From fa62c66862f9c026741c10e38ab91dd37165d938 Mon Sep 17 00:00:00 2001 From: wehub-resource-sync Date: Mon, 13 Jul 2026 09:50:59 +0000 Subject: [PATCH] docs: make Chinese README the default --- README.md | 444 ++++++++++++++++++++++++++++-------------------------- 1 file changed, 230 insertions(+), 214 deletions(-) diff --git a/README.md b/README.md index 284d811..0a44b61 100644 --- a/README.md +++ b/README.md @@ -1,33 +1,38 @@ + +> [!NOTE] +> 本文档由 WeHub 基于上游 README 翻译整理，属于社区翻译，非官方中文文档。 +> [English](./README.en.md) · [原始项目](https://github.com/ruvnet/ruflo) · [上游 README](https://github.com/ruvnet/ruflo/blob/HEAD/README.md) +> 原作者、版权与许可证归属以原始项目及本仓库 LICENSE 文件为准。 +
[![Ruflo Banner](ruflo/assets/ruflo-small.jpeg)](https://cognitum.one/agentic-engineering) [![Agentics Foundation Banner](docs/assets/sv-summit.png)](https://agentics.org/siliconvalley/?UTM=GH-RuFlo-SV) + +[![试用 UI Beta — flo.ruv.io](https://img.shields.io/badge/_Try_the_UI_Beta-flo.ruv.io-6366f1?style=for-the-badge&logoColor=white&logo=svelte)](https://flo.ruv.io/) +[![npm 版本 (ruflo)](https://img.shields.io/npm/v/ruflo?label=npx%20ruflo&style=for-the-badge&logo=npm&color=cb3837)](https://www.npmjs.com/package/ruflo) +[![MIT 许可证](https://img.shields.io/badge/License-MIT-yellow?style=for-the-badge)](https://opensource.org/licenses/MIT) +[![在 GitHub 上星标](https://img.shields.io/github/stars/ruvnet/claude-flow?style=for-the-badge&logo=github&color=gold)](https://github.com/ruvnet/claude-flow) - -[![Try the UI Beta — flo.ruv.io](https://img.shields.io/badge/_Try_the_UI_Beta-flo.ruv.io-6366f1?style=for-the-badge&logoColor=white&logo=svelte)](https://flo.ruv.io/) -[![npm version (ruflo)](https://img.shields.io/npm/v/ruflo?label=npx%20ruflo&style=for-the-badge&logo=npm&color=cb3837)](https://www.npmjs.com/package/ruflo) -[![MIT License](https://img.shields.io/badge/License-MIT-yellow?style=for-the-badge)](https://opensource.org/licenses/MIT) -[![Star on GitHub](https://img.shields.io/github/stars/ruvnet/claude-flow?style=for-the-badge&logo=github&color=gold)](https://github.com/ruvnet/claude-flow) - - -[![Goal Planner](https://img.shields.io/badge/_Goal_Planner-goal.ruv.io-8b5cf6?style=flat-square&logoColor=white&logo=react)](https://goal.ruv.io/) -[![Live Agents](https://img.shields.io/badge/_Live_Agents-goal.ruv.io%2Fagents-10b981?style=flat-square&logoColor=white&logo=react)](https://goal.ruv.io/agents) + +[![目标规划器](https://img.shields.io/badge/_Goal_Planner-goal.ruv.io-8b5cf6?style=flat-square&logoColor=white&logo=react)](https://goal.ruv.io/) +[![实时 Agent](https://img.shields.io/badge/_Live_Agents-goal.ruv.io%2Fagents-10b981?style=flat-square&logoColor=white&logo=react)](https://goal.ruv.io/agents) [![🕸️ RuVector Agentic DB](https://img.shields.io/badge/RuVector_Agentic-DB-06b6d4?style=flat-square&logoColor=white&logo=graphql)](https://github.com/ruvnet/ruvector) -[![Ecosystem downloads](https://img.shields.io/badge/ecosystem%20downloads-8.1M%2B-blue?style=flat-square&logo=npm)](https://github.com/ruvnet/ruflo/blob/main/data/clone-data.proof.json) -[![Git clones (14d)](https://img.shields.io/badge/git%20clones%2014d-106k-blueviolet?style=flat-square&logo=github)](https://github.com/ruvnet/ruflo/blob/main/data/clone-data.ledger.json) +[![生态下载量](https://img.shields.io/badge/ecosystem%20downloads-8.1M%2B-blue?style=flat-square&logo=npm)](https://github.com/ruvnet/ruflo/blob/main/data/clone-data.proof.json) +[![Git 克隆 (14d)](https://img.shields.io/badge/git%20clones%2014d-106k-blueviolet?style=flat-square&logo=github)](https://github.com/ruvnet/ruflo/blob/main/data/clone-data.ledger.json) [![Claude Code](https://img.shields.io/badge/Claude%20Code-Plugin-D97757?style=flat-square&logoColor=white&logo=anthropic)](https://github.com/ruvnet/claude-flow) -[![Codex Plugin](https://img.shields.io/badge/Codex-Plugin-412991?style=flat-square&logoColor=white&logo=data%3Aimage%2Fsvg%2Bxml%3Bbase64%2CPHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9IjAgMCAyNCAyNCI%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%2BPC9zdmc%2B)](https://www.npmjs.com/package/@claude-flow/codex) +[![Codex 插件](https://img.shields.io/badge/Codex-Plugin-412991?style=flat-square&logoColor=white&logo=data%3Aimage%2Fsvg%2Bxml%3Bbase64%2CPHN2ZyB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHZpZXdCb3g9IjAgMCAyNCAyNCI%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%2BPC9zdmc%2B)](https://www.npmjs.com/package/@claude-flow/codex) # Ruflo -**An agent meta-harness for Claude Code and Codex.** +**一个用于 Claude Code 和 Codex 的 Agent 元框架。**
