Skip to content

armgit / ruflo

Public Imported from GitHub
0

🌊 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

Checkpoint: File edits

rUv1d74697ca39c
diff --git a/v3/@claude-flow/cli/src/init/claudemd-generator.ts b/v3/@claude-flow/cli/src/init/claudemd-generator.ts
index 9ea34c68c0..dbc0b6d58e 100644
--- a/v3/@claude-flow/cli/src/init/claudemd-generator.ts
+++ b/v3/@claude-flow/cli/src/init/claudemd-generator.ts
@@ -13,7 +13,7 @@ export function generateClaudeMd(options: InitOptions): string {
const maxAgents = options.runtime.maxAgents;
const memoryBackend = options.runtime.memoryBackend;
- return `# Claude Code Configuration - SPARC Development Environment
+ return `# Claude Code Configuration - Claude Flow V3
## 🚨 AUTOMATIC SWARM ORCHESTRATION
@@ -74,15 +74,14 @@ mcp__claude-flow__memory_usage({
### πŸ“‹ Agent Routing by Task Type
-**Automatically select agents based on task:**
-
| Task Type | Required Agents | Topology |
|-----------|-----------------|----------|
| Bug Fix | researcher, coder, tester | mesh |
| New Feature | coordinator, architect, coder, tester, reviewer | hierarchical |
| Refactoring | architect, coder, reviewer | mesh |
-| Performance | researcher, coder, perf-analyzer | hierarchical |
-| Security Audit | security-manager, reviewer, tester | hierarchical |
+| Performance | researcher, performance-engineer, coder | hierarchical |
+| Security Audit | security-architect, security-auditor, reviewer | hierarchical |
+| Memory Optimization | memory-specialist, performance-engineer | mesh |
| Documentation | researcher, api-docs | mesh |
### 🎯 Task Complexity Detection
@@ -103,36 +102,6 @@ mcp__claude-flow__memory_usage({
- Configuration changes
- Quick questions/exploration
-### πŸ”§ Settings Configuration
-
-The following settings are auto-configured in \`.claude/settings.json\`:
-
-\`\`\`json
-{
- "hooks": {
- "PreToolUse": [{
- "matcher": "Task",
- "commands": ["npx claude-flow@v3alpha hooks pre-task --tool Task"]
- }],
- "PostToolUse": [{
- "matcher": "Task",
- "commands": ["npx claude-flow@v3alpha hooks post-task --tool Task"]
- }],
- "UserPromptSubmit": [{
- "matcher": ".*",
- "commands": ["npx claude-flow@v3alpha hooks route-task"]
- }]
- },
- "permissions": {
- "allow": [
- "Bash(npx claude-flow:*)",
- "mcp__claude-flow__*",
- "mcp__ruv-swarm__*"
- ]
- }
-}
-\`\`\`
-
## 🚨 CRITICAL: CONCURRENT EXECUTION & FILE MANAGEMENT
**ABSOLUTE RULES**:
@@ -150,24 +119,6 @@ The following settings are auto-configured in \`.claude/settings.json\`:
- **Bash commands**: ALWAYS batch ALL terminal operations in ONE message
- **Memory operations**: ALWAYS batch ALL memory store/retrieve in ONE message
-### 🎯 CRITICAL: Claude Code Task Tool for Agent Execution
-
-**Claude Code's Task tool is the PRIMARY way to spawn agents:**
-\`\`\`javascript
-// βœ… CORRECT: Use Claude Code's Task tool for parallel agent execution
-[Single Message]:
- Task("Research agent", "Analyze requirements and patterns...", "researcher")
- Task("Coder agent", "Implement core features...", "coder")
- Task("Tester agent", "Create comprehensive tests...", "tester")
- Task("Reviewer agent", "Review code quality...", "reviewer")
- Task("Architect agent", "Design system architecture...", "system-architect")
-\`\`\`
-
-**MCP tools are ONLY for coordination setup:**
-- \`mcp__claude-flow__swarm_init\` - Initialize coordination topology
-- \`mcp__claude-flow__agent_spawn\` - Define agent types for coordination
-- \`mcp__claude-flow__task_orchestrate\` - Orchestrate high-level workflows
-
### πŸ“ File Organization Rules
**NEVER save to root folder. Use these directories:**
@@ -184,30 +135,81 @@ This project is configured with Claude Flow V3:
