π The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
TypeScript agentic-aiagentic-frameworkagentic-workflowagentsai-agentsai-assistantai-skillsautonomous-agentsclaudecodexdsh-pluginharnessmcp-servermulti-agentmulti-agent-systemsnpmskillsswarmswarm-intelligencetypescript
Checkpoint: File edits
rUv9d0b69297942
diff --git a/README.md b/README.mdindex 38d7016ecc..529e4f9685 100644--- a/README.md+++ b/README.md@@ -1,14 +1,14 @@-# π Claude-Flow v3: Enterprise AI Orchestration Platform+# π RuvFlow v3: Enterprise AI Orchestration Platform<div align="center">-+[](https://github.com/ruvnet/claude-flow)-[](https://www.npmjs.com/package/claude-flow)-[](https://www.npmjs.com/package/claude-flow)+[](https://www.npmjs.com/package/ruvflow)+[](https://www.npmjs.com/package/ruvflow)[](https://ruv.io)[](https://discord.com/invite/dfxmpwkG2D)[](https://github.com/ruvnet/claude-flow)@@ -25,12 +25,12 @@## Getting into the Flow-Claude-Flow is a comprehensive AI agent orchestration framework that transforms Claude Code into a powerful multi-agent development platform. It enables teams to deploy, coordinate, and optimize specialized AI agents working together on complex software engineering tasks.+RuvFlow is a comprehensive AI agent orchestration framework that transforms Claude Code into a powerful multi-agent development platform. It enables teams to deploy, coordinate, and optimize specialized AI agents working together on complex software engineering tasks.### Self-Learning/Self-Optimizing Agent Architecture```-User β Claude-Flow (CLI/MCP) β Router β Swarm β Agents β Memory β LLM Providers+User β RuvFlow (CLI/MCP) β Router β Swarm β Agents β Memory β LLM Providersβ ββββββ Learning Loop ββββββββ```@@ -141,8 +141,8 @@ flowchart TB# Install RuVector standalonenpx ruvector-# Or use via Claude-Flow-npx claude-flow@v3alpha hooks intelligence --status+# Or use via RuvFlow+npx ruvflow@v3alpha hooks intelligence --status```</details>@@ -157,7 +157,7 @@ curl -fsSL https://cdn.jsdelivr.net/gh/ruvnet/claude-flow@main/scripts/install.scurl -fsSL https://cdn.jsdelivr.net/gh/ruvnet/claude-flow@main/scripts/install.sh | bash -s -- --full# Or via npx-npx claude-flow@alpha init --wizard+npx ruvflow@alpha init --wizard```---@@ -171,7 +171,7 @@ npx claude-flow@alpha init --wizardπ **Works With Any LLM** - Switch between Claude, GPT, Gemini, Cohere, or local models like Llama. Automatic failover if one provider is unavailable. Smart routing picks the cheapest option that meets quality requirements.-β‘ **Plugs Into Claude Code** - Native integration via MCP (Model Context Protocol). Use claude-flow commands directly in your Claude Code sessions with full tool access.+β‘ **Plugs Into Claude Code** - Native integration via MCP (Model Context Protocol). Use ruvflow commands directly in your Claude Code sessions with full tool access.π **Production-Ready Security** - Built-in protection against prompt injection, input validation, path traversal prevention, command injection blocking, and safe credential handling.@@ -346,7 +346,7 @@ const config = optimizer.getOptimalConfig(agentCount);<details><summary>π‘οΈ <strong>Anti-Drift Swarm Configuration</strong> β Prevent goal drift in multi-agent work</summary>-Complex swarms can drift from their original goals. Claude-Flow V3 includes anti-drift defaults that prevent agents from going off-task.+Complex swarms can drift from their original goals. RuvFlow V3 includes anti-drift defaults that prevent agents from going off-task.**Recommended Configuration:**@@ -388,9 +388,9 @@ swarm_init({</details>-### Claude Code: With vs Without Claude-Flow+### Claude Code: With vs Without RuvFlow-| Capability | Claude Code Alone | Claude Code + Claude-Flow |+| Capability | Claude Code Alone | Claude Code + RuvFlow ||------------|-------------------|---------------------------|| **Agent Collaboration** | Agents work in isolation, no shared context | Agents collaborate via swarms with shared memory and consensus || **Coordination** | Manual orchestration between tasks | Queen-led hierarchy with 5 consensus algorithms (Raft, Byzantine, Gossip) |@@ -475,14 +475,14 @@ curl ... | bash -s -- --full```bash# Quick start (no install needed)-npx claude-flow@alpha init+npx ruvflow@alpha init# Or install globally-npm install -g claude-flow@alpha-claude-flow init+npm install -g ruvflow@alpha+ruvflow init# With Bun (faster)-bunx claude-flow@alpha init+bunx ruvflow@alpha init```#### Install Profiles@@ -494,25 +494,25 @@ bunx claude-flow@alpha init```bash# Minimal install (skip ML/embeddings)-npm install -g claude-flow@alpha --omit=optional+npm install -g ruvflow@alpha --omit=optional```<details><summary>π€ <strong>OpenAI Codex CLI Support</strong> β Full Codex integration with self-learning</summary>-Claude-Flow supports both **Claude Code** and **OpenAI Codex CLI** via the [@claude-flow/codex](https://www.npmjs.com/package/@claude-flow/codex) package, following the [Agentics Foundation](https://agentics.org) standard.+RuvFlow supports both **Claude Code** and **OpenAI Codex CLI** via the [@claude-flow/codex](https://www.npmjs.com/package/@claude-flow/codex) package, following the [Agentics Foundation](https://agentics.org) standard.### Quick Start for Codex```bash# Initialize for Codex CLI (creates AGENTS.md instead of CLAUDE.md)-npx claude-flow@alpha init --codex+npx ruvflow@alpha init --codex# Full Codex setup with all 137+ skills-npx claude-flow@alpha init --codex --full+npx ruvflow@alpha init --codex --full# Initialize for both platforms (dual mode)-npx claude-flow@alpha init --dual+npx ruvflow@alpha init --dual```### Platform Comparison@@ -570,16 +570,16 @@ wait # Wait for all to complete```bash# List collaboration templates-npx claude-flow-codex dual templates+npx ruvflow-codex dual templates# Run feature development swarm (architect β coder β tester β reviewer)-npx claude-flow-codex dual run --template feature --task "Add user auth"+npx ruvflow-codex dual run --template feature --task "Add user auth"# Run security audit swarm (scanner β analyzer β fixer)-npx claude-flow-codex dual run --template security --task "src/auth/"+npx ruvflow-codex dual run --template security --task "src/auth/"# Run refactoring swarm (analyzer β planner β refactorer β validator)-npx claude-flow-codex dual run --template refactor --task "src/legacy/"+npx ruvflow-codex dual run --template refactor --task "src/legacy/"```### Pre-Built Collaboration Templates@@ -599,7 +599,7 @@ When you run `init --codex`, the MCP server is automatically registered:codex mcp list# If not present, add manually:-codex mcp add claude-flow -- npx claude-flow mcp start+codex mcp add ruvflow -- npx ruvflow mcp start```### Self-Learning Workflow@@ -648,43 +648,43 @@ codex mcp add claude-flow -- npx claude-flow mcp start```bash# Initialize project-npx claude-flow@alpha init+npx ruvflow@alpha init# Start MCP server for Claude Code integration-npx claude-flow@alpha mcp start+npx ruvflow@alpha mcp start# Run a task with agents-npx claude-flow@alpha --agent coder --task "Implement user authentication"+npx ruvflow@alpha --agent coder --task "Implement user authentication"# List available agents-npx claude-flow@alpha --list+npx ruvflow@alpha --list```### Upgrading```bash# Update helpers and statusline (preserves your data)-npx claude-flow@v3alpha init upgrade+npx ruvflow@v3alpha init upgrade# Update AND add any missing skills/agents/commands-npx claude-flow@v3alpha init upgrade --add-missing+npx ruvflow@v3alpha init upgrade --add-missing```The `--add-missing` flag automatically detects and installs new skills, agents, and commands that were added in newer versions, without overwriting your existing customizations.### Claude Code MCP Integration-Add claude-flow as an MCP server for seamless integration:+Add ruvflow as an MCP server for seamless integration:```bash-# Add claude-flow MCP server to Claude Code-claude mcp add claude-flow -- npx -y claude-flow@latest mcp start+# Add ruvflow MCP server to Claude Code+claude mcp add ruvflow -- npx -y ruvflow@latest mcp start# Verify installationclaude mcp list```-Once added, Claude Code can use all 175+ claude-flow MCP tools directly:+Once added, Claude Code can use all 175+ ruvflow MCP tools directly:- `swarm_init` - Initialize agent swarms- `agent_spawn` - Spawn specialized agents- `memory_search` - Search patterns with HNSW (150x faster)@@ -695,13 +695,13 @@ Once added, Claude Code can use all 175+ claude-flow MCP tools directly:## What is it exactly? Agents that learn, build and work perpetually.<details>-<summary>π <strong>Why Claude-Flow v3?</strong></summary>+<summary>π <strong>Why RuvFlow v3?</strong></summary>-Claude-Flow v3 introduces **self-learning neural capabilities** that no other agent orchestration framework offers. While competitors require manual agent configuration and static routing, Claude-Flow learns from every task execution, prevents catastrophic forgetting of successful patterns, and intelligently routes work to specialized experts.+RuvFlow v3 introduces **self-learning neural capabilities** that no other agent orchestration framework offers. While competitors require manual agent configuration and static routing, RuvFlow learns from every task execution, prevents catastrophic forgetting of successful patterns, and intelligently routes work to specialized experts.#### π§ Neural & Learning-| Feature | Claude Flow v3 | CrewAI | LangGraph | AutoGen | Manus |+| Feature | RuvFlow v3 | CrewAI | LangGraph | AutoGen | Manus ||---------|----------------|--------|-----------|---------|-------|| **Self-Learning** | β SONA + EWC++ | β | β | β | β || **Prevents Forgetting** | β EWC++ consolidation | β | β | β | β |@@ -712,7 +712,7 @@ Claude-Flow v3 introduces **self-learning neural capabilities** that no other ag#### πΎ Memory & Embeddings-| Feature | Claude Flow v3 | CrewAI | LangGraph | AutoGen | Manus |+| Feature | RuvFlow v3 | CrewAI | LangGraph | AutoGen | Manus ||---------|----------------|--------|-----------|---------|-------|| **Vector Memory** | β HNSW (150x faster) | β | Via plugins | β | β || **PostgreSQL Vector DB** | β RuVector (77+ SQL functions, ~61Β΅s) | β | pgvector only | β | β |@@ -724,7 +724,7 @@ Claude-Flow v3 introduces **self-learning neural capabilities** that no other ag#### π Swarm & Coordination-| Feature | Claude Flow v3 | CrewAI | LangGraph | AutoGen | Manus |+| Feature | RuvFlow v3 | CrewAI | LangGraph | AutoGen | Manus ||---------|----------------|--------|-----------|---------|-------|| **Swarm Topologies** | β 4 types | 1 | 1 | 1 | 1 || **Consensus Protocols** | β 5 (Raft, BFT, etc.) | β | β | β | β |@@ -734,7 +734,7 @@ Claude-Flow v3 introduces **self-learning neural capabilities** that no other ag#### π§ Developer Experience-| Feature | Claude Flow v3 | CrewAI | LangGraph | AutoGen | Manus |+| Feature | RuvFlow v3 | CrewAI | LangGraph | AutoGen | Manus ||---------|----------------|--------|-----------|---------|-------|| **MCP Integration** | β Native (170+ tools) | β | β | β | β || **Skills System** | β 42+ pre-built | β | β | β | Limited |@@ -744,7 +744,7 @@ Claude-Flow v3 introduces **self-learning neural capabilities** that no other ag#### π‘οΈ Security & Platform-| Feature | Claude Flow v3 | CrewAI | LangGraph | AutoGen | Manus |+| Feature | RuvFlow v3 | CrewAI | LangGraph | AutoGen | Manus ||---------|----------------|--------|-----------|---------|-------|| **Threat Detection** | β AIDefence (<10ms) | β | β | β | β || **Cloud Platform** | β Flow Nexus | β | β | β | β |@@ -758,7 +758,7 @@ Claude-Flow v3 introduces **self-learning neural capabilities** that no other ag<details><summary>π <strong>Key Differentiators</strong> β Self-learning, memory optimization, fault tolerance</summary>-What makes Claude-Flow different from other agent frameworks? These 10 capabilities work together to create a system that learns from experience, runs efficiently on any hardware, and keeps working even when things go wrong.+What makes RuvFlow different from other agent frameworks? These 10 capabilities work together to create a system that learns from experience, runs efficiently on any hardware, and keeps working even when things go wrong.