callable from Claude. For the full loop, use Path B below.\n\n\u003Cdetails>\n\u003Csummary>\u003Cstrong>🔌 All 32 plugins\u003C\u002Fstrong>\u003C\u002Fsummary>\n\n#### Core & Orchestration\n\n| Plugin | What it does |\n|--------|-------------|\n| **ruflo-core** | Foundation — server, health checks, plugin discovery |\n| **ruflo-swarm** | Coordinate multiple agents as a team |\n| **ruflo-autopilot** | Let agents run autonomously in a loop |\n| **ruflo-loop-workers** | Schedule background tasks on a timer |\n| **ruflo-workflows** | Reusable multi-step task templates |\n| **ruflo-federation** | Agents on different machines collaborate securely |\n\n#### Memory & Knowledge\n\n| Plugin | What it does |\n|--------|-------------|\n| **ruflo-agentdb** | Fast vector database for agent memory |\n| **ruflo-rag-memory** | Smart retrieval — hybrid search, graph hops, diversity ranking |\n| **ruflo-rvf** | Save and restore agent memory across sessions |\n| **ruflo-ruvector** | [`ruvector`](https:\u002F\u002Fnpmjs.com\u002Fpackage\u002Fruvector) — GPU-accelerated search, Graph RAG, 103 tools |\n| **ruflo-knowledge-graph** | Build and traverse entity relationship maps |\n\n#### Intelligence & Learning\n\n| Plugin | What it does |\n|--------|-------------|\n| **ruflo-intelligence** | Agents learn from past successes and get smarter |\n| **ruflo-daa** | Dynamic agent behavior and cognitive patterns |\n| **ruflo-ruvllm** | Run local LLMs (Ollama, etc.) with smart routing |\n| **ruflo-goals** | Break big goals into plans and track progress |\n\n#### Code Quality & Testing\n\n| Plugin | What it does |\n|--------|-------------|\n| **ruflo-testgen** | Find missing tests and generate them automatically |\n| **ruflo-browser** | Automate browser testing with Playwright |\n| **ruflo-jujutsu** | Analyze git diffs, score risk, suggest reviewers |\n| **ruflo-docs** | Generate and maintain documentation automatically |\n\n#### Security & Compliance\n\n| Plugin | What it does |\n|--------|-------------|\n| **ruflo-security-audit** | Scan for vulnerabilities and CVEs |\n| **ruflo-aidefence** | Block prompt injection, detect PII, safety scanning |\n\n#### Architecture & Methodology\n\n| Plugin | What it does |\n|--------|-------------|\n| **ruflo-adr** | Track architecture decisions with a living record |\n| **ruflo-ddd** | Scaffold domain-driven design — contexts, aggregates, events |\n| **ruflo-sparc** | Guided 5-phase development methodology with quality gates |\n\n#### DevOps & Observability\n\n| Plugin | What it does |\n|--------|-------------|\n| **ruflo-migrations** | Manage database schema changes safely |\n| **ruflo-observability** | Structured logs, traces, and metrics in one place |\n| **ruflo-cost-tracker** | Track token usage, set budgets, get cost alerts |\n\n#### Extensibility\n\n| Plugin | What it does |\n|--------|-------------|\n| **ruflo-wasm** | Run sandboxed WebAssembly agents |\n| **ruflo-plugin-creator** | Scaffold, validate, and publish your own plugins |\n\n#### Domain-Specific\n\n| Plugin | What it does |\n|--------|-------------|\n| **ruflo-iot-cognitum** | IoT device management — trust scoring, anomaly detection, fleets |\n| **ruflo-neural-trader** | [`neural-trader`](https:\u002F\u002Fnpmjs.com\u002Fpackage\u002Fneural-trader) — AI trading with 4 agents, backtesting, 112+ tools |\n| **ruflo-market-data** | Ingest market data, vectorize OHLCV, detect patterns |\n\n\u003C\u002Fdetails>\n\n### CLI Install\n\n```bash\n# One-line install\ncurl -fsSL https:\u002F\u002Fcdn.jsdelivr.net\u002Fgh\u002Fruvnet\u002Fruflo@main\u002Fscripts\u002Finstall.sh | bash\n\n# Or via npx (interactive setup)\nnpx ruflo@latest init wizard\n\n# Quick non-interactive init\n# npx ruflo@latest init\n\n# Or install globally\nnpm install -g ruflo@latest\n```\n\n### MCP Server\n\n```bash\n# Add Ruflo as an MCP server in Claude Code (canonical form, matches USERGUIDE.md)\nclaude mcp add ruflo -- npx ruflo@latest mcp start\n```\n\n---\n\n## What You Get\n\n| Capability | Description |\n|------------|-------------|\n| 🤖 **100+ Agents** | Specialized agents for coding, testing, security, docs, architecture |\n| 📡 **Comms Layer** | Zero-trust federation — agents across machines\u002Forgs