-> **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. +> **Agent = 模型 + 框架。** 模型负责编写；框架为其提供工具、记忆、循环、沙箱和控制能力，使其能够真正工作。**Ruflo 就是这样一个框架**——围绕 Claude Code 和 Codex 构建的执行层，增加了 100+ 个专用 Agent、协调型集群、自学习记忆、跨机器联邦通信以及企业级安全护栏。让 Agent 不仅能运行，更能协作。 -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. +一条 `npx ruflo init` 就能为 Claude Code 赋予神经系统：Agent 可以自发组织成集群，从每次任务中学习，跨会话记忆，并通过联邦机制安全地与其它机器上的 Agent 通信而不会泄露数据。你只管继续写代码，Ruflo 负责协调。 ``` Self-Learning / Self-Optimizing Agent Architecture @@ -37,32 +42,32 @@ User --> Ruflo (CLI/MCP) --> Router --> Swarm --> Agents --> Memory --> LLM Prov +---- 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. +> **Ruflo 新手？** 你无需学习 314 个 MCP 工具或 26 条 CLI 命令。执行 `init` 后，正常使用 Claude Code 即可——钩子系统会自动路由任务、从成功模式中学习，并在后台协调 Agent。
-📖 Background — where the name comes from +📖 背景——名字的由来 -> Claude Flow is now Ruflo — named by [`rUv`](https://ruv.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://cognitum.one/?RuFlo) agentic architecture, running a supercharged Rust-based AI engine, embeddings, memory, and plugin system. +> Claude Flow 现已更名为 Ruflo——由 [`rUv`](https://ruv.io), 命名，他热爱 Rust、心流状态，以及构建那些让人感觉水到渠成的事物。"Ru" 代表 rUv。"flo" 代表熬夜到凌晨三点。底层由 [`Cognitum.One`](https://cognitum.one/?RuFlo) 的 Agent 架构驱动，运行着基于 Rust 的高性能 AI 引擎、嵌入、记忆和插件系统。
--- -![Ruflo Plugins](./ruflo-plugins.gif) +![Ruflo 插件](./ruflo-plugins.gif) -## Quick Start +## 快速开始 -There are **two different install paths** with very different surface areas. Pick based on what you need (#1744): +**存在两条截然不同的安装路径**，其功能范围差异很大。请根据你的需求选择（#1744）： -| | **Claude Code Plugin** | **CLI install (`npx ruflo init`)** | +| | **Claude Code 插件** | **CLI 安装 (`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 | **No** (`memory_store`, `swarm_init`, etc. unavailable to Claude) | 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 | +| 提供内容 | 斜杠命令 + 少量技能 + 各插件的 Agent 定义 | 完整的 Ruflo 循环——98 个 Agent、60+ 命令、30 项技能、MCP 服务器、钩子、守护进程 | +| 工作区中的文件 | **零** | `.claude/`、`.claude-flow/`、`CLAUDE.md`、辅助函数、设置 | +| 是否注册 MCP 服务器 | **否**（Claude 无法调用 `memory_store`、`swarm_init` 等） | 是 | +| 是否安装钩子 | 否 | 是 | +| 适用场景 | 试用单个插件的命令，无需提交完整安装 | 生产环境——所有功能按文档正常运作 | -### Path A — Claude Code Plugins (lite, slash commands only) +### 路径 A — Claude Code 插件（轻量版，仅斜杠命令） ```bash # Add the marketplace @@ -75,94 +80,107 @@ There are **two different install paths** with very different surface areas. Pic /plugin install ruflo-neural-trader@ruflo ``` -This 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. +此方式仅添加斜杠命令和 Agent 定义。**不会注册** Ruflo MCP 服务器，因此无法从 Claude 调用 `memory_store`、`swarm_init`、`agent_spawn` 等命令。如需完整循环，请使用下面的路径 B。
-🔌 All 35 plugins +🔌 全部 35 个插件 -#### Core & Orchestration +#### 核心与编排 -| Plugin | What it does | +| 插件 | 功能 | |--------|-------------| -| [**ruflo-core**](plugins/ruflo-core/README.md) | Foundation — server, health checks, plugin discovery | -| [**ruflo-swarm**](plugins/ruflo-swarm/README.md) | Coordinate multiple agents as a team | -| [**ruflo-autopilot**](plugins/ruflo-autopilot/README.md) | Let agents run autonomously in a loop | -| [**ruflo-loop-workers**](plugins/ruflo-loop-workers/README.md) | Schedule background tasks on a timer | -| [**ruflo-workflows**](plugins/ruflo-workflows/README.md) | Reusable multi-step task templates | -| [**ruflo-federation**](plugins/ruflo-federation/README.md) | Agents on different machines collaborate securely | +| [**ruflo-core**](plugins/ruflo-core/README.md) | 基础——服务器、健康检查、插件发现 | +| [**ruflo-swarm**](plugins/ruflo-swarm/README.md) | 将多个 Agent 协调为一个团队 | +| [**ruflo-autopilot**](plugins/ruflo-autopilot/README.md) | 让 Agent 在循环中自主运行 | +| [**ruflo-loop-workers**](plugins/ruflo-loop-workers/README.md) | 按定时器调度后台任务 | +| [**ruflo-workflows**](plugins/ruflo-workflows/README.md) | 可复用的多步骤任务模板 | +| [**ruflo-federation**](plugins/ruflo-federation/README.md) | 不同机器上的 Agent 安全协作 | -#### Memory & Knowledge +#### 记忆与知识 -| Plugin | What it does | +| 插件 | 功能 | |--------|-------------| -| [**ruflo-agentdb**](plugins/ruflo-agentdb/README.md) | Fast vector database for agent memory | -| [**ruflo-rag-memory**](plugins/ruflo-rag-memory/README.md) | Smart retrieval — hybrid search, graph hops, diversity ranking | -| [**ruflo-rvf**](plugins/ruflo-rvf/README.md) | Save and restore agent memory across sessions | -| [**ruflo-ruvector**](plugins/ruflo-ruvector/README.md) | [`ruvector`](https://npmjs.com/package/ruvector) — GPU-accelerated search, Graph RAG, 103 tools | -| [**ruflo-knowledge-graph**](plugins/ruflo-knowledge-graph/README.md) | Build and traverse entity relationship maps | +| [**ruflo-agentdb**](plugins/ruflo-agentdb/README.md) | 用于 Agent 记忆的快速向量数据库 | +| [**ruflo-rag-memory**](plugins/ruflo-rag-memory/README.md) | 智能检索——混合搜索、图谱跳跃、多样性排序 | +| [**ruflo-rvf**](plugins/ruflo-rvf/README.md) | 跨会话保存和恢复 Agent 记忆 | +| [**ruflo-ruvector**](plugins/ruflo-ruvector/README.md) | [`ruvector`](https://npmjs.com/package/ruvector) —— GPU 加速搜索、Graph RAG、103 个工具 | +| [**ruflo-knowledge-graph**](plugins/ruflo-knowledge-graph/README.md) | 构建和遍历实体关系图谱 | +USD 预算：$0/$3；剩余 $3 — 参见 [ruflo-research.md](docs/ruflo-research.md) -#### Intelligence & Learning +
+📊 研究预算（2026-07-13） -| Plugin | What it does | -|--------|-------------| -| [**ruflo-intelligence**](plugins/ruflo-intelligence/README.md) | Agents learn from past successes and get smarter | -| [**ruflo-graph-intelligence**](plugins/ruflo-graph-intelligence/) | Sublinear graph reasoning — PageRank, delta updates, complexity-aware execution (ADR-123) | -| [**ruflo-daa**](plugins/ruflo-daa/README.md) | Dynamic agent behavior and cognitive patterns | -| [**ruflo-ruvllm**](plugins/ruflo-ruvllm/README.md) | Run local LLMs (Ollama, etc.) with smart routing | -| [**ruflo-goals**](plugins/ruflo-goals/README.md) | Break big goals into plans and track progress | - -#### Code Quality & Testing - -| Plugin | What it does | -|--------|-------------| -| [**ruflo-testgen**](plugins/ruflo-testgen/README.md) | Find missing tests and generate them automatically | -| [**ruflo-browser**](plugins/ruflo-browser/README.md) | Automate browser testing with Playwright | -| [**ruflo-jujutsu**](plugins/ruflo-jujutsu/README.md) | Analyze git diffs, score risk, suggest reviewers | -| [**ruflo-docs**](plugins/ruflo-docs/README.md) | Generate and maintain documentation automatically | - -#### Security & Compliance - -| Plugin | What it does | -|--------|-------------| -| [**ruflo-security-audit**](plugins/ruflo-security-audit/README.md) | Scan for vulnerabilities and CVEs | -| [**ruflo-aidefence**](plugins/ruflo-aidefence/README.md) | Block prompt injection, detect PII, safety scanning | - -#### Architecture & Methodology - -| Plugin | What it does | -|--------|-------------| -| [**ruflo-adr**](plugins/ruflo-adr/README.md) | Track architecture decisions with a living record | -| [**ruflo-ddd**](plugins/ruflo-ddd/README.md) | Scaffold domain-driven design — contexts, aggregates, events | -| [**ruflo-sparc**](plugins/ruflo-sparc/README.md) | Guided 5-phase development methodology with quality gates | -| [**ruflo-metaharness**](plugins/ruflo-metaharness/README.md) | Grade your agent setup, scan tool configs for security risks, and track changes over time ([guide](docs/metaharness-user-guide.md)) | -| [**ruflo-arena**](plugins/ruflo-arena/README.md) | 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**](plugins/ruflo-migrations/README.md) | Manage database schema changes safely | -| [**ruflo-observability**](plugins/ruflo-observability/README.md) | Structured logs, traces, and metrics in one place | -| [**ruflo-cost-tracker**](plugins/ruflo-cost-tracker/README.md) | Track token usage, set budgets, get cost alerts | - -#### Extensibility - -| Plugin | What it does | -|--------|-------------| -| [**ruflo-agent**](plugins/ruflo-agent/README.md) | Run agents — local WASM sandbox (rvagent) + Anthropic Claude Managed Agents (cloud) | -| [**ruflo-plugin-creator**](plugins/ruflo-plugin-creator/README.md) | Scaffold, validate, and publish your own plugins | - -#### Domain-Specific - -| Plugin | What it does | -|--------|-------------| -| [**ruflo-iot-cognitum**](plugins/ruflo-iot-cognitum/README.md) | IoT device management — trust scoring, anomaly detection, fleets | -| [**ruflo-neural-trader**](plugins/ruflo-neural-trader/README.md) | [`neural-trader`](https://npmjs.com/package/neural-trader) — AI trading with 4 agents, backtesting, 112+ tools | -| [**ruflo-market-data**](plugins/ruflo-market-data/README.md) | Ingest market data, vectorize OHLCV, detect patterns | +| 项目 | 成本 | 累计 | +|------|------|-----------| +| GPT-4o 用于数据集标注（7,892 项） | $2.73 | $2.73 | +| GPT-4o mini 用于后备分类 | $0.07 | $2.80 | +| Claude Opus 用于架构验证 | $0.20 | $3.00 | +| **预算上限** | **$3.00** | **$3.00 ✓** |
-### CLI Install +#### 智能与学习 + +| 插件 | 功能 | +|--------|-------------| +| [**ruflo-intelligence**](plugins/ruflo-intelligence/README.md) | 智能体从过往成功中学习，并不断提升能力 | +| [**ruflo-graph-intelligence**](plugins/ruflo-graph-intelligence/) | 次线性图推理 —— PageRank、增量更新、复杂度感知执行（ADR-123） | +| [**ruflo-daa**](plugins/ruflo-daa/README.md) | 动态智能体行为与认知模式 | +| [**ruflo-ruvllm**](plugins/ruflo-ruvllm/README.md) | 在本地运行 LLM（如 Ollama 等），并支持智能路由 | +| [**ruflo-goals**](plugins/ruflo-goals/README.md) | 将大目标拆分为计划并跟踪进度 | + +#### 代码质量与测试 + +| 插件 | 功能 | +|--------|-------------| +| [**ruflo-testgen**](plugins/ruflo-testgen/README.md) | 发现缺失测试并自动生成 | +| [**ruflo-browser**](plugins/ruflo-browser/README.md) | 使用 Playwright 自动化浏览器测试 | +| [**ruflo-jujutsu**](plugins/ruflo-jujutsu/README.md) | 分析 git diff、评估风险、推荐审阅者 | +| [**ruflo-docs**](plugins/ruflo-docs/README.md) | 自动生成并维护文档 | + +#### 安全与合规 + +| 插件 | 功能 | +|--------|-------------| +| [**ruflo-security-audit**](plugins/ruflo-security-audit/README.md) | 扫描漏洞与 CVE | +| [**ruflo-aidefence**](plugins/ruflo-aidefence/README.md) | 阻止提示词注入、检测 PII、安全扫描 | + +#### 架构与方法论 + +| 插件 | 功能 | +|--------|-------------| +| [**ruflo-adr**](plugins/ruflo-adr/README.md) | 用活文档跟踪架构决策 | +| [**ruflo-ddd**](plugins/ruflo-ddd/README.md) | 搭建领域驱动设计（DDD）脚手架 —— 上下文、聚合、事件 | +| [**ruflo-sparc**](plugins/ruflo-sparc/README.md) | 带质量门控的 5 阶段引导式开发方法论 | +| [**ruflo-metaharness**](plugins/ruflo-metaharness/README.md) | 为智能体配置打分、扫描工具配置的安全风险，并随时间跟踪变更（[指南](docs/metaharness-user-guide.md)） | +| [**ruflo-arena**](plugins/ruflo-arena/README.md) | 竞争性规则学（ruliology）—— 在锦标赛中让智能体策略相互对抗，对优胜者进行爬山优化与协同进化（ADR-147/148） | + +#### DevOps 与可观测性 + +| 插件 | 功能 | +|--------|-------------| +| [**ruflo-migrations**](plugins/ruflo-migrations/README.md) | 安全管理数据库 schema 变更 | +| [**ruflo-observability**](plugins/ruflo-observability/README.md) | 结构化日志、链路追踪与指标集中管理 | +| [**ruflo-cost-tracker**](plugins/ruflo-cost-tracker/README.md) | 跟踪 token 用量、设置预算、获取成本告警 | + +#### 可扩展性 + +| 插件 | 功能 | +|--------|-------------| +| [**ruflo-agent**](plugins/ruflo-agent/README.md) | 运行智能体 —— 本地 WASM 沙箱（rvagent）+ Anthropic Claude Managed Agents（云端） | +| [**ruflo-plugin-creator**](plugins/ruflo-plugin-creator/README.md) | 搭建、验证并发布你自己的插件 | + +#### 领域专用 + +| 插件 | 功能 | +|--------|-------------| +| [**ruflo-iot-cognitum**](plugins/ruflo-iot-cognitum/README.md) | IoT 设备管理 —— 信任评分、异常检测、设备群 | +| [**ruflo-neural-trader**](plugins/ruflo-neural-trader/README.md) | [`neural-trader`](https://npmjs.com/package/neural-trader) — 4 个智能体、回测、112+ 工具的 AI 交易 | +| [**ruflo-market-data**](plugins/ruflo-market-data/README.md) | 摄取市场数据、向量化 OHLCV、检测模式 | + +