| | Feature | What It Does | Technical Details ||---|---------|--------------|-------------------|@@ -778,7 +778,7 @@ What makes Claude-Flow different from other agent frameworks? These 10 capabilit<details><summary>π° <strong>Intelligent 3-Tier Model Routing</strong> β Save 75% on API costs, extend Claude Max 2.5x</summary>-Not every task needs the most powerful (and expensive) model. Claude-Flow analyzes each request and automatically routes it to the cheapest handler that can do the job well. Simple code transforms skip the LLM entirely using WebAssembly. Medium tasks use faster, cheaper models. Only complex architecture decisions use Opus.+Not every task needs the most powerful (and expensive) model. RuvFlow analyzes each request and automatically routes it to the cheapest handler that can do the job well. Simple code transforms skip the LLM entirely using WebAssembly. Medium tasks use faster, cheaper models. Only complex architecture decisions use Opus.**Cost & Usage Benefits:**@@ -804,7 +804,7 @@ Not every task needs the most powerful (and expensive) model. Claude-Flow analyz<details><summary>π <strong>Spec-Driven Development</strong> β Build complete specs, implement without drift</summary>-Complex projects fail when implementation drifts from the original plan. Claude-Flow solves this with a spec-first approach: define your architecture through ADRs (Architecture Decision Records), organize code into DDD bounded contexts, and let the system enforce compliance as agents work. The result is implementations that match specifications β even across multi-agent swarms working in parallel.+Complex projects fail when implementation drifts from the original plan. RuvFlow solves this with a spec-first approach: define your architecture through ADRs (Architecture Decision Records), organize code into DDD bounded contexts, and let the system enforce compliance as agents work. The result is implementations that match specifications β even across multi-agent swarms working in parallel.**How It Prevents Drift:**@@ -1051,18 +1051,18 @@ flowchart TB## π Setup & Configuration-Connect Claude-Flow to your development environment.+Connect RuvFlow to your development environment.<details>-<summary>π <strong>MCP Setup</strong> β Connect Claude-Flow to Any AI Environment</summary>+<summary>π <strong>MCP Setup</strong> β Connect RuvFlow to Any AI Environment</summary>-Claude-Flow runs as an MCP (Model Context Protocol) server, allowing you to connect it to any MCP-compatible AI client. This means you can use Claude-Flow's 60+ agents, swarm coordination, and self-learning capabilities from Claude Desktop, VS Code, Cursor, Windsurf, ChatGPT, and more.+RuvFlow runs as an MCP (Model Context Protocol) server, allowing you to connect it to any MCP-compatible AI client. This means you can use RuvFlow's 60+ agents, swarm coordination, and self-learning capabilities from Claude Desktop, VS Code, Cursor, Windsurf, ChatGPT, and more.### Quick Add Command```bash-# Start Claude-Flow MCP server in any environment-npx claude-flow@v3alpha mcp start+# Start RuvFlow MCP server in any environment+npx ruvflow@v3alpha mcp start```<details open>@@ -1077,9 +1077,9 @@ npx claude-flow@v3alpha mcp start```json{"mcpServers": {- "claude-flow": {+ "ruvflow": {"command": "npx",- "args": ["claude-flow@v3alpha", "mcp", "start"],+ "args": ["ruvflow@v3alpha", "mcp", "start"],"env": {"ANTHROPIC_API_KEY": "sk-ant-..."}@@ -1099,12 +1099,12 @@ Restart Claude Desktop after saving. Look for the MCP indicator (hammer icon) in```bash# Add via CLI (recommended)-claude mcp add claude-flow -- npx claude-flow@v3alpha mcp start+claude mcp add ruvflow -- npx ruvflow@v3alpha mcp start# Or add with environment variables-claude mcp add claude-flow \+claude mcp add ruvflow \--env ANTHROPIC_API_KEY=sk-ant-... \- -- npx claude-flow@v3alpha mcp start+ -- npx ruvflow@v3alpha mcp start# Verify installationclaude mcp list@@ -1131,9 +1131,9 @@ Create `.vscode/mcp.json` in your project:```json{"mcpServers": {- "claude-flow": {+ "ruvflow": {"command": "npx",- "args": ["claude-flow@v3alpha", "mcp", "start"],+ "args": ["ruvflow@v3alpha", "mcp", "start"],"env": {"ANTHROPIC_API_KEY": "sk-ant-..."}@@ -1158,9 +1158,9 @@ Create `.cursor/mcp.json` in your project (or global config):```json{"mcpServers": {- "claude-flow": {+ "ruvflow": {"command": "npx",- "args": ["claude-flow@v3alpha", "mcp", "start"],+ "args": ["ruvflow@v3alpha", "mcp", "start"],"env": {"ANTHROPIC_API_KEY": "sk-ant-..."}@@ -1185,9 +1185,9 @@ Create `.cursor/mcp.json` in your project (or global config):```json{"mcpServers": {- "claude-flow": {+ "ruvflow": {"command": "npx",- "args": ["claude-flow@v3alpha", "mcp", "start"],+ "args": ["ruvflow@v3alpha", "mcp", "start"],"env": {"ANTHROPIC_API_KEY": "sk-ant-..."}@@ -1214,11 +1214,11 @@ Click **Refresh** in the MCP settings to connect. Windsurf supports up to 100 MC**Remote Server Setup:**-For ChatGPT, you need a remote MCP server (not local stdio). Deploy claude-flow to a server with HTTP transport:+For ChatGPT, you need a remote MCP server (not local stdio). Deploy ruvflow to a server with HTTP transport:```bash# Start with HTTP transport-npx claude-flow@v3alpha mcp start --transport http --port 3000+npx ruvflow@v3alpha mcp start --transport http --port 3000```Then add the server URL in ChatGPT Connectors settings.@@ -1234,7 +1234,7 @@ Google AI Studio supports MCP natively since May 2025, with managed MCP servers**Using MCP SuperAssistant Extension:**1. Install [MCP SuperAssistant](https://chrome.google.com/webstore) Chrome extension-2. Configure your claude-flow MCP server+2. Configure your ruvflow MCP server3. Use with Google AI Studio, Gemini, and other AI platforms**Native SDK Integration:**@@ -1247,9 +1247,9 @@ const ai = new GoogleGenAI({ apiKey: 'YOUR_API_KEY' });// MCP definitions are natively supported in the Gen AI SDKconst mcpConfig = {servers: [{- name: 'claude-flow',+ name: 'ruvflow',command: 'npx',- args: ['claude-flow@v3alpha', 'mcp', 'start']+ args: ['ruvflow@v3alpha', 'mcp', 'start']}]};```@@ -1270,9 +1270,9 @@ JetBrains AI Assistant supports MCP for IntelliJ IDEA, PyCharm, WebStorm, and ot```json{- "name": "claude-flow",+ "name": "ruvflow","command": "npx",- "args": ["claude-flow@v3alpha", "mcp", "start"]+ "args": ["ruvflow@v3alpha", "mcp", "start"]}```@@ -1502,13 +1502,13 @@ The Hive Mind system implements queen-led hierarchical coordination where strate**CLI Commands:**```bash-npx claude-flow hive-mind init # Initialize hive mind-npx claude-flow hive-mind spawn "Build API" # Spawn with objective-npx claude-flow hive-mind spawn "..." --queen-type strategic --consensus byzantine-npx claude-flow hive-mind status # Check status-npx claude-flow hive-mind metrics # Performance metrics-npx claude-flow hive-mind memory # Collective memory stats-npx claude-flow hive-mind sessions # List active sessions+npx ruvflow hive-mind init # Initialize hive mind+npx ruvflow hive-mind spawn "Build API" # Spawn with objective+npx ruvflow hive-mind spawn "..." --queen-type strategic --consensus byzantine+npx ruvflow hive-mind status # Check status+npx ruvflow hive-mind metrics # Performance metrics+npx ruvflow hive-mind memory # Collective memory stats+npx ruvflow hive-mind sessions # List active sessions```**Performance:** 10-20x faster batch spawning, 2.8-4.4x speed improvement, 84.8% SWE-Bench solve rate@@ -1522,8 +1522,8 @@ Native integration with Claude Code's experimental Agent Teams feature for spawn**Enable Agent Teams:**```bash-# Automatically enabled with claude-flow init-npx claude-flow@latest init+# Automatically enabled with ruvflow init+npx ruvflow@latest init# Or manually add to .claude/settings.json{@@ -1575,10 +1575,10 @@ TeamDelete()```bash# Handle idle teammate-npx claude-flow@latest hooks teammate-idle --auto-assign true+npx ruvflow@latest hooks teammate-idle --auto-assign true# Handle task completion-npx claude-flow@latest hooks task-completed --task-id <id> --train-patterns+npx ruvflow@latest hooks task-completed --task-id <id> --train-patterns```**Display Modes:** `auto` (default), `in-process`, `tmux` (split-pane)@@ -1655,14 +1655,14 @@ Build custom plugins with the fluent builder API. Create MCP tools, hooks, worke### π¦ Available Optional Plugins-Install these optional plugins to extend Claude Flow capabilities:+Install these optional plugins to extend RuvFlow capabilities:| Plugin | Version | Description | Install Command ||--------|---------|-------------|-----------------|| **@claude-flow/plugin-agentic-qe** | 3.0.0-alpha.2 | Quality Engineering with 58 AI agents across 12 DDD contexts. TDD, coverage analysis, security scanning, chaos engineering, accessibility testing. | `npm install @claude-flow/plugin-agentic-qe` || **@claude-flow/plugin-prime-radiant** | 0.1.4 | Mathematical AI interpretability with 6 engines: sheaf cohomology, spectral analysis, causal inference, quantum topology, category theory, HoTT proofs. | `npm install @claude-flow/plugin-prime-radiant` |-| **@claude-flow/plugin-gastown-bridge** | 0.1.0 | Gas Town orchestrator integration with WASM-accelerated formula parsing (352x faster), Beads sync, convoy management, and graph analysis. 20 MCP tools. | `npx claude-flow@latest plugins install -n @claude-flow/plugin-gastown-bridge` |-| **@claude-flow/teammate-plugin** | 1.0.0-alpha.1 | Native TeammateTool integration for Claude Code v2.1.19+. BMSSP WASM acceleration, rate limiting, circuit breaker, semantic routing. 21 MCP tools. | `npx claude-flow@latest plugins install -n @claude-flow/teammate-plugin` |+| **@claude-flow/plugin-gastown-bridge** | 0.1.0 | Gas Town orchestrator integration with WASM-accelerated formula parsing (352x faster), Beads sync, convoy management, and graph analysis. 20 MCP tools. | `npx ruvflow@latest plugins install -n @claude-flow/plugin-gastown-bridge` |+| **@claude-flow/teammate-plugin** | 1.0.0-alpha.1 | Native TeammateTool integration for Claude Code v2.1.19+. BMSSP WASM acceleration, rate limiting, circuit breaker, semantic routing. 21 MCP tools. | `npx ruvflow@latest plugins install -n @claude-flow/teammate-plugin` |#### π₯ Domain-Specific Plugins@@ -1732,7 +1732,7 @@ npm install @claude-flow/plugin-agentic-qenpm install @claude-flow/plugin-prime-radiant# Install Gas Town Bridge plugin (WASM-accelerated orchestration)-npx claude-flow@latest plugins install -n @claude-flow/plugin-gastown-bridge+npx ruvflow@latest plugins install -n @claude-flow/plugin-gastown-bridge# Install domain-specific pluginsnpm install @claude-flow/plugin-healthcare-clinical@@ -1751,7 +1751,7 @@ npm install @claude-flow/plugin-quantum-optimizernpm install @claude-flow/plugin-hyperbolic-reasoning# List all installed plugins-npx claude-flow plugins list --installed+npx ruvflow plugins list --installed```</details>@@ -1920,8 +1920,8 @@ Workers run automatically based on context, or dispatch manually via MCP tools.