discover, authenticate, and exchange work securely |\n| 🐝 **Swarm Coordination** | Hierarchical, mesh, and adaptive topologies with consensus |\n| 🧠 **Self-Learning** | SONA neural patterns, ReasoningBank, trajectory learning |\n| 💾 **Vector Memory** | HNSW-indexed AgentDB with 150x-12,500x faster search |\n| ⚡ **Background Workers** | 12 auto-triggered workers (audit, optimize, testgaps, etc.) |\n| 🧩 **Plugin Marketplace** | 32 native Claude Code plugins + 21 npm plugins |\n| 🔌 **Multi-Provider** | Claude, GPT, Gemini, Cohere, Ollama with smart routing |\n| 🛡️ **Security** | AIDefence, input validation, CVE remediation, path traversal prevention |\n| 🌐 **Agent Federation** | Cross-installation agent collaboration with zero-trust security |\n| 💬 **[Web UI Beta](https:\u002F\u002Fflo.ruv.io\u002F)** | Multi-model chat at flo.ruv.io with parallel MCP tool calling and an in-browser WASM tool gallery |\n| 🎯 **[RuFlo Research](https:\u002F\u002Fgoal.ruv.io\u002F)** | GOAP A\\* planner at goal.ruv.io — plain-English goals → executable agent plans, with a live agent dashboard at [\u002Fagents](https:\u002F\u002Fgoal.ruv.io\u002Fagents) |\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fflo.ruv.io\u002F\">\n    \u003Cimg src=\"v3\u002Fdocs\u002Fassets\u002FruVocal.png\" alt=\"RuFlo Web UI executing parallel MCP tool calls at flo.ruv.io — ruflo__memory_store and ruflo__memory_search firing in a single model turn with the 'Step 1 — 2 tools completed' parallel-execution indicator, thinking process panel visible, Qwen 3.6 Max as the active model. Multi-agent AI chat with Model Context Protocol (MCP) tool calling, persistent vector memory via AgentDB + HNSW, swarm coordination, and 6 frontier models including Claude Sonnet 4.6, Gemini 2.5 Pro, and OpenAI through OpenRouter.\" width=\"100%\" \u002F>\n  \u003C\u002Fa>\n\u003C\u002Fp>\n\n### Web UI (Beta) — self-hostable, hosted demo at [flo.ruv.io](https:\u002F\u002Fflo.ruv.io\u002F)\n\n**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.\n\n| | What it is | Why it matters |\n|---|------------|----------------|\n| 🧠 | **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). |\n| 🦾 | **ruvLLM self-learning AI** | Native support for [ruvLLM](https:\u002F\u002Fgithub.com\u002Fruvnet\u002FRuVector\u002Ftree\u002Fmain\u002Fexamples\u002FruvLLM) (lives in `ruvnet\u002FRuVector\u002Fexamples\u002FruvLLM`) — 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. |\n| 🛠️ | **~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. |\n| 🔌 | **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. |\n| ⚡ | **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. |\n| 💾 | **Memory that sticks** | Say *\"remember my favorite color is indigo\"* and ask weeks later — RuFlo recalls it. Backed by AgentDB + HNSW vector search (≥150× faster than brute force). |\n| 📘 | **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. |\n| 🏠 | **Self-hostable** | Web UI is shipped as Docker (`ruflo\u002Fsrc\u002Fruvocal\u002FDockerfile`) with embedded Mongo. Deploy to your own Cloud Run \u002F Fly \u002F Kubernetes \u002F docker-compose. The hosted [flo.ruv.io](https:\u002F\u002Fflo.ruv.io\u002F) demo is one option; running your own is fully supported. |\n| 🚀 | **Zero install to try** | Open the hosted URL, pick a model, type a question. That's the whole onboarding. |\n\n**Try the hosted demo:** [https:\u002F\u002Fflo.ruv.io\u002F](https:\u002F\u002Fflo.ruv.io\u002F) — no account, no API key. **Run your own:** the source lives in [`ruflo\u002Fsrc\u002Fruvocal\u002F`](ruflo\u002Fsrc\u002Fruvocal\u002F) with a multi-stage Dockerfile (`INCLUDE_DB=true` builds in MongoDB) and a `cloudbuild.yaml` for Google Cloud Run. See [ADR-033](ruflo\u002Fdocs\u002Fadr\u002FADR-033-RUVOCAL-WASM-MCP-INTEGRATION.md) for the architecture and [issue #1689](https:\u002F\u002Fgithub.com\u002Fruvnet\u002Fruflo\u002Fissues\u002F1689) for the roadmap.\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgoal.ruv.io\u002Fagents\">\n    \u003Cimg src=\"v3\u002Fdocs\u002Fassets\u002Fgoal.png\" alt=\"goal.ruv.io\u002Fagents — RuFlo Goal-Oriented Action Planning (GOAP) UI for autonomous AI agents. Visual goal decomposition, A* search through state spaces, multi-agent task assignment, and live agent telemetry.