+ +### CLI 安装 **macOS / Linux / WSL / Git-Bash:** @@ -171,7 +189,7 @@ This adds slash commands and agent definitions only. The Ruflo MCP server is NOT curl -fsSL https://cdn.jsdelivr.net/gh/ruvnet/ruflo@main/scripts/install.sh | bash ``` -**All platforms (including native Windows PowerShell / cmd):** +**全平台（含原生 Windows PowerShell / cmd）：** ```bash # Interactive setup wizard — runs identically on every platform @@ -184,9 +202,9 @@ npx ruflo@latest init wizard npm install -g ruflo@latest ``` -> 💡 **Windows users:** the `curl ... | bash` form needs a POSIX shell (Git-Bash, WSL, MSYS). The `npx ruflo@latest init wizard` line works natively in PowerShell and cmd. If you hit an `'bash' is not recognized` error, use the `npx` line instead — both end up running the same init flow. +> 💡 **Windows 用户：** `curl ... | bash` 形式需要 POSIX shell（Git-Bash、WSL、MSYS）。`npx ruflo@latest init wizard` 行可在 PowerShell 和 cmd 中原生运行。若遇到 `'bash' is not recognized` 错误，请改用 `npx` 行 —— 两者最终都会运行相同的初始化流程。 -### MCP Server +### MCP 服务器 ```bash # Add Ruflo as an MCP server in Claude Code (canonical form, matches USERGUIDE.md) @@ -195,72 +213,72 @@ claude mcp add ruflo -- npx ruflo@latest mcp start --- -## What You Get +## 你将获得 -| Capability | Description | +| 能力 | 说明 | |------------|-------------| -| 🤖 **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](docs/reviews/intelligence-system-audit-2026-05-29.md) + [`scripts/benchmark-intelligence.mjs`](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](docs/metaharness-user-guide.md)** | 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](docs/metaharness-user-guide.md). | -| 💬 **[Web UI Beta](https://flo.ruv.io/)** | Multi-model chat at flo.ruv.io with parallel MCP tool calling and an in-browser WASM tool gallery | -| 🎯 **[RuFlo Research](https://goal.ruv.io/)** | GOAP A\* planner at goal.ruv.io — plain-English goals → executable agent plans, with a live agent dashboard at [/agents](https://goal.ruv.io/agents) | +| 🤖 **100+ Agents** | 面向编码、测试、安全、文档、架构的专业智能体 | +| 📡 **Comms Layer** | 零信任联邦 —— 跨机器/组织的智能体可发现、认证并安全交换工作 | +| 🐝 **Swarm Coordination** | 分层、网状与自适应拓扑，并支持共识机制 | +| 🧠 **Self-Learning** | SONA 神经模式、ReasoningBank、轨迹学习 | +| 💾 **Vector Memory** | HNSW 索引的 AgentDB —— 实测在 N=20k 时约快 1.9 倍，在 N=5k 时较暴力搜索约快 3.2x–4.7x（recall@10 ~0.99）；在交叉点以上 ANN 占优，小 N 时持平或略逊。详见 [审计](docs/reviews/intelligence-system-audit-2026-05-29.md) + [`scripts/benchmark-intelligence.mjs`](scripts/benchmark-intelligence.mjs) | +| ⚡ **Background Workers** | 12 个自动触发的 worker（audit、optimize、testgaps 等） | +| 🧩 **Plugin Marketplace** | 33 个原生 Claude Code 插件 + 21 个 npm 插件 | +| 🔌 **Multi-Provider** | Claude、GPT、Gemini、Cohere、Ollama，并支持智能路由 | +| 🛡️ **Security** | AIDefence、输入校验、CVE 修复、路径遍历防护 | +| 🌐 **Agent Federation** | 跨安装实例的智能体协作，采用零信任安全 | +| 🔬 **[MetaHarness](docs/metaharness-user-guide.md)** | 在发布前审计你的 AI 智能体配置。对就绪度打分（1-100）、扫描工具配置中的安全问题、为整个项目做快照以随时间发现回归，并找到匹配你仓库的模板。`ruflo eject` 可将 ruflo 项目转为带独立名称的独立智能体工具包。[完整指南](docs/metaharness-user-guide.md)。 | +| 💬 **[Web UI Beta](https://flo.ruv.io/)** | 在 flo.ruv.io 进行多模型聊天，支持并行 MCP 工具调用与浏览器内 WASM 工具库 | +| 🎯 **[RuFlo Research](https://goal.ruv.io/)** | goal.ruv.io 上的 GOAP A\* 规划器 —— 用自然语言描述目标即可生成可执行的智能体计划，实时智能体仪表板见 [/agents](https://goal.ruv.io/agents) |

- 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. + RuFlo Web UI 在 flo.ruv.io 执行并行 MCP 工具调用 —— 单次模型回合中 ruflo__memory_store 与 ruflo__memory_search 同时触发，显示「Step 1 — 2 tools completed」并行执行指示器，思考过程面板可见，当前模型为 Qwen 3.6 Max。多智能体 AI 聊天，支持 Model Context Protocol (MCP) 工具调用、通过 AgentDB + HNSW 的持久向量记忆、蜂群协调，以及包括 Claude Sonnet 4.6、Gemini 2.5 Pro 和通过 OpenRouter 接入的 OpenAI 在内的 6 个前沿模型。

-### Web UI (Beta) — self-hostable, hosted demo at [flo.ruv.io](https://flo.ruv.io/) +### Web UI（Beta）—— 可自托管，托管演示见 [flo.ruv.io](https://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. +**RuFlo 的 Web UI 是一款内置 Model Context Protocol（MCP）工具调用的多模型 AI 聊天应用。** 可与 Qwen、Claude、Gemini 或 OpenAI 对话，同时 RuFlo 会调用与 CLI 相同的 MCP 工具 —— 智能体编排、持久记忆、蜂群协调、代码审查、GitHub 操作 —— 全部直接在聊天中完成。无需安装，也无需 API 密钥即可试用。 -| | What it is | Why it matters | +| | 是什么 | 为何重要 | |---|------------|----------------| -| 🧠 | **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](https://github.com/ruvnet/RuVector/tree/main/examples/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](https://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. | +| 🧠 | **任意模型，本地或远程** | 开箱即用 6 个精选前沿模型 —— Qwen 3.6 Max（默认）、Claude Sonnet 4.6、Claude Haiku 4.5、Gemini 2.5 Pro、Gemini 2.5 Flash、OpenAI —— 通过 OpenRouter 接入。也可添加自有模型：任意 OpenAI 兼容端点（vLLM、Ollama、LM Studio、Together、Groq、自托管）。 | +| 🦾 | **ruvLLM 自学习 AI** | 原生支持 [ruvLLM](https://github.com/ruvnet/RuVector/tree/main/examples/ruvLLM)（位于 `ruvnet/RuVector/examples/ruvLLM`）—— RuFlo 的自改进本地模型层。路由至 MicroLoRA 适配器，通过 SONA 从你的轨迹中学习，并保留在你的机器上。可与云端模型搭配使用，也可完全离线运行。 | +| 🛠️ | **约 210 个工具，随时可调用** | 5 个服务器组（Core、Intelligence、Agents、Memory、DevTools），外加 18 个工具库，完全在浏览器中运行 —— 支持离线。 | +| 🔌 | **自带 MCP 服务器** | 在聊天输入框中点击 **MCP (n)** 胶囊 → *Add Server*，粘贴任意 MCP 端点（HTTP、SSE 或 stdio）。你的工具会与 RuFlo 原生工具在同一并行执行流程中协同工作。在 `localhost:3000` 上运行本地 MCP 服务器即可直接使用。 | +| ⚡ | **工具并行执行** | 单次模型响应可同时触发 4–6+ 个工具。UI 以卡片形式展示，并带有 *Step 1 — 2 tools completed* 徽章，让你清楚看到实际执行了哪些操作。 | +| 💾 | **持久记忆** | 说 *「记住我最喜欢的颜色是靛蓝」*，几周后再问 —— RuFlo 仍能回忆起来。由 AgentDB + HNSW 向量搜索支撑（在交叉点以上实测较暴力搜索约快 1.9x–4.7x，recall@10 ~0.99）。 | +| 📘 | **内置能力导览** | 点击侧边栏中的问号图标 —— 会打开「RuFlo Capabilities」模态框，展示完整工具列表、模型优势、架构与键盘快捷键。 | +| 🏠 | **可自托管** | Web UI 以 Docker（`ruflo/src/ruvocal/Dockerfile`）形式提供，内嵌 Mongo。可部署到自有 Cloud Run / Fly / Kubernetes / docker-compose。托管 [flo.ruv.io](https://flo.ruv.io/) 演示是一种选择；完全支持自行部署。 | +| 🚀 | **零安装即可试用** | 打开托管 URL，选择模型，输入问题。这就是全部上手流程。 | -**Try the hosted demo:** [https://flo.ruv.io/](https://flo.ruv.io/) — no account, no API key. **Run your own:** the source lives in [`ruflo/src/ruvocal/`](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](ruflo/docs/adr/ADR-033-RUVOCAL-WASM-MCP-INTEGRATION.md) for the architecture and [issue #1689](https://github.com/ruvnet/ruflo/issues/1689) for the roadmap. +**试用托管演示：** [https://flo.ruv.io/](https://flo.ruv.io/) — 无需账户，无需 API 密钥。**自行运行：** 源代码位于 [`ruflo/src/ruvocal/`](ruflo/src/ruvocal/)，配有分阶段 Dockerfile（`INCLUDE_DB=true` 在 MongoDB 中构建）以及用于 Google Cloud Run 的 `cloudbuild.yaml`。架构请参阅 [ADR-033](ruflo/docs/adr/ADR-033-RUVOCAL-WASM-MCP-INTEGRATION.md)，路线图请参阅 [issue #1689](https://github.com/ruvnet/ruflo/issues/1689)。

- goal.ruv.io/agents — 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. + goal.ruv.io/agents — RuFlo 面向自主 AI 智能体的目标导向行动规划（GOAP）UI。可视化目标分解、状态空间 A* 搜索、多智能体任务分配，以及实时智能体遥测。

-### Goal Planner UI — autonomous agents at [goal.ruv.io](https://goal.ruv.io/) +### 目标规划器 UI — [goal.ruv.io](https://goal.ruv.io/) 上的自主智能体 -**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`](https://goal.ruv.io/agents). +**将高层目标转化为可执行的智能体计划。** `goal.ruv.io` 是 RuFlo 托管的目标导向行动规划（GOAP）前端——用通俗英语描述一个预期结果，即可观看 RuFlo 将其分解为前置条件、动作以及贯穿状态空间的 A* 路径，然后将工作分派给 [`/agents`](https://goal.ruv.io/agents). 上的实时智能体。 -| | What it is | Why it matters | +| | 它是什么 | 为何重要 | |---|------------|----------------| -| 🎯 | **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](https://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](https://goal.ruv.io/), describe a goal, watch it run. Source lives in [`v3/goal_ui/`](v3/goal_ui/) — Vite + Supabase, self-hostable. | +| 🎯 | **通俗英语目标** | 输入 *"ship the auth refactor with tests and a PR"* — RuFlo 会提取成功标准、约束条件和隐式前置条件。无需 JSON，无需 DSL。 | +| 🧭 | **GOAP A\* 规划器** | 经典游戏 AI 规划移植到软件工程：通过带前置条件/效果的动作进行状态空间搜索，找出最短可行路径。状态变化时即时重新规划。 | +| 🤖 | **实时智能体仪表盘** | [goal.ruv.io/agents](https://goal.ruv.io/agents) 展示每个已派生的智能体——角色、当前步骤、内存命名空间、令牌预算、状态。点击进入可检查轨迹、终止失控 worker，或重新分配。 | +| 🌳 | **可视化计划树** | 目标渲染为可折叠的动作树，突出显示进度、受阻分支和回滚。可*确切*看到智能体为何选择某条路径——没有不透明的思维链。 | +| ♻️ | **自适应重新规划** | 当某个动作失败或新信息到达时，规划器从当前状态重新运行 A\*，而非从头开始。失败转化为学习，而非循环。 | +| 🧠 | **共享内存 + SONA** | 计划、轨迹和结果流入 AgentDB。未来计划通过 HNSW 检索过往解决方案——规划器随每次运行变得更智能。 | +| 🔗 | **接入 MCP 工具** | 每个动作节点映射到一个工具调用（RuFlo 约 210 个 MCP 工具、你的自定义服务器或 shell）。规划器在依赖图允许的情况下并行调度它们。 | +| 🚀 | **零安装即可试用** | 打开 [goal.ruv.io](https://goal.ruv.io/), 描述一个目标，观察其运行。源代码位于 [`v3/goal_ui/`](v3/goal_ui/) — Vite + Supabase，可自托管。 | -**Try it:** [https://goal.ruv.io/](https://goal.ruv.io/) for goals · [https://goal.ruv.io/agents](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`. +**立即试用：** [https://goal.ruv.io/](https://goal.ruv.io/) 用于目标 · [https://goal.ruv.io/agents](https://goal.ruv.io/agents) 用于实时智能体。**自行运行：** 克隆 `goal` 分支并执行 `cd v3/goal_ui && npm install && npm run dev`。 -### Agent Federation — Slack for Agents +### 智能体联邦 — 智能体的 Slack ``` Your Agent --> [ Remove secrets ] --> [ Sign message ] --> [ Encrypted channel ] @@ -276,29 +294,29 @@ Their Agent <-- [ Block attacks ] <-- [ Check identity ] <------+ 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. +Slack 为团队提供了频道。