| **TestGaps** | `testgaps` | Test coverage analysis | Code changes without tests |```bash-npx claude-flow@v3alpha worker dispatch --trigger audit --context "./src"-npx claude-flow@v3alpha worker status+npx ruvflow@v3alpha worker dispatch --trigger audit --context "./src"+npx ruvflow@v3alpha worker status```</details>@@ -2145,7 +2145,7 @@ npx claude-flow@v3alpha worker status| Feature | Description | Performance ||---------|-------------|-------------|| **Multi-Provider** | Agentic-Flow (ONNX), OpenAI, Transformers.js, Mock | 4 providers |-| **Auto-Install** | `claude-flow embeddings init` or `createEmbeddingServiceAsync()` | Zero config |+| **Auto-Install** | `ruvflow embeddings init` or `createEmbeddingServiceAsync()` | Zero config || **75x Faster** | Agentic-flow ONNX SIMD vs Transformers.js | 3ms vs 230ms || **Hyperbolic Space** | PoincarΓ© ball model for hierarchical data | Exponential capacity || **Dimensions** | 384 to 3072 configurable | Quality vs speed tradeoff |@@ -2155,13 +2155,13 @@ npx claude-flow@v3alpha worker status```bash# Initialize ONNX embeddings with hyperbolic config-claude-flow embeddings init+ruvflow embeddings init# Use larger model for higher quality-claude-flow embeddings init --model all-mpnet-base-v2+ruvflow embeddings init --model all-mpnet-base-v2# Semantic search-claude-flow embeddings search -q "authentication patterns"+ruvflow embeddings search -q "authentication patterns"```| Mode | Adaptation | Quality | Memory | Use Case |@@ -2198,22 +2198,22 @@ claude-flow embeddings search -q "authentication patterns"```bash# Initialize RuVector in PostgreSQL-claude-flow ruvector init --database mydb --user admin+ruvflow ruvector init --database mydb --user admin# Check connection and schema status-claude-flow ruvector status --verbose+ruvflow ruvector status --verbose# Run pending migrations-claude-flow ruvector migrate --up+ruvflow ruvector migrate --up# Performance benchmark-claude-flow ruvector benchmark --iterations 1000+ruvflow ruvector benchmark --iterations 1000# Optimize indices and vacuum-claude-flow ruvector optimize --analyze+ruvflow ruvector optimize --analyze# Backup vector data-claude-flow ruvector backup --output ./backup.sql+ruvflow ruvector backup --output ./backup.sql```| Migration | Purpose | Features |@@ -2245,13 +2245,13 @@ claude-flow ruvector backup --output ./backup.sql**Quick Commands:**```bash-npx claude-flow hive-mind init # Initialize-npx claude-flow hive-mind spawn "Build API" --queen-type tactical # Spawn swarm-npx claude-flow hive-mind spawn "Research AI" --consensus byzantine --claude-npx claude-flow hive-mind status # Check status+npx ruvflow hive-mind init # Initialize+npx ruvflow hive-mind spawn "Build API" --queen-type tactical # Spawn swarm+npx ruvflow hive-mind spawn "Research AI" --consensus byzantine --claude+npx ruvflow hive-mind status # Check status```-**Claude-Flow Skill:** `/hive-mind-advanced` β Full hive mind orchestration+**RuvFlow Skill:** `/hive-mind-advanced` β Full hive mind orchestration**Performance:** 10-20x faster batch spawning, 84.8% SWE-Bench solve rate, 32.3% token reduction@@ -2363,7 +2363,7 @@ Real-time development status display for Claude Code integration showing DDD pro**Output Format:**```-β Claude Flow V3 β ruvnet β β v3 β Opus 4.5+β RuvFlow V3 β ruvnet β β v3 β Opus 4.5βββββββββββββββββββββββββββββββββββββββββββββββββββββποΈ DDD Domains [βββββ] 5/5 β‘ 1.0x β 2.49x-7.47xπ€ Swarm β [58/15] π₯ 0 π’ CVE 3/3 πΎ 22282MB π 47% π§ 10%@@ -2372,7 +2372,7 @@ Real-time development status display for Claude Code integration showing DDD pro| Indicator | Description | Values ||-----------|-------------|--------|-| `β Claude Flow V3` | Project header | Always shown |+| `β RuvFlow V3` | Project header | Always shown || `β ruvnet` | GitHub user (via `gh` CLI) | Dynamic || `β v3` | Current git branch | Dynamic || `Opus 4.5` | Claude model name | From Claude Code |@@ -2393,19 +2393,19 @@ Real-time development status display for Claude Code integration showing DDD pro**Usage:**```bash# Default: Safe multi-line (avoids Claude Code collision zone)-npx claude-flow@v3alpha hooks statusline+npx ruvflow@v3alpha hooks statusline# Single-line mode (completely avoids collision)-npx claude-flow@v3alpha hooks statusline --single+npx ruvflow@v3alpha hooks statusline --single# Legacy multi-line (original behavior, may have bleeding)-npx claude-flow@v3alpha hooks statusline --legacy+npx ruvflow@v3alpha hooks statusline --legacy# JSON output for scripting-npx claude-flow@v3alpha hooks statusline --json+npx ruvflow@v3alpha hooks statusline --json# Compact JSON (single line)-npx claude-flow@v3alpha hooks statusline --compact+npx ruvflow@v3alpha hooks statusline --compact```**Collision Zone Fix (Issue #985):**@@ -2427,16 +2427,16 @@ Add to `.claude/settings.json`:{"statusLine": {"type": "command",- "command": "npx claude-flow@v3alpha hooks statusline --single"+ "command": "npx ruvflow@v3alpha hooks statusline --single"}}```**Data Sources:**-- `.claude-flow/metrics/v3-progress.json` - DDD domain progress-- `.claude-flow/metrics/swarm-activity.json` - Active agent counts-- `.claude-flow/security/audit-status.json` - CVE remediation status-- `.claude-flow/learning/patterns.db` - Intelligence score (pattern count)+- `.ruvflow/metrics/v3-progress.json` - DDD domain progress+- `.ruvflow/metrics/swarm-activity.json` - Active agent counts+- `.ruvflow/security/audit-status.json` - CVE remediation status+- `.ruvflow/learning/patterns.db` - Intelligence score (pattern count)- Process detection via `ps aux` - Real-time memory and agent counts- Git branch via `git branch --show-current`- GitHub user via `gh api user`@@ -2461,19 +2461,19 @@ Cross-platform TypeScript-based daemon service with auto-scheduling:**Commands:**```bash# Start daemon (auto-runs on SessionStart hooks)-npx claude-flow@v3alpha daemon start+npx ruvflow@v3alpha daemon start# Check status with worker history-npx claude-flow@v3alpha daemon status+npx ruvflow@v3alpha daemon status# Manually trigger a worker-npx claude-flow@v3alpha daemon trigger map+npx ruvflow@v3alpha daemon trigger map# Enable/disable workers-npx claude-flow@v3alpha daemon enable map audit optimize+npx ruvflow@v3alpha daemon enable map audit optimize# Stop daemon-npx claude-flow@v3alpha daemon stop+npx ruvflow@v3alpha daemon stop```**Daemon Status Output:**@@ -2547,7 +2547,7 @@ Shell-based daemons for monitoring (Linux/macOS only):<details><summary>β¨οΈ <strong>V3 CLI Commands</strong> β 26 commands with 140+ subcommands</summary>-Complete command-line interface for all Claude-Flow operations.+Complete command-line interface for all RuvFlow operations.**Core Commands:**@@ -2589,25 +2589,25 @@ Complete command-line interface for all Claude-Flow operations.```bash# Initialize project with wizard-npx claude-flow@v3alpha init --wizard+npx ruvflow@v3alpha init --wizard# Start daemon with background workers-npx claude-flow@v3alpha daemon start+npx ruvflow@v3alpha daemon start# Spawn an agent with specific type-npx claude-flow@v3alpha agent spawn -t coder --name my-coder+npx ruvflow@v3alpha agent spawn -t coder --name my-coder# Initialize swarm with V3 mode-npx claude-flow@v3alpha swarm init --v3-mode+npx ruvflow@v3alpha swarm init --v3-mode# Search memory (HNSW-indexed, 150x faster)-npx claude-flow@v3alpha memory search -q "authentication patterns"+npx ruvflow@v3alpha memory search -q "authentication patterns"# Run security scan-npx claude-flow@v3alpha security scan --depth full+npx ruvflow@v3alpha security scan --depth full# Performance benchmark-npx claude-flow@v3alpha performance benchmark --suite all+npx ruvflow@v3alpha performance benchmark --suite all```</details>@@ -2615,7 +2615,7 @@ npx claude-flow@v3alpha performance benchmark --suite all<details><summary>π©Ί <strong>Doctor Health Checks</strong> β System diagnostics with auto-fix</summary>-Run `npx claude-flow@v3alpha doctor` to diagnose and fix common issues.+Run `npx ruvflow@v3alpha doctor` to diagnose and fix common issues.**Health Checks Performed:**@@ -2636,22 +2636,22 @@ Run `npx claude-flow@v3alpha doctor` to diagnose and fix common issues.```bash# Run full diagnostics-npx claude-flow@v3alpha doctor+npx ruvflow@v3alpha doctor# Run diagnostics with auto-fix-npx claude-flow@v3alpha doctor --fix+npx ruvflow@v3alpha doctor --fix# Check specific component-npx claude-flow@v3alpha doctor --component memory+npx ruvflow@v3alpha doctor --component memory# Verbose output-npx claude-flow@v3alpha doctor --verbose+npx ruvflow@v3alpha doctor --verbose```**Output Example:**```-π©Ί Claude-Flow Doctor v3.0.0-alpha+π©Ί RuvFlow Doctor v3.0.0-alphaβ Node.js 20.11.0 (required: 20+)β npm 10.2.4 (required: 9+)@@ -2695,16 +2695,16 @@ The embeddings package (v3.0.0-alpha.12) provides high-performance vector embedd```bash# Initialize embeddings system-npx claude-flow@v3alpha embeddings init+npx ruvflow@v3alpha embeddings init# Generate embedding for text-npx claude-flow@v3alpha embeddings embed "authentication patterns"+npx ruvflow@v3alpha embeddings embed "authentication patterns"# Batch embed multiple texts-npx claude-flow@v3alpha embeddings batch --file texts.txt+npx ruvflow@v3alpha embeddings batch --file texts.txt# Search with semantic similarity-npx claude-flow@v3alpha embeddings search "login flow" --top-k 5+npx ruvflow@v3alpha embeddings search "login flow" --top-k 5```**Programmatic:**@@ -2741,59 +2741,59 @@ Real-world scenarios and pre-built workflows for common tasks.| Scenario | What It Solves | How To Do It ||----------|----------------|--------------|-| **Code Review** | Get thorough reviews with security, performance, and style checks | `npx claude-flow@v3alpha --agent reviewer --task "Review PR #123"` |-| **Test Generation** | Auto-generate unit, integration, and e2e tests for existing code | `npx claude-flow@v3alpha --agent tester --task "Write tests for auth module"` |-| **Refactoring** | Safely restructure code while maintaining behavior | `npx claude-flow@v3alpha --agent coder --task "Refactor user service to use repository pattern"` |-| **Bug Fixing** | Diagnose and fix bugs with full context analysis | `npx claude-flow@v3alpha --agent coder --task "Fix race condition in checkout flow"` |+| **Code Review** | Get thorough reviews with security, performance, and style checks | `npx ruvflow@v3alpha --agent reviewer --task "Review PR #123"` |+| **Test Generation** | Auto-generate unit, integration, and e2e tests for existing code | `npx ruvflow@v3alpha --agent tester --task "Write tests for auth module"` |+| **Refactoring** | Safely restructure code while maintaining behavior | `npx ruvflow@v3alpha --agent coder --task "Refactor user service to use repository pattern"` |+| **Bug Fixing** | Diagnose and fix bugs with full context analysis | `npx ruvflow@v3alpha --agent coder --task "Fix race condition in checkout flow"` |### π Security & Compliance| Scenario | What It Solves | How To Do It ||----------|----------------|--------------|-| **Security Audit** | Find vulnerabilities before attackers do | `npx claude-flow@v3alpha --agent security-architect --task "Audit for OWASP Top 10"` |-| **Dependency Scan** | Identify vulnerable packages and suggest upgrades | `npx claude-flow@v3alpha security scan --depth full` |-| **Compliance Check** | Ensure code meets security standards | `npx claude-flow@v3alpha --agent security-architect --task "Check PCI-DSS compliance"` |+| **Security Audit** | Find vulnerabilities before attackers do | `npx ruvflow@v3alpha --agent security-architect --task "Audit for OWASP Top 10"` |+| **Dependency Scan** | Identify vulnerable packages and suggest upgrades | `npx ruvflow@v3alpha security scan --depth full` |+| **Compliance Check** | Ensure code meets security standards | `npx ruvflow@v3alpha --agent security-architect --task "Check PCI-DSS compliance"` |### π Multi-Agent Swarms| Scenario | What It Solves | How To Do It ||----------|----------------|--------------|-| **Feature Development** | Coordinate multiple agents on complex features | `npx claude-flow@v3alpha swarm init --topology hierarchical && npx claude-flow@v3alpha task orchestrate "Build user dashboard"` |-| **Large Refactors** | Parallel refactoring across many files without conflicts | `npx claude-flow@v3alpha swarm init --topology mesh --max-agents 8` |-| **Codebase Migration** | Migrate frameworks, languages, or patterns systematically | `npx claude-flow@v3alpha task orchestrate "Migrate from Express to Fastify" --strategy adaptive` |+| **Feature Development** | Coordinate multiple agents on complex features | `npx ruvflow@v3alpha swarm init --topology hierarchical && npx ruvflow@v3alpha task orchestrate "Build user dashboard"` |+| **Large Refactors** | Parallel refactoring across many files without conflicts | `npx ruvflow@v3alpha swarm init --topology mesh --max-agents 8` |+| **Codebase Migration** | Migrate frameworks, languages, or patterns systematically | `npx ruvflow@v3alpha task orchestrate "Migrate from Express to Fastify" --strategy adaptive` |### π Performance & Optimization| Scenario | What It Solves | How To Do It ||----------|----------------|--------------|-| **Performance Profiling** | Find and fix bottlenecks in your application | `npx claude-flow@v3alpha --agent perf-analyzer --task "Profile API