\" width=\"100%\" \u002F>\n  \u003C\u002Fa>\n\u003C\u002Fp>\n\n### Goal Planner UI — autonomous agents at [goal.ruv.io](https:\u002F\u002Fgoal.ruv.io\u002F)\n\n**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 [`\u002Fagents`](https:\u002F\u002Fgoal.ruv.io\u002Fagents).\n\n| | What it is | Why it matters |\n|---|------------|----------------|\n| 🎯 | **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. |\n| 🧭 | **GOAP A\\* planner** | Classic gaming-AI planning ported to software work: state-space search through actions with preconditions\u002Feffects to find the shortest viable path. Replans on the fly when state changes. |\n| 🤖 | **Live agent dashboard** | [goal.ruv.io\u002Fagents](https:\u002F\u002Fgoal.ruv.io\u002Fagents) shows every spawned agent — role, current step, memory namespace, token budget, status. Click in to inspect trajectories, kill runaway workers, or reassign. |\n| 🌳 | **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. |\n| ♻️ | **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. |\n| 🧠 | **Shared memory + SONA** | Plans, trajectories, and outcomes flow into AgentDB. Future plans retrieve past solutions via HNSW — the planner gets smarter with every run. |\n| 🔗 | **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. |\n| 🚀 | **Zero install to try** | Open [goal.ruv.io](https:\u002F\u002Fgoal.ruv.io\u002F), describe a goal, watch it run. Source lives in [`v3\u002Fgoal_ui\u002F`](v3\u002Fgoal_ui\u002F) — Vite + Supabase, self-hostable. |\n\n**Try it:** [https:\u002F\u002Fgoal.ruv.io\u002F](https:\u002F\u002Fgoal.ruv.io\u002F) for goals · [https:\u002F\u002Fgoal.ruv.io\u002Fagents](https:\u002F\u002Fgoal.ruv.io\u002Fagents) for live agents. **Run your own:** clone the `goal` branch and `cd v3\u002Fgoal_ui && npm install && npm run dev`.\n\n### Agent Federation — Slack for Agents\n\n```\nYour Agent --> [ Remove secrets ] --> [ Sign message ] --> [ Encrypted channel ]\n                 Emails, SSNs,        Proves it came       No one reads it\n                 keys stripped         from you              in transit\n                                                                |\n                                                                v\nTheir Agent \u003C-- [ Block attacks ] \u003C-- [ Check identity ] \u003C------+\n                 Stops prompt          Rejects forgeries\n                 injection\n\n                          Audit trail on both sides.\n                  Trust builds over time. Bad behavior = instant downgrade.\n```\n\nSlack 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.\n\nThe difference: some channels are trusted, some aren't. [`@claude-flow\u002Fplugin-agent-federation`](https:\u002F\u002Fgithub.com\u002Fruvnet\u002Fruflo\u002Fissues\u002F1669) 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.\n\nYou 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.\n\n\u003Cdetails>\n\u003Csummary>\u003Cstrong>Federation capabilities\u003C\u002Fstrong>\u003C\u002Fsummary>\n\n| | Capability | How it works |\n|---|---|---|\n| 🔒 | **Zero-trust federation** | Remote agents start untrusted. Identity proven via mTLS + ed25519 challenge-response. No API keys, no shared secrets. |\n| 🛡️ | **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. |\n| 📊 | **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. |\n| 📋 | **Compliance built-in** | HIPAA, SOC2, GDPR audit trails as compliance modes. Every federation event produces a structured record searchable via HNSW. |\n| 🤝 | **9 MCP tools + 10 CLI commands** | Full lifecycle: `federation_init`, `federation_send`, `federation_trust`, `federation_audit`, and more. |\n\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cstrong>Example: two teams sharing fraud signals without sharing customer data\u003C\u002Fstrong>\u003C\u002Fsummary>\n\n```bash\n# Team A: initialize federation and generate keypair\nnpx claude-flow@latest federation init\n\n# Team A: join Team B's federation endpoint\nnpx claude-flow@latest federation join wss:\u002F\u002Fteam-b.example.com:8443\n\n# Team A: send a task — PII is stripped automatically before it leaves\nnpx claude-flow@latest federation send --to team-b --type task-request \\\n  --message \"Analyze transaction patterns for account anomalies\"\n\n# Team A: check peer trust levels and session health\nnpx claude-flow@latest federation status\n```\n\n\u003C\u002Fdetails>\n\nSee [issue #1669](https:\u002F\u002Fgithub.com\u002Fruvnet\u002Fruflo\u002Fissues\u002F1669) for the complete architecture, trust model, and implementation roadmap.