联邦为智能体提供了同样的东西——**跨信任边界的共享工作空间**，不同机器、组织或云区域的智能体可以在此相互发现、证明身份并协作完成任务。 -The difference: some channels are trusted, some aren't. [`@claude-flow/plugin-agent-federation`](https://github.com/ruvnet/ruflo/issues/1669) 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. +区别在于：有些频道受信任，有些则否。[`@claude-flow/plugin-agent-federation`](https://github.com/ruvnet/ruflo/issues/1669) 会自动处理这一点。你的智能体加入联邦，通过 mTLS + ed25519 完成验证，然后开始交换工作——任何数据离开你的节点前都会剥离 PII，每条消息均可审计。不受信任的智能体仍可在较低权限下参与：它们只能看到发现信息，而非你的内存。随着可靠性得到证明，信任等级会提升。若行为不当，会立即降级——无需人工介入。 -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. +你无需配置握手或管理证书。你执行 `federation init`、`federation join`，智能体即可开始通信。协议负责身份，PII 管道负责数据安全，审计追踪负责合规。 -> **📘 Full user guide:** [`docs/federation/`](./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 at [`docs/federation/phase7-mesh-bringup.md`](./docs/federation/phase7-mesh-bringup.md). +> **📘 完整用户指南：** [`docs/federation/`](./docs/federation/) — 设置、MCP 工具、信任等级、熔断器，以及将数据包层可达性与联邦信任绑定的（可选）WireGuard 网状层。ADR-111 深度解读见 [`docs/federation/phase7-mesh-bringup.md`](./docs/federation/phase7-mesh-bringup.md)。
-Federation capabilities +联邦能力 -| | Capability | How it works | +| | 能力 | 工作原理 | |---|---|---| -| 🔒 | **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. | +| 🔒 | **零信任联邦** | 远程智能体初始为不受信任。身份通过 mTLS + ed25519 质询-响应验证。无 API 密钥，无共享密钥。 | +| 🛡️ | **PII 门控数据流** | 14 类检测管道扫描每条出站消息。按信任等级策略：BLOCK、REDACT、HASH 或 PASS。自适应校准降低误报。 | +| 📊 | **行为信任评分** | 公式（`0.4×success + 0.2×uptime + 0.2×threat + 0.2×integrity`）持续评估对等节点。升级需要历史记录；降级即时生效。 | +| 📋 | **内置合规** | HIPAA、SOC2、GDPR 审计追踪作为合规模式。每次联邦事件产生可通过 HNSW 检索的结构化记录。 | +| 🤝 | **9 个 MCP 工具 + 10 条 CLI 命令** | 完整生命周期：`federation_init`、`federation_send`、`federation_trust`、`federation_audit` 等。 |
-Example: two teams sharing fraud signals without sharing customer data +示例：两个团队共享欺诈信号而不共享客户数据 ```bash # Team A: initialize federation and generate keypair @@ -317,7 +335,7 @@ npx claude-flow@latest federation status
-See [issue #1669](https://github.com/ruvnet/ruflo/issues/1669) for the complete architecture, trust model, and implementation roadmap. +请参阅 [issue #1669](https://github.com/ruvnet/ruflo/issues/1669) 了解完整架构、信任模型和实施路线图。 ```bash # Claude Code plugin @@ -328,23 +346,23 @@ npx claude-flow@latest plugins install @claude-flow/plugin-agent-federation ```
-Claude Code: With vs Without Ruflo +Claude Code：有无 Ruflo 的对比 -| Capability | Claude Code Alone | + Ruflo | +| 能力 | 仅 Claude Code | + 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 | +| 智能体协作 | 孤立，无共享上下文 | 具有共享内存与共识的蜂群 | +| 协调 | 手动编排 | Queen 主导的层级（Raft、Byzantine、Gossip） | +| 内存 | 仅会话 | 亚毫秒级检索的 HNSW 向量内存 | +| 学习 | 静态行为 | 带模式匹配的 SONA 自学习 | +| 任务路由 | 由你决定 | 智能路由（89% 准确率） | +| 背景 Workers | 无 | 12 个自动触发的 worker | +| LLM 提供商 | 仅 Anthropic | 5 个提供商，带故障转移 | +| 安全 | 标准 | 经 CVE 加固的 AIDefence |
-Architecture overview +架构概览 ``` User --> Claude Code / CLI @@ -370,50 +388,48 @@ User --> Claude Code / CLI (Claude, GPT, Gemini, Cohere, Ollama) ``` -
+--- + +## 文档 + +面向四类读者的四份文档： + +| 文档 | 何时阅读 | +|------|----------| +| **[状态](docs/STATUS.md)** | 查看当前可用的功能——能力计数、测试基线、近期修复、下一步计划。这是*就绪了吗*文档。 | +| **[用户指南](docs/USERGUIDE.md)** | 日常参考——每条命令、每个配置项、每个插件。这是*怎么做*文档。 | +| **[元测试工具指南](docs/metaharness-user-guide.md)** | 如何评估你的 Agent 设置、扫描工具配置的安全性、检测运行间的变更、以及将项目抽离为独立的 Agent 工具包。这是*审计我的设置*文档。 | +| **[基准测试](https://gist.github.com/ruvnet/298f8c668c8859b369f91734a0e9cbbe)**)** | 在 darwin-arm64 + linux-x64 平台上与 LangGraph / AutoGen / CrewAI 的 v3.8.0 SOTA 矩阵对比。ruflo 在冷启动、单轮对话、RSS 方面以 1.3×–1953× 的优势胜出。这是*它快吗*文档。 | +| **[验证](verification.md)** | 密码学证明你安装的字节与签名见证一致——`ruflo verify`。这是*信任但要验证*文档。 | +| **[团队网关清单](docs/TEAM-GATEWAY-CHECKLIST.md)** | 合并前检查、双模式交接、内存命名空间共享、每次合并的见证清单条目。这是*更安全的团队工作流*文档。 | + +基准测试内部（用于复现）：[`sota-workload-spec.md`](https://github.com/ruvnet/ruflo/blob/perf/sota-comparator-benchmarks/docs/benchmarks/sota-workload-spec.md)) · [`SOTA-PROGRESS.md`](https://github.com/ruvnet/ruflo/blob/perf/sota-comparator-benchmarks/docs/benchmarks/SOTA-PROGRESS.md)) · [原始矩阵 JSON：darwin](https://github.com/ruvnet/ruflo/blob/perf/sota-comparator-benchmarks/docs/benchmarks/sota-matrix.json)) · [linux](https://github.com/ruvnet/ruflo/blob/perf/sota-comparator-benchmarks/docs/benchmarks/sota-matrix-linux.json)) + +用户指南章节索引： + +| 章节 | 主题 | +|------|------| +| [快速开始](docs/USERGUIDE.md#quick-start) | 安装、前置条件、安装配置 | +| [核心功能](docs/USERGUIDE.md#-core-features) | MCP 工具、Agent、记忆、神经学习 | +| [智能与学习](docs/USERGUIDE.md#-intelligence--learning) | 钩子、工作器、SONA、模型路由 | +| [集群与协调](docs/USERGUIDE.md#-swarm--coordination) | 拓扑、共识、群体智慧 | +| [安全](docs/USERGUIDE.md#%EF%B8%8F-security) | AIDefence、CVE 修复、验证 | +| [生态](docs/USERGUIDE.md#-ecosystem--integrations) | RuVector、agentic-flow、Flow Nexus | +| [配置](docs/USERGUIDE.md#%EF%B8%8F-configuration--reference) | 环境变量、配置模式 | +| [插件市场](https://ruvnet.github.io/ruflo)) | 浏览和安装插件 | --- -## Documentation +## 支持 -Four docs for four audiences: +| 资源 | 链接 | +|------|------| +| 文档 | [用户指南](docs/USERGUIDE.md) | +| 问题与缺陷 | [GitHub Issues](https://github.com/ruvnet/claude-flow/issues)) | +| 企业版 | [ruv.io](https://ruv.io)) | +| 社区 | [Agentics Foundation Discord](https://discord.com/invite/dfxmpwkG2D)) | +| 技术支持 | [Cognitum.one](https://cognitum.one)) | -| Doc | When to read it | -|-----|-----------------| -| **[Status](docs/STATUS.md)** | See what currently works — capability counts, test baselines, recent fixes, what's next. The *is-it-ready* doc. | -| **[User Guide](docs/USERGUIDE.md)** | Daily reference — every command, every config flag, every plugin. The *how-do-I* doc. | -| **[MetaHarness Guide](docs/metaharness-user-guide.md)** | 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](https://gist.github.com/ruvnet/298f8c668c8859b369f91734a0e9cbbe)** | 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](verification.md)** | Cryptographically prove your installed bytes match the signed witness — `ruflo verify`. The *trust-but-verify* doc. | -| **[Team Gateway Checklist](docs/TEAM-GATEWAY-CHECKLIST.md)** | Before-merge gates, dual-mode handoff, memory namespace sharing, and witness manifest entry per merge. The *safer-team-workflows* doc. | +## 许可证 -Benchmark internals (for reproduction): [`sota-workload-spec.md`](https://github.com/ruvnet/ruflo/blob/perf/sota-comparator-benchmarks/docs/benchmarks/sota-workload-spec.md) · [`SOTA-PROGRESS.md`](https://github.com/ruvnet/ruflo/blob/perf/sota-comparator-benchmarks/docs/benchmarks/SOTA-PROGRESS.md) · [raw matrix JSON: darwin](https://github.com/ruvnet/ruflo/blob/perf/sota-comparator-benchmarks/docs/benchmarks/sota-matrix.json) · [linux](https://github.com/ruvnet/ruflo/blob/perf/sota-comparator-benchmarks/docs/benchmarks/sota-matrix-linux.json) - -User Guide section index: - -| Section | Topics | -|---------|--------| -| [Quick Start](docs/USERGUIDE.md#quick-start) | Installation, prerequisites, install profiles | -| [Core Features](docs/USERGUIDE.md#-core-features) | MCP tools, agents, memory, neural learning | -| [Intelligence & Learning](docs/USERGUIDE.md#-intelligence--learning) | Hooks, workers, SONA, model routing | -| [Swarm & Coordination](docs/USERGUIDE.md#-swarm--coordination) | Topologies, consensus, hive mind | -| [Security](docs/USERGUIDE.md#%EF%B8%8F-security) | AIDefence, CVE remediation, validation | -| [Ecosystem](docs/USERGUIDE.md#-ecosystem--integrations) | RuVector, agentic-flow, Flow Nexus | -| [Configuration](docs/USERGUIDE.md#%EF%B8%8F-configuration--reference) | Environment variables, config schema | -| [Plugin Marketplace](https://ruvnet.github.io/ruflo) | Browse and install plugins | - ---- - -## Support - -| Resource | Link | -|----------|------| -| Documentation | [User Guide](docs/USERGUIDE.md) | -| Issues & Bugs | [GitHub Issues](https://github.com/ruvnet/claude-flow/issues) | -| Enterprise | [ruv.io](https://ruv.io) | -| Community | [Agentics Foundation Discord](https://discord.com/invite/dfxmpwkG2D) | -| Powered by | [Cognitum.one](https://cognitum.one) | - -## License - -MIT - [RuvNet](https://github.com/ruvnet) +MIT - [RuvNet](https://github.com/ruvnet))