endpoints"` |-| **Query Optimization** | Speed up slow database queries | `npx claude-flow@v3alpha hooks route "Optimize database queries"` |-| **Memory Analysis** | Reduce memory usage and fix leaks | `npx claude-flow@v3alpha --agent perf-analyzer --task "Analyze memory usage patterns"` |+| **Performance Profiling** | Find and fix bottlenecks in your application | `npx ruvflow@v3alpha --agent perf-analyzer --task "Profile API endpoints"` |+| **Query Optimization** | Speed up slow database queries | `npx ruvflow@v3alpha hooks route "Optimize database queries"` |+| **Memory Analysis** | Reduce memory usage and fix leaks | `npx ruvflow@v3alpha --agent perf-analyzer --task "Analyze memory usage patterns"` |### π GitHub & DevOps| Scenario | What It Solves | How To Do It ||----------|----------------|--------------|-| **PR Management** | Review, approve, and merge PRs efficiently | `npx claude-flow@v3alpha --agent pr-manager --task "Review open PRs"` |-| **Issue Triage** | Categorize, prioritize, and assign issues automatically | `npx claude-flow@v3alpha --agent issue-tracker --task "Triage new issues"` |-| **Release Management** | Coordinate releases with changelogs and versioning | `npx claude-flow@v3alpha --agent release-manager --task "Prepare v2.0 release"` |-| **CI/CD Optimization** | Speed up pipelines and reduce flaky tests | `npx claude-flow@v3alpha --agent cicd-engineer --task "Optimize GitHub Actions workflow"` |+| **PR Management** | Review, approve, and merge PRs efficiently | `npx ruvflow@v3alpha --agent pr-manager --task "Review open PRs"` |+| **Issue Triage** | Categorize, prioritize, and assign issues automatically | `npx ruvflow@v3alpha --agent issue-tracker --task "Triage new issues"` |+| **Release Management** | Coordinate releases with changelogs and versioning | `npx ruvflow@v3alpha --agent release-manager --task "Prepare v2.0 release"` |+| **CI/CD Optimization** | Speed up pipelines and reduce flaky tests | `npx ruvflow@v3alpha --agent cicd-engineer --task "Optimize GitHub Actions workflow"` |### π Spec-Driven Development| Scenario | What It Solves | How To Do It ||----------|----------------|--------------|-| **Generate Specs** | Create complete specifications before coding | `npx claude-flow@v3alpha --agent architect --task "Create ADR for authentication system"` |-| **Validate Implementation** | Ensure code matches specifications | `npx claude-flow@v3alpha hooks progress --detailed` |-| **Track Compliance** | Monitor spec adherence across the team | `npx claude-flow@v3alpha progress sync` |+| **Generate Specs** | Create complete specifications before coding | `npx ruvflow@v3alpha --agent architect --task "Create ADR for authentication system"` |+| **Validate Implementation** | Ensure code matches specifications | `npx ruvflow@v3alpha hooks progress --detailed` |+| **Track Compliance** | Monitor spec adherence across the team | `npx ruvflow@v3alpha progress sync` |### π§ Learning & Intelligence| Scenario | What It Solves | How To Do It ||----------|----------------|--------------|-| **Bootstrap Intelligence** | Train the system on your codebase patterns | `npx claude-flow@v3alpha hooks pretrain --depth deep` |-| **Optimize Routing** | Improve task-to-agent matching over time | `npx claude-flow@v3alpha hooks route "<task>" --include-explanation` |-| **Transfer Learning** | Apply patterns learned from other projects | `npx claude-flow@v3alpha hooks transfer <sourceProject>` |+| **Bootstrap Intelligence** | Train the system on your codebase patterns | `npx ruvflow@v3alpha hooks pretrain --depth deep` |+| **Optimize Routing** | Improve task-to-agent matching over time | `npx ruvflow@v3alpha hooks route "<task>" --include-explanation` |+| **Transfer Learning** | Apply patterns learned from other projects | `npx ruvflow@v3alpha hooks transfer <sourceProject>` |</details>@@ -2851,7 +2851,7 @@ When hooks run, they emit signals that guide routing decisions. Watch for these**Example Hook Output:**```bash-$ npx claude-flow@v3alpha hooks pre-task --description "convert var to const in utils.ts"+$ npx ruvflow@v3alpha hooks pre-task --description "convert var to const in utils.ts"[AGENT_BOOSTER_AVAILABLE] Intent: var-to-constRecommendation: Use Edit tool directly@@ -2874,8 +2874,8 @@ Cost: $0```bash# Example: Edit with pattern learning-npx claude-flow@v3alpha hooks pre-edit ./src/auth.ts-npx claude-flow@v3alpha hooks post-edit ./src/auth.ts --success true --train-patterns+npx ruvflow@v3alpha hooks pre-edit ./src/auth.ts+npx ruvflow@v3alpha hooks post-edit ./src/auth.ts --success true --train-patterns```#### π§ Intelligence & Routing Hooks (8 hooks)@@ -2893,10 +2893,10 @@ npx claude-flow@v3alpha hooks post-edit ./src/auth.ts --success true --train-pat```bash# Route a task with explanation-npx claude-flow@v3alpha hooks route "refactor authentication to use JWT" --include-explanation+npx ruvflow@v3alpha hooks route "refactor authentication to use JWT" --include-explanation# Bootstrap intelligence from your codebase-npx claude-flow@v3alpha hooks pretrain --depth deep --model-type moe+npx ruvflow@v3alpha hooks pretrain --depth deep --model-type moe```#### π Session Management Hooks (4 hooks)@@ -2910,10 +2910,10 @@ npx claude-flow@v3alpha hooks pretrain --depth deep --model-type moe```bash# Start session with auto-daemon-npx claude-flow@v3alpha hooks session-start --session-id "feature-auth" --start-daemon+npx ruvflow@v3alpha hooks session-start --session-id "feature-auth" --start-daemon# End session and export learnings-npx claude-flow@v3alpha hooks session-end --export-metrics --persist-patterns+npx ruvflow@v3alpha hooks session-end --export-metrics --persist-patterns```#### π€ Intelligence System Hooks (9 hooks)@@ -2932,13 +2932,13 @@ npx claude-flow@v3alpha hooks session-end --export-metrics --persist-patterns```bash# Start trajectory for complex task-npx claude-flow@v3alpha hooks intelligence trajectory-start --task "implement OAuth2"+npx ruvflow@v3alpha hooks intelligence trajectory-start --task "implement OAuth2"# Record successful action-npx claude-flow@v3alpha hooks intelligence trajectory-step --action "created token service" --quality 0.9+npx ruvflow@v3alpha hooks intelligence trajectory-step --action "created token service" --quality 0.9# End trajectory and trigger learning-npx claude-flow@v3alpha hooks intelligence trajectory-end --success true+npx ruvflow@v3alpha hooks intelligence trajectory-end --success true```### 12 Background Workers (Auto-Triggered)@@ -2962,13 +2962,13 @@ Workers run automatically based on context, or dispatch manually.```bash# List all workers-npx claude-flow@v3alpha hooks worker list+npx ruvflow@v3alpha hooks worker list# Manually dispatch security audit-npx claude-flow@v3alpha hooks worker dispatch --trigger audit --context "./src/auth"+npx ruvflow@v3alpha hooks worker dispatch --trigger audit --context "./src/auth"# Check worker status-npx claude-flow@v3alpha hooks worker status+npx ruvflow@v3alpha hooks worker status```### Model Routing Hooks (3 hooks)@@ -2983,10 +2983,10 @@ Automatically selects haiku/sonnet/opus based on task complexity.```bash# Get model recommendation-npx claude-flow@v3alpha hooks model-route --task "fix typo in README"+npx ruvflow@v3alpha hooks model-route --task "fix typo in README"# β Recommends: haiku (simple task, low complexity)-npx claude-flow@v3alpha hooks model-route --task "design distributed consensus system"+npx ruvflow@v3alpha hooks model-route --task "design distributed consensus system"# β Recommends: opus (complex architecture, high reasoning)```@@ -3007,21 +3007,21 @@ npx claude-flow@v3alpha hooks model-route --task "design distributed consensus s# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ# Route task to best agent-npx claude-flow@v3alpha hooks route "<task>" --include-explanation+npx ruvflow@v3alpha hooks route "<task>" --include-explanation# Start/end session with learning-npx claude-flow@v3alpha hooks session-start --start-daemon-npx claude-flow@v3alpha hooks session-end --persist-patterns+npx ruvflow@v3alpha hooks session-start --start-daemon+npx ruvflow@v3alpha hooks session-end --persist-patterns# View what the system has learned-npx claude-flow@v3alpha hooks metrics-npx claude-flow@v3alpha hooks intelligence stats+npx ruvflow@v3alpha hooks metrics+npx ruvflow@v3alpha hooks intelligence stats# Bootstrap on new project-npx claude-flow@v3alpha hooks pretrain --depth deep+npx ruvflow@v3alpha hooks pretrain --depth deep# Dispatch background worker-npx claude-flow@v3alpha hooks worker dispatch --trigger audit+npx ruvflow@v3alpha hooks worker dispatch --trigger audit```</details>@@ -3047,38 +3047,38 @@ Share learned patterns across projects, teams, and the community via the decentr```bash# Export learned patterns to file-npx claude-flow@v3alpha memory export --format json --output ./patterns.json+npx ruvflow@v3alpha memory export --format json --output ./patterns.json# Export specific namespace-npx claude-flow@v3alpha memory export --namespace "security" --output ./security-patterns.json+npx ruvflow@v3alpha memory export --namespace "security" --output ./security-patterns.json# Export with embeddings (larger file, faster import)-npx claude-flow@v3alpha memory export --include-embeddings --output ./full-export.json+npx ruvflow@v3alpha memory export --include-embeddings --output ./full-export.json# Export agent configurations-npx claude-flow@v3alpha config export --scope project --output ./agent-configs.json+npx ruvflow@v3alpha config export --scope project --output ./agent-configs.json# Export session state-npx claude-flow@v3alpha session export --session-id "my-session" --output ./session.json+npx ruvflow@v3alpha session export --session-id "my-session" --output ./session.json```### Import Commands```bash# Import patterns from file-npx claude-flow@v3alpha memory import --input ./patterns.json+npx ruvflow@v3alpha memory import --input ./patterns.json# Import and merge with existing (don't overwrite)-npx claude-flow@v3alpha memory import --input ./patterns.json --merge+npx ruvflow@v3alpha memory import --input ./patterns.json --merge# Import from another project-npx claude-flow@v3alpha hooks transfer --source-path ../other-project+npx ruvflow@v3alpha hooks transfer --source-path ../other-project# Import agent configurations-npx claude-flow@v3alpha config import --input ./agent-configs.json --scope project+npx ruvflow@v3alpha config import --input ./agent-configs.json --scope project# Restore session-npx claude-flow@v3alpha session restore --session-id "my-session"+npx ruvflow@v3alpha session restore --session-id "my-session"```### Pattern Store (IPFS Marketplace)@@ -3096,13 +3096,13 @@ Decentralized pattern marketplace for sharing and discovering community patterns```bash# Search for authentication patterns-npx claude-flow@v3alpha transfer-store search --query "authentication" --min-rating 4.0+npx ruvflow@v3alpha transfer-store search --query "authentication" --min-rating 4.0# Download a pattern-npx claude-flow@v3alpha transfer-store download --id "auth-jwt-patterns-v2" --verify+npx ruvflow@v3alpha transfer-store download --id "auth-jwt-patterns-v2" --verify# Publish your patterns-npx claude-flow@v3alpha transfer-store publish --input ./my-patterns.json --category "security"+npx ruvflow@v3alpha transfer-store publish --input ./my-patterns.json --category "security"```### Plugin Store@@ -3120,22 +3120,22 @@ Discover and install community plugins from the **live IPFS registry** with 19 o```bash# List plugins with live ratings from Cloud Function-npx claude-flow@v3alpha plugins list+npx ruvflow@v3alpha plugins list# Filter by type-npx claude-flow@v3alpha plugins list --type integration+npx ruvflow@v3alpha plugins list --type integration# Rate a plugin-npx claude-flow@v3alpha plugins rate --name @claude-flow/embeddings --rating 5+npx ruvflow@v3alpha plugins rate --name @claude-flow/embeddings --rating 5# Search for MCP tool plugins-npx claude-flow@v3alpha transfer plugin-search --type "mcp-tool" --verified+npx ruvflow@v3alpha transfer plugin-search --type "mcp-tool" --verified# Get plugin info-npx claude-flow@v3alpha transfer plugin-info --name "semantic-code-search"+npx ruvflow@v3alpha transfer plugin-info --name "semantic-code-search"# List official plugins-npx claude-flow@v3alpha transfer plugin-official+npx ruvflow@v3alpha transfer plugin-official```#### Live IPFS Plugin Registry@@ -3168,10 +3168,10 @@ Patterns and models are distributed via IPFS for decentralization and integrity.