\n\n```bash\n# Claude Code plugin\n\u002Fplugin install ruflo-federation@ruflo\n\n# Or via CLI\nnpx claude-flow@latest plugins install @claude-flow\u002Fplugin-agent-federation\n```\n\n\u003Cdetails>\n\u003Csummary>\u003Cstrong>Claude Code: With vs Without Ruflo\u003C\u002Fstrong>\u003C\u002Fsummary>\n\n| Capability | Claude Code Alone | + Ruflo |\n|------------|-------------------|---------|\n| Agent Collaboration | Isolated, no shared context | Swarms with shared memory and consensus |\n| Coordination | Manual orchestration | Queen-led hierarchy (Raft, Byzantine, Gossip) |\n| Memory | Session-only | HNSW vector memory with sub-ms retrieval |\n| Learning | Static behavior | SONA self-learning with pattern matching |\n| Task Routing | You decide | Intelligent routing (89% accuracy) |\n| Background Workers | None | 12 auto-triggered workers |\n| LLM Providers | Anthropic only | 5 providers with failover |\n| Security | Standard | CVE-hardened with AIDefence |\n\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cstrong>Architecture overview\u003C\u002Fstrong>\u003C\u002Fsummary>\n\n```\nUser --> Claude Code \u002F CLI\n          |\n          v\n    Orchestration Layer\n    (MCP Server, Router, 27 Hooks)\n          |\n          v\n    Swarm Coordination\n    (Queen, Topology, Consensus)\n          |\n          v\n    100+ Specialized Agents\n    (coder, tester, reviewer, architect, security...)\n          |\n          v\n    Memory & Learning\n    (AgentDB, HNSW, SONA, ReasoningBank)\n          |\n          v\n    LLM Providers\n    (Claude, GPT, Gemini, Cohere, Ollama)\n```\n\n\u003C\u002Fdetails>\n\n---\n\n## Documentation\n\nThree docs for three audiences:\n\n| Doc | When to read it |\n|-----|-----------------|\n| **[Status](docs\u002FSTATUS.md)** | See what currently works — capability counts, test baselines, recent fixes, what's next. The *is-it-ready* doc. |\n| **[User Guide](docs\u002FUSERGUIDE.md)** | Daily reference — every command, every config flag, every plugin. The *how-do-I* doc. |\n| **[Verification](verification.md)** | Cryptographically prove your installed bytes match the signed witness — `ruflo verify`. The *trust-but-verify* doc. |\n\nUser Guide section index:\n\n| Section | Topics |\n|---------|--------|\n| [Quick Start](docs\u002FUSERGUIDE.md#quick-start) | Installation, prerequisites, install profiles |\n| [Core Features](docs\u002FUSERGUIDE.md#-core-features) | MCP tools, agents, memory, neural learning |\n| [Intelligence & Learning](docs\u002FUSERGUIDE.md#-intelligence--learning) | Hooks, workers, SONA, model routing |\n| [Swarm & Coordination](docs\u002FUSERGUIDE.md#-swarm--coordination) | Topologies, consensus, hive mind |\n| [Security](docs\u002FUSERGUIDE.md#%EF%B8%8F-security) | AIDefence, CVE remediation, validation |\n| [Ecosystem](docs\u002FUSERGUIDE.md#-ecosystem--integrations) | RuVector, agentic-flow, Flow Nexus |\n| [Configuration](docs\u002FUSERGUIDE.md#%EF%B8%8F-configuration--reference) | Environment variables, config schema |\n| [Plugin Marketplace](https:\u002F\u002Fruvnet.github.io\u002Fruflo) | Browse and install plugins |\n\n---\n\n## Support\n\n| Resource | Link |\n|----------|------|\n| Documentation | [User Guide](docs\u002FUSERGUIDE.md) |\n| Issues & Bugs | [GitHub Issues](https:\u002F\u002Fgithub.com\u002Fruvnet\u002Fclaude-flow\u002Fissues) |\n| Enterprise | [ruv.io](https:\u002F\u002Fruv.io) |\n| Community | [Agentics Foundation Discord](https:\u002F\u002Fdiscord.com\u002Finvite\u002FdfxmpwkG2D) |\n| Powered by | [Cognitum.one](https:\u002F\u002Fcognitum.one) |\n\n## License\n\nMIT - [RuvNet](https:\u002F\u002Fgithub.com\u002Fruvnet)\n","Ruflo 是一个面向 Claude 的领先代理编排平台，能够部署智能多代理集群、协调自主工作流并构建对话式 AI 系统。该项目采用 TypeScript 编写，具备企业级架构设计，支持自我学习的集群智能、RAG 集成以及与 Claude Code\u002FCodex 的原生集成等核心功能。它适用于需要复杂交互和自动化流程处理的场景，如客户服务、任务规划及执行等领域。","2026-06-11 02:30:24","trending"]