```bash# Resolve IPNS name to CID-npx claude-flow@v3alpha transfer ipfs-resolve --name "/ipns/patterns.claude-flow.io"+npx ruvflow@v3alpha transfer ipfs-resolve --name "/ipns/patterns.ruvflow.io"# Detect PII before publishing-npx claude-flow@v3alpha transfer detect-pii --content "$(cat ./patterns.json)"+npx ruvflow@v3alpha transfer detect-pii --content "$(cat ./patterns.json)"```### Model & Learning Pattern Import/Export@@ -3194,7 +3194,7 @@ curl -X POST "https://api.pinata.cloud/pinning/pinJSONToIPFS" \"name": "my-patterns","patterns": [...]},- "pinataMetadata": {"name": "claude-flow-learning-pattern"}+ "pinataMetadata": {"name": "ruvflow-learning-pattern"}}'# Import a pattern from IPFS CID@@ -3236,13 +3236,13 @@ Import pre-trained learning patterns for common tasks. **90.5% average accuracy*curl -s "https://gateway.pinata.cloud/ipfs/QmNr1yYMKi7YBaL8JSztQyuB5ZUaTdRMLxJC1pBpGbjsTc" | jq '.models[].name'# Import all models-npx claude-flow@v3alpha transfer import --cid QmNr1yYMKi7YBaL8JSztQyuB5ZUaTdRMLxJC1pBpGbjsTc+npx ruvflow@v3alpha transfer import --cid QmNr1yYMKi7YBaL8JSztQyuB5ZUaTdRMLxJC1pBpGbjsTc# Import specific category-npx claude-flow@v3alpha neural import --model security-review-patterns --source ipfs+npx ruvflow@v3alpha neural import --model security-review-patterns --source ipfs# Use patterns in routing-npx claude-flow@v3alpha hooks route --task "review authentication code" --use-patterns+npx ruvflow@v3alpha hooks route --task "review authentication code" --use-patterns```#### Benefits vs Fresh Install@@ -3267,7 +3267,7 @@ npx claude-flow@v3alpha hooks route --task "review authentication code" --use-pa```bash# Install a pattern pack-npx claude-flow@v3alpha transfer-store download --id "security-essentials" --apply+npx ruvflow@v3alpha transfer-store download --id "security-essentials" --apply```### RuVector WASM Neural Training@@ -3285,25 +3285,25 @@ Real WASM-accelerated neural training using `@ruvector/learning-wasm` and `@ruve```bash# List available pre-trained models from IPFS registry-npx claude-flow@v3alpha neural list+npx ruvflow@v3alpha neural list# List models by category-npx claude-flow@v3alpha neural list --category security+npx ruvflow@v3alpha neural list --category security# Train with WASM acceleration-npx claude-flow@v3alpha neural train -p coordination -e 100 --wasm --flash --contrastive+npx ruvflow@v3alpha neural train -p coordination -e 100 --wasm --flash --contrastive# Train security patterns-npx claude-flow@v3alpha neural train -p security --wasm --contrastive+npx ruvflow@v3alpha neural train -p security --wasm --contrastive# Benchmark WASM performance-npx claude-flow@v3alpha neural benchmark -d 256 -i 1000+npx ruvflow@v3alpha neural benchmark -d 256 -i 1000# Import pre-trained models-npx claude-flow@v3alpha neural import --cid QmNr1yYMKi7YBaL8JSztQyuB5ZUaTdRMLxJC1pBpGbjsTc+npx ruvflow@v3alpha neural import --cid QmNr1yYMKi7YBaL8JSztQyuB5ZUaTdRMLxJC1pBpGbjsTc# Export trained patterns to IPFS-npx claude-flow@v3alpha neural export --ipfs --sign+npx ruvflow@v3alpha neural export --ipfs --sign```#### Benchmark Results@@ -3642,9 +3642,9 @@ Skills are **reusable workflows** that combine agents, hooks, and patterns into/v3-security-overhaul# Via CLI-npx claude-flow@v3alpha skill run github-code-review-npx claude-flow@v3alpha skill list-npx claude-flow@v3alpha skill info sparc-methodology+npx ruvflow@v3alpha skill run github-code-review+npx ruvflow@v3alpha skill list+npx ruvflow@v3alpha skill info sparc-methodology```### Creating Custom Skills@@ -3701,21 +3701,21 @@ The Claims system manages **who is working on what** β whether human or agent.| Command | What It Does | Example ||---------|--------------|---------|-| `issues list` | See all issues and their status | `npx claude-flow@v3alpha issues list` |-| `issues claim` | Claim an issue for yourself/agent | `npx claude-flow@v3alpha issues claim #123 --as coder-1` |-| `issues release` | Release your claim | `npx claude-flow@v3alpha issues release #123` |-| `issues handoff` | Hand off to another worker | `npx claude-flow@v3alpha issues handoff #123 --to reviewer` |-| `issues status` | Update progress on claimed work | `npx claude-flow@v3alpha issues status #123 --progress 75` |-| `issues stealable` | List abandoned/stuck issues | `npx claude-flow@v3alpha issues stealable` |-| `issues steal` | Take over stealable issue | `npx claude-flow@v3alpha issues steal #123` |-| `issues load` | View agent workloads | `npx claude-flow@v3alpha issues load` |-| `issues rebalance` | Redistribute work evenly | `npx claude-flow@v3alpha issues rebalance --dry-run` |-| `issues board` | Visual board view | `npx claude-flow@v3alpha issues board` |+| `issues list` | See all issues and their status | `npx ruvflow@v3alpha issues list` |+| `issues claim` | Claim an issue for yourself/agent | `npx ruvflow@v3alpha issues claim #123 --as coder-1` |+| `issues release` | Release your claim | `npx ruvflow@v3alpha issues release #123` |+| `issues handoff` | Hand off to another worker | `npx ruvflow@v3alpha issues handoff #123 --to reviewer` |+| `issues status` | Update progress on claimed work | `npx ruvflow@v3alpha issues status #123 --progress 75` |+| `issues stealable` | List abandoned/stuck issues | `npx ruvflow@v3alpha issues stealable` |+| `issues steal` | Take over stealable issue | `npx ruvflow@v3alpha issues steal #123` |+| `issues load` | View agent workloads | `npx ruvflow@v3alpha issues load` |+| `issues rebalance` | Redistribute work evenly | `npx ruvflow@v3alpha issues rebalance --dry-run` |+| `issues board` | Visual board view | `npx ruvflow@v3alpha issues board` |### Visual Board View```bash-npx claude-flow@v3alpha issues board+npx ruvflow@v3alpha issues board``````@@ -3737,13 +3737,13 @@ When you need to pass work to someone else:```bash# 1. Request handoff with context-npx claude-flow@v3alpha issues handoff #123 \+npx ruvflow@v3alpha issues handoff #123 \--to security-architect \--reason "Needs security review" \--progress 80# 2. Target accepts handoff-npx claude-flow@v3alpha issues accept #123 --as security-architect+npx ruvflow@v3alpha issues accept #123 --as security-architect# 3. Work continues with full context```@@ -3752,7 +3752,7 @@ npx claude-flow@v3alpha issues accept #123 --as security-architect```bash# View current load-npx claude-flow@v3alpha issues load+npx ruvflow@v3alpha issues load# Output:# Agent | Claims | Load | Status@@ -3763,7 +3763,7 @@ npx claude-flow@v3alpha issues load# security-arch | 0 | 0% | π’ Available# Auto-rebalance-npx claude-flow@v3alpha issues rebalance+npx ruvflow@v3alpha issues rebalance```### MCP Tools@@ -3824,14 +3824,14 @@ The Route system uses **Q-Learning** to automatically assign tasks to the best a| Command | What It Does | Example ||---------|--------------|---------|-| `route task` | Get agent recommendation | `npx claude-flow@v3alpha route task "implement OAuth2"` |-| `route explain` | Understand routing decision | `npx claude-flow@v3alpha route explain "task"` |-| `route coverage` | Route based on test coverage | `npx claude-flow@v3alpha route coverage` |+| `route task` | Get agent recommendation | `npx ruvflow@v3alpha route task "implement OAuth2"` |+| `route explain` | Understand routing decision | `npx ruvflow@v3alpha route explain "task"` |+| `route coverage` | Route based on test coverage | `npx ruvflow@v3alpha route coverage` |### Example: Route a Task```bash-npx claude-flow@v3alpha route task "refactor authentication to use JWT"+npx ruvflow@v3alpha route task "refactor authentication to use JWT"# Output:# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ@@ -3858,7 +3858,7 @@ npx claude-flow@v3alpha route task "refactor authentication to use JWT"Routes tasks to agents based on **test coverage gaps**:```bash-npx claude-flow@v3alpha route coverage+npx ruvflow@v3alpha route coverage# Finds untested code and routes to tester agent:# β’ src/auth/jwt.ts - 23% coverage β tester@@ -3870,10 +3870,10 @@ npx claude-flow@v3alpha route coverage```bash# Route via hooks (preferred)-npx claude-flow@v3alpha hooks route "implement caching layer" --include-explanation+npx ruvflow@v3alpha hooks route "implement caching layer" --include-explanation# Record outcome for learning-npx claude-flow@v3alpha hooks post-task --task-id "task-123" --success true --agent coder+npx ruvflow@v3alpha hooks post-task --task-id "task-123" --success true --agent coder```### How Q-Learning Improves Over Time@@ -3893,12 +3893,12 @@ The system **remembers** what works and applies it to future similar tasks.## π» Programmatic Usage-Use Claude-Flow packages directly in your applications.+Use RuvFlow packages directly in your applications.<details>-<summary>π» <strong>Programmatic SDK</strong> β Use Claude-Flow in Your Code</summary>+<summary>π» <strong>Programmatic SDK</strong> β Use RuvFlow in Your Code</summary>-Use Claude-Flow packages directly in your TypeScript/JavaScript applications.+Use RuvFlow packages directly in your TypeScript/JavaScript applications.### Installation@@ -3907,7 +3907,7 @@ Use Claude-Flow packages directly in your TypeScript/JavaScript applications.npm install @claude-flow/cli @claude-flow/memory @claude-flow/swarm# Or install everything-npm install claude-flow@v3alpha+npm install ruvflow@v3alpha```### Quick Examples@@ -3944,21 +3944,21 @@ console.log(results);**CLI Commands:**```bash# Initialize memory database-npx claude-flow@alpha memory init --force+npx ruvflow@alpha memory init --force# Store patterns-npx claude-flow@alpha memory store --key "pattern-auth" --value "JWT authentication with refresh tokens"-npx claude-flow@alpha memory store --key "pattern-cache" --value "Redis caching for API responses"+npx ruvflow@alpha memory store --key "pattern-auth" --value "JWT authentication with refresh tokens"+npx ruvflow@alpha memory store --key "pattern-cache" --value "Redis caching for API responses"# Build HNSW index for 150x-12,500x faster search-npx claude-flow@alpha memory search --query "authentication" --build-hnsw+npx ruvflow@alpha memory search --query "authentication" --build-hnsw# Semantic search (uses HNSW if built)-npx claude-flow@alpha memory search --query "how to cache data" --limit 5+npx ruvflow@alpha memory search --query "how to cache data" --limit 5# List and manage entries-npx claude-flow@alpha memory list --namespace patterns-npx claude-flow@alpha memory stats+npx ruvflow@alpha memory list --namespace patterns+npx ruvflow@alpha memory stats```</details>@@ -4192,35 +4192,35 @@ console.log(`Hit rate: ${(stats.hitRate * 100).toFixed(1)}%`);```bash# Generate embedding-claude-flow embeddings embed "Your text here"+ruvflow embeddings embed "Your text here"# Batch embed from file-claude-flow embeddings batch documents.txt -o embeddings.json+ruvflow embeddings batch documents.txt -o embeddings.json# Similarity search-claude-flow embeddings search "query" --index ./vectors+ruvflow embeddings search "query" --index ./vectors# Document chunking-claude-flow embeddings chunk document.txt --strategy sentence --max-size 512+ruvflow embeddings chunk document.txt --strategy sentence --max-size 512# Normalize embeddings-claude-flow embeddings normalize embeddings.json --type l2 -o normalized.json+ruvflow embeddings normalize embeddings.json --type l2 -o normalized.json# Convert to hyperbolic-claude-flow embeddings hyperbolic embeddings.json -o poincare.json+ruvflow embeddings hyperbolic embeddings.json -o poincare.json# Neural operations-claude-flow embeddings neural drift --baseline "context" --input "check"-claude-flow embeddings neural store --id mem-1 --content "data"-claude-flow embeddings neural recall "query" --top-k 5+ruvflow embeddings neural drift --baseline "context" --input "check"+ruvflow embeddings neural store --id mem-1 --content "data"+ruvflow embeddings neural recall "query" --top-k 5# Model management-claude-flow embeddings models list-claude-flow embeddings models download all-MiniLM-L6-v2+ruvflow embeddings models list+ruvflow embeddings models download all-MiniLM-L6-v2# Cache management-claude-flow embeddings cache stats-claude-flow embeddings cache clear --older-than 7d+ruvflow embeddings cache stats+ruvflow embeddings cache clear --older-than 7d```### Available Models@@ -4287,7 +4287,7 @@ await hooks.endTrajectory(trajectory, { success: true });## π Ecosystem & Integrations-Core infrastructure packages powering Claude-Flow's intelligence layer.+Core infrastructure packages powering RuvFlow's intelligence layer.<details><summary>β‘ <strong>Agentic-Flow Integration</strong> β Core AI Infrastructure</summary>@@ -4296,7 +4296,7 @@ Core infrastructure packages powering Claude-Flow's intelligence layer.[](https://www.npmjs.com/package/agentic-flow)[](https://github.com/ruvnet/agentic-flow)-Claude-Flow v3 is built on top of **[agentic-flow](https://github.com/ruvnet/agentic-flow)**, a production-ready AI agent orchestration platform. This deep integration provides 352x faster code transformations, learning memory, and geometric intelligence.+RuvFlow v3 is built on top of **[agentic-flow](https://github.com/ruvnet/agentic-flow)**, a production-ready AI agent orchestration platform. This deep integration provides 352x faster code transformations, learning memory, and geometric intelligence.### Quick Start@@ -4577,9 +4577,9 @@ claude mcp add agentic-flow -- npx agentic-flow mcp start</details>-### Integration with Claude-Flow+### Integration with RuvFlow-Claude-Flow automatically leverages agentic-flow for:+RuvFlow automatically leverages agentic-flow for:| Feature | How It's Used ||---------|---------------|@@ -4590,7 +4590,7 @@ Claude-Flow automatically leverages agentic-flow for:| **Embedding Search** | HNSW-indexed vector search (150x faster) |```typescript-// Claude-Flow automatically uses agentic-flow optimizations+// RuvFlow automatically uses agentic-flow optimizationsimport { getTokenOptimizer } from '@claude-flow/integration';const optimizer = await getTokenOptimizer();@@ -4766,9 +4766,9 @@ jj.enableEncryption(key);</details>-### Claude-Flow Skill+### RuvFlow Skill-Claude-Flow includes a dedicated `/agentic-jujutsu` skill for AI-powered version control:+RuvFlow includes a dedicated `/agentic-jujutsu` skill for AI-powered version control:```bash# Invoke the skill@@ -4851,7 +4851,7 @@ npx agentic-jujutsu examples # Show usage examples[](https://github.com/ruvnet/ruvector)[](https://hub.docker.com/r/ruvnet/ruvector-postgres)-**RuVector** is a high-performance distributed vector database combining vector search, graph queries, and self-learning neural networks. Written in Rust with Node.js/WASM bindings, it powers Claude-Flow's intelligence layer with native speed.+**RuVector** is a high-performance distributed vector database combining vector search, graph queries, and self-learning neural networks. Written in Rust with Node.js/WASM bindings, it powers RuvFlow's intelligence layer with native speed.### Key Capabilities@@ -4933,7 +4933,7 @@ const compressed = ruvector.compress(embedding, 0.3); // 30% quality threshold```bash# Quick setup with CLI (recommended)-npx claude-flow ruvector setup --output ./my-ruvector+npx ruvflow ruvector setup --output ./my-ruvectorcd my-ruvector && docker-compose up -d# Or pull directly from Docker Hub@@ -4941,12 +4941,12 @@ docker run -d \--name ruvector-postgres \-p 5432:5432 \-e POSTGRES_USER=claude \- -e POSTGRES_PASSWORD=claude-flow-test \+ -e POSTGRES_PASSWORD=ruvflow-test \-e POSTGRES_DB=claude_flow \ruvnet/ruvector-postgres# Migrate existing memory to PostgreSQL-npx claude-flow ruvector import --input memory-export.json+npx ruvflow ruvector import --input memory-export.json```**RuVector PostgreSQL vs pgvector:**@@ -5103,12 +5103,12 @@ await db.createHyperedge(['agent-1', 'agent-2', 'agent-3'], {</details>-### Integration with Claude-Flow+### Integration with RuvFlow-Claude-Flow automatically uses RuVector when available:+RuvFlow automatically uses RuVector when available:```typescript-// Claude-Flow detects and uses native ruvector+// RuvFlow detects and uses native ruvectorimport { getVectorStore } from '@claude-flow/memory';const store = await getVectorStore();@@ -5126,19 +5126,19 @@ const similarity = attention.attention(queries, keys, values);```bash# RuVector PostgreSQL Setup (generates Docker files + SQL)-npx claude-flow ruvector setup # Output to ./ruvector-postgres-npx claude-flow ruvector setup --output ./mydir # Custom directory-npx claude-flow ruvector setup --print # Preview files+npx ruvflow ruvector setup # Output to ./ruvector-postgres+npx ruvflow ruvector setup --output ./mydir # Custom directory+npx ruvflow ruvector setup --print # Preview files# Import from sql.js/JSON to PostgreSQL-npx claude-flow ruvector import --input data.json # Direct import-npx claude-flow ruvector import --input data.json --output sql # Dry-run (generate SQL)+npx ruvflow ruvector import --input data.json # Direct import+npx ruvflow ruvector import --input data.json --output sql # Dry-run (generate SQL)# Other RuVector commands-npx claude-flow ruvector status --verbose # Check connection-npx claude-flow ruvector benchmark --vectors 10000 # Performance test-npx claude-flow ruvector optimize --analyze # Optimization suggestions-npx claude-flow ruvector backup --output backup.sql # Backup data+npx ruvflow ruvector status --verbose # Check connection+npx ruvflow ruvector benchmark --vectors 10000 # Performance test+npx ruvflow ruvector optimize --analyze # Optimization suggestions+npx ruvflow ruvector backup --output backup.sql # Backup data# Native ruvector CLInpx ruvector status # Check installation@@ -5165,11 +5165,11 @@ Cloud platform integration and deployment tools.<details><summary>βοΈ <strong>Flow Nexus</strong> β Cloud Platform Integration</summary>-Flow Nexus is a **cloud platform** for deploying and scaling Claude-Flow beyond your local machine.+Flow Nexus is a **cloud platform** for deploying and scaling RuvFlow beyond your local machine.### What Flow Nexus Provides-| Feature | Local Claude-Flow | + Flow Nexus |+| Feature | Local RuvFlow | + Flow Nexus ||---------|-------------------|--------------|| **Swarm Scale** | 15 agents (local resources) | 100+ agents (cloud resources) || **Neural Training** | Limited by local GPU/CPU | Distributed GPU clusters |@@ -5218,7 +5218,7 @@ Flow Nexus is a **cloud platform** for deploying and scaling Claude-Flow beyond/flow-nexus-swarm# Or via CLI-npx claude-flow@v3alpha nexus swarm deploy \+npx ruvflow@v3alpha nexus swarm deploy \--topology hierarchical \--max-agents 50 \--region us-east-1@@ -5230,13 +5230,13 @@ Isolated execution environments for running untrusted code:```bash# Create sandbox-npx claude-flow@v3alpha nexus sandbox create --language python+npx ruvflow@v3alpha nexus sandbox create --language python# Execute code safely-npx claude-flow@v3alpha nexus sandbox exec --code "print('Hello')"+npx ruvflow@v3alpha nexus sandbox exec --code "print('Hello')"# Cleanup-npx claude-flow@v3alpha nexus sandbox destroy+npx ruvflow@v3alpha nexus sandbox destroy```### Event-Driven Workflows@@ -5262,10 +5262,10 @@ steps:# 1. Sign up at flow-nexus.io# 2. Get API key# 3. Configure-npx claude-flow@v3alpha nexus configure --api-key <key>+npx ruvflow@v3alpha nexus configure --api-key <key># 4. Deploy-npx claude-flow@v3alpha nexus swarm deploy+npx ruvflow@v3alpha nexus swarm deploy```</details>@@ -5299,7 +5299,7 @@ Stream-Chain enables **sequential processing** where the output of one agent bec/stream-chain# Define pipeline-npx claude-flow@v3alpha stream-chain create \+npx ruvflow@v3alpha stream-chain create \--name "feature-pipeline" \--stages "researcher,architect,coder,tester,reviewer"```@@ -5341,11 +5341,11 @@ stages:```bash# Run the pipeline-npx claude-flow@v3alpha stream-chain run feature-pipeline \+npx ruvflow@v3alpha stream-chain run feature-pipeline \--input '{"requirements": "Add user dashboard with analytics"}'# Monitor progress-npx claude-flow@v3alpha stream-chain status feature-pipeline+npx ruvflow@v3alpha stream-chain status feature-pipeline```### Use Cases@@ -5385,7 +5385,7 @@ The Pair Programming skill provides **human-AI collaborative coding** with role/pair-programming --mode tdd# Via CLI-npx claude-flow@v3alpha pair start --mode navigator+npx ruvflow@v3alpha pair start --mode navigator```### TDD Mode Workflow@@ -5425,16 +5425,16 @@ npx claude-flow@v3alpha pair start --mode navigator```bash# Switch roles mid-session-npx claude-flow@v3alpha pair switch+npx ruvflow@v3alpha pair switch# Get AI explanation-npx claude-flow@v3alpha pair explain+npx ruvflow@v3alpha pair explain# Run tests-npx claude-flow@v3alpha pair test+npx ruvflow@v3alpha pair test# End session with summary-npx claude-flow@v3alpha pair end+npx ruvflow@v3alpha pair end```</details>@@ -5491,22 +5491,22 @@ Detection Time: 0.04ms | 50+ Patterns | Self-Learning | HNSW Vector Search```bash# Basic threat scan-npx claude-flow@v3alpha security defend -i "ignore previous instructions"+npx ruvflow@v3alpha security defend -i "ignore previous instructions"# Scan a file-npx claude-flow@v3alpha security defend -f ./user-prompts.txt+npx ruvflow@v3alpha security defend -f ./user-prompts.txt# Quick scan (faster)-npx claude-flow@v3alpha security defend -i "some text" --quick+npx ruvflow@v3alpha security defend -i "some text" --quick# JSON output-npx claude-flow@v3alpha security defend -i "test" -o json+npx ruvflow@v3alpha security defend -i "test" -o json# View statistics-npx claude-flow@v3alpha security defend --stats+npx ruvflow@v3alpha security defend --stats# Full security audit-npx claude-flow@v3alpha security scan --depth full+npx ruvflow@v3alpha security scan --depth full```### MCP Tools@@ -5692,7 +5692,7 @@ Domain-Driven Design with bounded contexts, clean architecture, and measured per[](https://www.npmjs.com/package/@claude-flow/browser)-AI-optimized browser automation integrating [agent-browser](https://github.com/AugmentCode/agent-browser) with claude-flow for intelligent web automation, trajectory learning, and multi-agent browser coordination.+AI-optimized browser automation integrating [agent-browser](https://github.com/AugmentCode/agent-browser) with ruvflow for intelligent web automation, trajectory learning, and multi-agent browser coordination.### Installation@@ -5777,7 +5777,7 @@ const template = getWorkflow('login-basic');<details><summary>π¦ <strong>Release Management</strong> β @claude-flow/deployment</summary>-Automated release management, versioning, and CI/CD for Claude Flow packages.+Automated release management, versioning, and CI/CD for RuvFlow packages.### Features@@ -6091,10 +6091,10 @@ npm run bench:attentionnpm run bench:startup# Performance report-npx claude-flow@v3alpha performance report+npx ruvflow@v3alpha performance report# Benchmark specific suite-npx claude-flow@v3alpha performance benchmark --suite memory+npx ruvflow@v3alpha performance benchmark --suite memory```</details>@@ -6475,7 +6475,7 @@ export CLAUDE_FLOW_MEMORY_PATH="./data"| `GCS_PROJECT_ID` | GCS project ID | Optional || `GOOGLE_CLOUD_PROJECT` | Alternative project ID variable | Optional || `GOOGLE_APPLICATION_CREDENTIALS` | Path to GCS service account JSON | Optional |-| `GCS_PREFIX` | Prefix for stored files | `claude-flow-patterns` |+| `GCS_PREFIX` | Prefix for stored files | `ruvflow-patterns` |### Auto-Update System@@ -6546,9 +6546,9 @@ CLAUDE_FLOW_HNSW_EF=200### Configuration File Location-Claude Flow looks for configuration in this order:+RuvFlow looks for configuration in this order:1. `./claude-flow.config.json` (project root)-2. `~/.config/claude-flow/config.json` (user config)+2. `~/.config/ruvflow/config.json` (user config)3. Environment variables (override any file config)### Complete Configuration Schema@@ -6648,7 +6648,7 @@ Claude Flow looks for configuration in this order:"level": "info","format": "json","destination": "console",- "filePath": "./logs/claude-flow.log",+ "filePath": "./logs/ruvflow.log","maxFileSize": "100MB","maxFiles": 10},@@ -6715,7 +6715,7 @@ Claude Flow looks for configuration in this order:"version": "3.0.0","memory": {"type": "hybrid",- "path": "/var/lib/claude-flow/data",+ "path": "/var/lib/ruvflow/data","encryption": { "enabled": true, "algorithm": "aes-256-gcm" }},"swarm": { "topology": "hierarchical", "maxAgents": 15 },@@ -6727,7 +6727,7 @@ Claude Flow looks for configuration in this order:"level": "warn","format": "json","destination": "file",- "filePath": "/var/log/claude-flow/production.log"+ "filePath": "/var/log/ruvflow/production.log"},"monitoring": { "enabled": true, "metricsInterval": 30000 }}@@ -6771,25 +6771,25 @@ Claude Flow looks for configuration in this order:```bash# View current configuration-npx claude-flow@v3alpha config list+npx ruvflow@v3alpha config list# Get specific value-npx claude-flow@v3alpha config get --key memory.type+npx ruvflow@v3alpha config get --key memory.type# Set configuration value-npx claude-flow@v3alpha config set --key swarm.maxAgents --value 10+npx ruvflow@v3alpha config set --key swarm.maxAgents --value 10# Export configuration-npx claude-flow@v3alpha config export > my-config.json+npx ruvflow@v3alpha config export > my-config.json# Import configuration-npx claude-flow@v3alpha config import --file my-config.json+npx ruvflow@v3alpha config import --file my-config.json# Reset to defaults-npx claude-flow@v3alpha config reset --key swarm+npx ruvflow@v3alpha config reset --key swarm# Initialize with wizard-npx claude-flow@v3alpha init --wizard+npx ruvflow@v3alpha init --wizard```</details>@@ -6813,7 +6813,7 @@ lsof -i :3000# Kill existing processkill -9 <PID># Restart MCP server-npx claude-flow@v3alpha mcp start+npx ruvflow@v3alpha mcp start```**Agent spawn failures**@@ -6827,9 +6827,9 @@ export CLAUDE_FLOW_MAX_AGENTS=5**Pattern search returning no results**```bash# Verify patterns are stored-npx claude-flow@v3alpha hooks metrics+npx ruvflow@v3alpha hooks metrics# Re-run pretraining if empty-npx claude-flow@v3alpha hooks pretrain+npx ruvflow@v3alpha hooks pretrain```**Windows path issues**@@ -6837,7 +6837,7 @@ npx claude-flow@v3alpha hooks pretrain# Use forward slashes or escape backslashes$env:CLAUDE_FLOW_MEMORY_PATH = "./data"# Or use absolute path-$env:CLAUDE_FLOW_MEMORY_PATH = "C:/Users/name/claude-flow/data"+$env:CLAUDE_FLOW_MEMORY_PATH = "C:/Users/name/ruvflow/data"```**Permission denied errors**@@ -6850,7 +6850,7 @@ sudo chown -R $(whoami) ~/.npm**High memory usage**```bash# Enable garbage collection-node --expose-gc node_modules/.bin/claude-flow+node --expose-gc node_modules/.bin/ruvflow# Reduce HNSW parameters for lower memoryexport CLAUDE_FLOW_HNSW_M=8export CLAUDE_FLOW_HNSW_EF=100@@ -6882,45 +6882,45 @@ export CLAUDE_FLOW_HNSW_EF=100| Change | V2 | V3 | Impact ||--------|----|----|--------|-| **Package Structure** | `claude-flow` | `@claude-flow/*` (scoped) | Update imports |+| **Package Structure** | `ruvflow` | `@claude-flow/*` (scoped) | Update imports || **Memory Backend** | JSON files | AgentDB + HNSW | Faster search || **Hooks System** | Basic patterns | ReasoningBank + SONA | Self-learning || **Security** | Manual validation | Automatic strict mode | More secure || **CLI Commands** | Flat structure | Nested subcommands | New syntax |-| **Config Format** | `.claude-flow/config.json` | `claude-flow.config.json` | Update path |+| **Config Format** | `.ruvflow/config.json` | `claude-flow.config.json` | Update path |### Step-by-Step Migration```bash# STEP 1: Backup existing data (CRITICAL)cp -r ./data ./data-backup-v2-cp -r ./.claude-flow ./.claude-flow-backup-v2+cp -r ./.ruvflow ./.ruvflow-backup-v2# STEP 2: Check migration status-npx claude-flow@v3alpha migrate status+npx ruvflow@v3alpha migrate status# STEP 3: Run migration with dry-run first-npx claude-flow@v3alpha migrate run --dry-run+npx ruvflow@v3alpha migrate run --dry-run# STEP 4: Execute migration-npx claude-flow@v3alpha migrate run --from v2+npx ruvflow@v3alpha migrate run --from v2# STEP 5: Verify migration-npx claude-flow@v3alpha migrate verify+npx ruvflow@v3alpha migrate verify# STEP 6: Initialize V3 learning-npx claude-flow@v3alpha hooks pretrain-npx claude-flow@v3alpha doctor --fix+npx ruvflow@v3alpha hooks pretrain+npx ruvflow@v3alpha doctor --fix```### Command Changes Reference| V2 Command | V3 Command | Notes ||------------|------------|-------|-| `claude-flow start` | `claude-flow mcp start` | MCP is explicit |-| `claude-flow init` | `claude-flow init --wizard` | Interactive mode |-| `claude-flow spawn <type>` | `claude-flow agent spawn -t <type>` | Nested under `agent` |-| `claude-flow swarm create` | `claude-flow swarm init --topology mesh` | Explicit topology |+| `ruvflow start` | `ruvflow mcp start` | MCP is explicit |+| `ruvflow init` | `ruvflow init --wizard` | Interactive mode |+| `ruvflow spawn <type>` | `ruvflow agent spawn -t <type>` | Nested under `agent` |+| `ruvflow swarm create` | `ruvflow swarm init --topology mesh` | Explicit topology || `--pattern-store path` | `--memory-backend agentdb` | Backend selection || `hooks record` | `hooks post-edit --success true` | Explicit success flag || `memory get <key>` | `memory retrieve --key <key>` | Explicit flag |@@ -6930,7 +6930,7 @@ npx claude-flow@v3alpha doctor --fix### Configuration Migration-**V2 Config (`.claude-flow/config.json`)**:+**V2 Config (`.ruvflow/config.json`)**:```json{"mode": "basic",@@ -6962,7 +6962,7 @@ npx claude-flow@v3alpha doctor --fix```typescript// V2 (deprecated)-import { ClaudeFlow, Agent, Memory } from 'claude-flow';+import { ClaudeFlow, Agent, Memory } from 'ruvflow';// V3 (new)import { ClaudeFlowClient } from '@claude-flow/cli';@@ -6977,10 +6977,10 @@ If migration fails, you can rollback:```bash# Check rollback options-npx claude-flow@v3alpha migrate rollback --list+npx ruvflow@v3alpha migrate rollback --list# Rollback to V2-npx claude-flow@v3alpha migrate rollback --to v2+npx ruvflow@v3alpha migrate rollback --to v2# Restore backup manually if neededrm -rf ./data@@ -6989,12 +6989,12 @@ cp -r ./data-backup-v2 ./data### Post-Migration Checklist-- [ ] Verify all agents spawn correctly: `npx claude-flow@v3alpha agent list`-- [ ] Check memory search works: `npx claude-flow@v3alpha memory search -q "test"`-- [ ] Confirm MCP server starts: `npx claude-flow@v3alpha mcp start`-- [ ] Run doctor diagnostics: `npx claude-flow@v3alpha doctor`-- [ ] Test a simple swarm: `npx claude-flow@v3alpha swarm init --topology mesh`-- [ ] Bootstrap learning: `npx claude-flow@v3alpha hooks pretrain`+- [ ] Verify all agents spawn correctly: `npx ruvflow@v3alpha agent list`+- [ ] Check memory search works: `npx ruvflow@v3alpha memory search -q "test"`+- [ ] Confirm MCP server starts: `npx ruvflow@v3alpha mcp start`+- [ ] Run doctor diagnostics: `npx ruvflow@v3alpha doctor`+- [ ] Test a simple swarm: `npx ruvflow@v3alpha swarm init --topology mesh`+- [ ] Bootstrap learning: `npx ruvflow@v3alpha hooks pretrain`### Common Migration Issuesdiff --git a/agents/architect.yaml b/agents/architect.yamlindex 348190ac5d..9c93b22356 100644--- a/agents/architect.yaml+++ b/agents/architect.yaml@@ -8,4 +8,4 @@ capabilities:optimizations:- context-caching- memory-persistence-createdAt: "2026-02-08T00:09:44.782Z"+createdAt: "2026-02-08T00:12:26.467Z"diff --git a/agents/coder.yaml b/agents/coder.yamlindex 44bad6eb41..3603ed1afa 100644--- a/agents/coder.yaml+++ b/agents/coder.yaml@@ -8,4 +8,4 @@ capabilities:optimizations:- flash-attention- token-reduction-createdAt: "2026-02-08T00:09:44.782Z"+createdAt: "2026-02-08T00:12:26.467Z"diff --git a/agents/reviewer.yaml b/agents/reviewer.yamlindex a90f5773ea..06128499b0 100644--- a/agents/reviewer.yaml+++ b/agents/reviewer.yaml@@ -7,4 +7,4 @@ capabilities:- best-practicesoptimizations:- incremental-analysis-createdAt: "2026-02-08T00:09:44.782Z"+createdAt: "2026-02-08T00:12:26.468Z"diff --git a/agents/security-architect.yaml b/agents/security-architect.yamlindex 5430aa1e29..768d037c1f 100644--- a/agents/security-architect.yaml+++ b/agents/security-architect.yaml@@ -7,4 +7,4 @@ capabilities:- security-reviewoptimizations:- pattern-matching-createdAt: "2026-02-08T00:09:44.782Z"+createdAt: "2026-02-08T00:12:26.468Z"diff --git a/agents/tester.yaml b/agents/tester.yamlindex 4ea4936569..a1d18db622 100644--- a/agents/tester.yaml+++ b/agents/tester.yaml@@ -7,4 +7,4 @@ capabilities:- coverageoptimizations:- parallel-execution-createdAt: "2026-02-08T00:09:44.782Z"+createdAt: "2026-02-08T00:12:26.468Z"diff --git a/v3/implementation/adrs/ADR-048-auto-memory-integration.md b/v3/implementation/adrs/ADR-048-auto-memory-integration.mdnew file mode 100644index 0000000000..73333e288c--- /dev/null+++ b/v3/implementation/adrs/ADR-048-auto-memory-integration.md@@ -0,0 +1,521 @@+# ADR-048: Claude Code Auto Memory Integration++**Status:** Proposed+**Date:** 2026-02-08+**Authors:** RuvNet, Claude Flow Team+**Supersedes:** None+**Related:** ADR-006 (Unified Memory), ADR-018 (Claude Code Integration)++## Context++Claude Code has introduced **Auto Memory** β a persistent directory where Claude automatically records learnings, patterns, and insights as it works. Unlike CLAUDE.md files (human-written instructions), auto memory contains notes Claude writes for itself based on session discoveries.++### What Is Auto Memory?++Auto memory is a per-project persistent directory at `~/.claude/projects/<project>/memory/` containing:++```+~/.claude/projects/<project>/memory/+βββ MEMORY.md # Concise index (first 200 lines loaded into system prompt)+βββ debugging.md # Detailed notes on debugging patterns+βββ api-conventions.md # API design decisions+βββ ... # Any topic files Claude creates+```++Key characteristics:++| Aspect | Details |+|--------|---------|+| Location | `~/.claude/projects/<project>/memory/` |+| Entrypoint | `MEMORY.md` β first 200 lines loaded at session start |+| Topic files | On-demand files for detailed notes (not auto-loaded) |+| Scope | Per-project (derived from git repo root) |+| Persistence | Survives across sessions |+| Activation | `CLAUDE_CODE_DISABLE_AUTO_MEMORY=0` to force on |++### What Claude Remembers++- **Project patterns**: build commands, test conventions, code style+- **Debugging insights**: solutions to tricky problems, common error causes+- **Architecture notes**: key files, module relationships, important abstractions+- **User preferences**: communication style, workflow habits, tool choices++### Problem Statement++Claude-flow v3 has its own rich memory system (`@claude-flow/memory`) backed by AgentDB with HNSW vector indexing. These two memory systems are currently disconnected:++1. **Auto memory** β markdown files, loaded into system prompt, human-readable+2. **AgentDB memory** β structured entries, vector-indexed, 150x-12,500x faster search++Without integration, insights discovered during swarm orchestration are lost between sessions, and auto memory cannot benefit from AgentDB's semantic search capabilities.++## Decision++Implement a **bidirectional bridge** between Claude Code auto memory and claude-flow's unified memory system, treating auto memory as a persistent projection of the most relevant AgentDB entries.++### Architecture++```+βββββββββββββββββββββββββββββββββββββββββββββββββββββββ+β Claude Code Session β+β β+β System Prompt β MEMORY.md (first 200 lines) β+β β+β ββββββββββββββββββββ ββββββββββββββββββββββββ β+β β Auto Memory Dir ββββββΊβ AutoMemoryBridge β β+β β ~/.claude/... β β (@claude-flow/memory)β β+β β β β β β+β β MEMORY.md β β βββββββββββββββββββ β β+β β debugging.md β β β AgentDB + HNSW β β β+β β patterns.md β β β (structured) β β β+β β architecture.md β β βββββββββββββββββββ β β+β ββββββββββββββββββββ ββββββββββββββββββββββββ β+β β+β ββββββββββββββββββββββββββββββββββββββββββββββββ β+β β Swarm Agents β β+β β Agent 1 βββΊ store to AgentDB βββΊ sync to MD β β+β β Agent 2 βββΊ store to AgentDB βββΊ sync to MD β β+β β Agent N βββΊ store to AgentDB βββΊ sync to MD β β+β ββββββββββββββββββββββββββββββββββββββββββββββββ β+βββββββββββββββββββββββββββββββββββββββββββββββββββββββ+```++### Integration Points++#### 1. Auto Memory Bridge Service++New service in `@claude-flow/memory` that syncs between AgentDB and auto memory files:++```typescript+interface AutoMemoryBridgeConfig {+ /** Auto memory directory path */+ memoryDir: string;++ /** Max lines for MEMORY.md (Claude Code reads first 200) */+ maxIndexLines: number; // default: 180 (leave headroom)++ /** Topic file mapping: AgentDB namespace β markdown file */+ topicMapping: Record<string, string>;++ /** Sync strategy */+ syncMode: 'on-write' | 'on-session-end' | 'periodic';++ /** Periodic sync interval in ms (if syncMode is 'periodic') */+ syncIntervalMs?: number;+}++interface IAutoMemoryBridge {+ /** Resolve auto memory directory for current project */+ resolveMemoryDir(): string;++ /** Sync high-value AgentDB entries β MEMORY.md + topic files */+ syncToAutoMemory(): Promise<SyncResult>;++ /** Import auto memory files β AgentDB entries */+ importFromAutoMemory(): Promise<ImportResult>;++ /** Write a specific insight to auto memory */+ recordInsight(insight: MemoryInsight): Promise<void>;++ /** Curate MEMORY.md to stay under 200 lines */+ curateIndex(): Promise<void>;+}+```++#### 2. Memory Directory Resolution++Auto memory path is derived from the git repo root:++```typescript+function resolveAutoMemoryDir(workingDir: string): string {+ const gitRoot = findGitRoot(workingDir);+ const projectKey = gitRoot+ ? gitRoot.replace(/\//g, '-').replace(/^-/, '')+ : workingDir.replace(/\//g, '-').replace(/^-/, '');++ return path.join(+ os.homedir(),+ '.claude',+ 'projects',+ projectKey,+ 'memory'+ );+}+```++#### 3. MEMORY.md Index Generation++MEMORY.md is the entrypoint β first 200 lines are loaded into every session. It must be concise and serve as an index to topic files:++```typescript+interface MemoryInsight {+ /** Category for organization in MEMORY.md */+ category: 'project-patterns' | 'debugging' | 'architecture'+ | 'preferences' | 'performance' | 'security';++ /** One-line summary for MEMORY.md index */+ summary: string;++ /** Detailed content (goes in topic file if > 2 lines) */+ detail?: string;++ /** Source: which agent/hook discovered this */+ source: string;++ /** Confidence score (0-1), used for curation priority */+ confidence: number;++ /** AgentDB entry ID for cross-reference */+ agentDbId?: string;+}+```++Generated MEMORY.md structure:++```markdown+# Claude Flow V3 Project Memory++## Project Patterns+- Use `pnpm` for package management (not npm)+- Build: `npm run build` in each package directory+- Tests: `vitest run` (London School TDD, mock-first)+- See `patterns.md` for detailed conventions++## Architecture+- DDD with bounded contexts in `v3/@claude-flow/`+- Key packages: cli, memory, security, hooks, guidance+- See `architecture.md` for module relationships++## Debugging+- HNSW index requires initialization before search+- SQLite WASM needs `sql.js` not native `better-sqlite3`+- See `debugging.md` for resolved issues++## Performance+- HNSW: 150x-12,500x faster than brute-force+- Int8 quantization: 3.92x memory reduction+- See `performance.md` for benchmark results++## Security+- Input validation at all system boundaries (Zod)+- Path traversal prevention in file operations+- See `security.md` for CVE status+```++#### 4. Hooks Integration++Auto memory syncs are triggered by claude-flow hooks:++| Hook | Auto Memory Action |+|------|--------------------|+| `session-start` | Import auto memory β AgentDB (if stale) |+| `session-end` | Sync AgentDB insights β auto memory files |+| `post-task` | Record task outcome as insight if noteworthy |+| `post-edit` | Record file pattern if new convention detected |+| `intelligence` | Store learned patterns with confidence scores |++```typescript+// session-end hook handler+async function onSessionEnd(ctx: HookContext): Promise<void> {+ const bridge = ctx.resolve<IAutoMemoryBridge>('autoMemoryBridge');++ // Sync high-confidence learnings to auto memory+ await bridge.syncToAutoMemory();++ // Curate MEMORY.md to stay under 200 lines+ await bridge.curateIndex();+}++// post-task hook handler+async function onPostTask(ctx: HookContext): Promise<void> {+ const bridge = ctx.resolve<IAutoMemoryBridge>('autoMemoryBridge');+ const task = ctx.taskResult;++ if (task.success && task.learnings.length > 0) {+ for (const learning of task.learnings) {+ await bridge.recordInsight({+ category: classifyInsight(learning),+ summary: learning.summary,+ detail: learning.detail,+ source: `agent:${task.agentType}`,+ confidence: task.confidenceScore,+ agentDbId: learning.memoryId,+ });+ }+ }+}+```++#### 5. Topic File Management++Detailed notes are stored in topic files (not loaded at startup β read on demand):++```typescript+const DEFAULT_TOPIC_MAPPING: Record<string, string> = {+ 'patterns': 'patterns.md',+ 'debugging': 'debugging.md',+ 'architecture': 'architecture.md',+ 'performance': 'performance.md',+ 'security': 'security.md',+ 'preferences': 'preferences.md',+ 'swarm-results': 'swarm-results.md',+};+```++Topic files are kept under 500 lines each. When a topic file exceeds this, older low-confidence entries are archived or pruned.++#### 6. AgentDB β Auto Memory Sync Strategy++**AgentDB β Auto Memory (on session-end):**++```typescript+async syncToAutoMemory(): Promise<SyncResult> {+ // 1. Query AgentDB for high-confidence entries since last sync+ const entries = await this.memory.query(+ query()+ .inNamespace('learnings')+ .where('confidence', '>=', 0.7)+ .where('updatedAt', '>=', this.lastSyncTime)+ .orderBy('confidence', 'desc')+ .limit(50)+ .build()+ );++ // 2. Classify entries into categories+ const categorized = this.categorize(entries);++ // 3. Update topic files with new entries+ for (const [category, items] of Object.entries(categorized)) {+ await this.appendToTopicFile(category, items);+ }++ // 4. Regenerate MEMORY.md index from topic file summaries+ await this.curateIndex();++ return { synced: entries.length, categories: Object.keys(categorized) };+}+```++**Auto Memory β AgentDB (on session-start):**++```typescript+async importFromAutoMemory(): Promise<ImportResult> {+ const memoryDir = this.resolveMemoryDir();+ if (!existsSync(memoryDir)) return { imported: 0 };++ // 1. Read all topic files+ const files = await glob('*.md', { cwd: memoryDir });++ let imported = 0;+ for (const file of files) {+ const content = await readFile(join(memoryDir, file), 'utf-8');+ const entries = this.parseMarkdownEntries(content);++ for (const entry of entries) {+ // 2. Check if already in AgentDB (by content hash)+ const exists = await this.memory.search(+ query().where('contentHash', '=', hash(entry.content)).build()+ );++ if (exists.length === 0) {+ // 3. Store with embedding for semantic search+ await this.memory.store({+ key: `auto-memory:${file}:${entry.heading}`,+ content: entry.content,+ namespace: 'auto-memory',+ type: 'semantic',+ tags: ['auto-memory', file.replace('.md', '')],+ metadata: {+ sourceFile: file,+ importedAt: new Date().toISOString(),+ contentHash: hash(entry.content),+ },+ });+ imported++;+ }+ }+ }++ return { imported };+}+```++#### 7. Swarm Agent Memory Persistence++When swarm agents complete tasks, their findings are automatically persisted:++```typescript+// In swarm coordinator (post-task)+async function persistSwarmLearnings(+ swarmResult: SwarmResult,+ bridge: IAutoMemoryBridge+): Promise<void> {+ // Extract learnings from all agents+ const learnings = swarmResult.agents+ .flatMap(agent => agent.findings)+ .filter(f => f.isNovel && f.confidence > 0.6);++ // Deduplicate by semantic similarity+ const unique = await deduplicateBySimilarity(learnings, 0.85);++ // Record each unique insight+ for (const learning of unique) {+ await bridge.recordInsight({+ category: learning.category,+ summary: learning.oneLiner,+ detail: learning.fullDescription,+ source: `swarm:${swarmResult.swarmId}:${learning.agentType}`,+ confidence: learning.confidence,+ });+ }+}+```++#### 8. CLI Commands++New subcommands under `npx claude-flow@v3alpha memory`:++```bash+# Sync AgentDB β auto memory files+npx claude-flow@v3alpha memory sync-auto++# Import auto memory β AgentDB+npx claude-flow@v3alpha memory import-auto++# Show auto memory status+npx claude-flow@v3alpha memory auto-status++# Curate MEMORY.md (prune to 200 lines)+npx claude-flow@v3alpha memory curate+```++#### 9. MCP Tool Extensions++New MCP tools for auto memory operations:++```typescript+// memory_auto_sync - Sync AgentDB to auto memory files+{+ name: 'memory_auto_sync',+ description: 'Sync high-confidence AgentDB entries to auto memory files',+ inputSchema: {+ type: 'object',+ properties: {+ direction: { enum: ['to-auto', 'from-auto', 'bidirectional'] },+ minConfidence: { type: 'number', default: 0.7 },+ categories: { type: 'array', items: { type: 'string' } },+ },+ },+}++// memory_auto_record - Record an insight to auto memory+{+ name: 'memory_auto_record',+ description: 'Record a specific insight to auto memory and AgentDB',+ inputSchema: {+ type: 'object',+ properties: {+ category: { type: 'string' },+ summary: { type: 'string' },+ detail: { type: 'string' },+ confidence: { type: 'number' },+ },+ required: ['category', 'summary'],+ },+}+```++## Configuration++Add to `claude-flow.config.json`:++```json+{+ "memory": {+ "autoMemory": {+ "enabled": true,+ "syncMode": "on-session-end",+ "maxIndexLines": 180,+ "minConfidenceForSync": 0.7,+ "topicMapping": {+ "patterns": "patterns.md",+ "debugging": "debugging.md",+ "architecture": "architecture.md",+ "performance": "performance.md",+ "security": "security.md"+ },+ "pruneStrategy": "confidence-weighted",+ "maxTopicFileLines": 500+ }+ }+}+```++Add to `.claude/settings.json`:++```json+{+ "env": {+ "CLAUDE_CODE_DISABLE_AUTO_MEMORY": "0"+ }+}+```++## Consequences++### Positive++- **Cross-session learning**: Swarm insights persist across sessions via auto memory+- **Human-readable**: Auto memory files are plain markdown β inspectable and editable+- **Dual indexing**: MEMORY.md for system prompt loading + AgentDB for semantic search+- **Progressive enhancement**: Works without AgentDB (graceful fallback to file-only)+- **Agent continuity**: New agents in new sessions inherit previous session learnings++### Negative++- **Sync overhead**: Bidirectional sync adds latency at session boundaries (~100-500ms)+- **Staleness risk**: Auto memory files may diverge from AgentDB if syncs fail+- **200-line constraint**: MEMORY.md must be curated carefully to stay within limit+- **Storage duplication**: Same data exists in both markdown files and AgentDB++### Mitigations++| Risk | Mitigation |+|------|------------|+| Sync failure | Idempotent sync with content hashing; retry on next session |+| MEMORY.md overflow | Automated curation with confidence-weighted pruning |+| Staleness | Content hash comparison on import; skip unchanged entries |+| Duplication | AgentDB entries link to auto memory source via `contentHash` |++## Implementation Plan++### Phase 1: Foundation (Week 1)+- [ ] Implement `resolveAutoMemoryDir()` path resolution+- [ ] Create `AutoMemoryBridge` class with basic read/write+- [ ] Add `memory sync-auto` CLI command+- [ ] Unit tests for path resolution and file parsing++### Phase 2: Hooks Integration (Week 2)+- [ ] Wire `session-end` hook to trigger sync+- [ ] Wire `session-start` hook to trigger import+- [ ] Wire `post-task` hook for insight recording+- [ ] Integration tests with mock hook context++### Phase 3: Curation & MCP (Week 3)+- [ ] Implement MEMORY.md curation (confidence-weighted pruning)+- [ ] Add MCP tools (`memory_auto_sync`, `memory_auto_record`)+- [ ] Add topic file management with 500-line limit+- [ ] End-to-end tests with real AgentDB++### Phase 4: Swarm Integration (Week 4)+- [ ] Add swarm result β auto memory pipeline+- [ ] Semantic deduplication for swarm learnings+- [ ] Dashboard/status command for auto memory health+- [ ] Performance benchmarks for sync operations++## References++- [Claude Code Auto Memory Documentation](https://code.claude.com/docs/en/memory)+- ADR-006: Unified Memory Service+- ADR-018: Claude Code Deep Integration Architecture+- ADR-017: RuVector Integration