- **Topology**: ${topology}
- **Max Agents**: ${maxAgents}
- **Memory Backend**: ${memoryBackend}
-- **HNSW Indexing**: ${options.runtime.enableHNSW ? 'Enabled' : 'Disabled'}
-- **Neural Learning**: ${options.runtime.enableNeural ? 'Enabled' : 'Disabled'}
+- **HNSW Indexing**: ${options.runtime.enableHNSW ? 'Enabled (150x-12,500x faster)' : 'Disabled'}
+- **Neural Learning**: ${options.runtime.enableNeural ? 'Enabled (SONA)' : 'Disabled'}
+
+## πŸš€ V3 CLI Commands (26 Commands, 140+ Subcommands)
+
+### Core Commands
+
+| Command | Subcommands | Description |
+|---------|-------------|-------------|
+| \`init\` | 4 | Project initialization with wizard, presets, skills, hooks |
+| \`agent\` | 8 | Agent lifecycle (spawn, list, status, stop, metrics, pool, health, logs) |
+| \`swarm\` | 6 | Multi-agent swarm coordination and orchestration |
+| \`memory\` | 11 | AgentDB memory with vector search (150x-12,500x faster) |
+| \`mcp\` | 9 | MCP server management and tool execution |
+| \`task\` | 6 | Task creation, assignment, and lifecycle |
+| \`session\` | 7 | Session state management and persistence |
+| \`config\` | 7 | Configuration management and provider setup |
+| \`status\` | 3 | System status monitoring with watch mode |
+| \`workflow\` | 6 | Workflow execution and template management |
+| \`hooks\` | 17 | Self-learning hooks + 12 background workers |
+| \`hive-mind\` | 6 | Queen-led Byzantine fault-tolerant consensus |
+
+### Advanced Commands
+
+| Command | Subcommands | Description |
+|---------|-------------|-------------|
+| \`daemon\` | 5 | Background worker daemon (start, stop, status, trigger, enable) |
+| \`neural\` | 5 | Neural pattern training (train, status, patterns, predict, optimize) |
+| \`security\` | 6 | Security scanning (scan, audit, cve, threats, validate, report) |
+| \`performance\` | 5 | Performance profiling (benchmark, profile, metrics, optimize, report) |
+| \`providers\` | 5 | AI providers (list, add, remove, test, configure) |
+| \`plugins\` | 5 | Plugin management (list, install, uninstall, enable, disable) |
+| \`deployment\` | 5 | Deployment management (deploy, rollback, status, environments, release) |
+| \`embeddings\` | 4 | Vector embeddings (embed, batch, search, init) - 75x faster with agentic-flow |
+| \`claims\` | 4 | Claims-based authorization (check, grant, revoke, list) |
+| \`migrate\` | 5 | V2 to V3 migration with rollback support |
+| \`doctor\` | 1 | System diagnostics with health checks |
+| \`completions\` | 4 | Shell completions (bash, zsh, fish, powershell) |
+
+### Quick CLI Examples
-## SPARC Workflow Phases
+\`\`\`bash
+# Initialize project
+npx claude-flow@v3alpha init --wizard
+
+# Start daemon with background workers
+npx claude-flow@v3alpha daemon start
+
+# Spawn an agent
+npx claude-flow@v3alpha agent spawn -t coder --name my-coder
-1. **Specification** - Requirements analysis (\`sparc run spec-pseudocode\`)
-2. **Pseudocode** - Algorithm design (\`sparc run spec-pseudocode\`)
-3. **Architecture** - System design (\`sparc run architect\`)
-4. **Refinement** - TDD implementation (\`sparc tdd\`)
-5. **Completion** - Integration (\`sparc run integration\`)
+# Initialize swarm
+npx claude-flow@v3alpha swarm init --v3-mode
-## Code Style & Best Practices
+# Search memory (HNSW-indexed)
+npx claude-flow@v3alpha memory search -q "authentication patterns"
-- **Modular Design**: Files under 500 lines
-- **Environment Safety**: Never hardcode secrets
-- **Test-First**: Write tests before implementation
-- **Clean Architecture**: Separate concerns
-- **Documentation**: Keep updated
+# System diagnostics
+npx claude-flow@v3alpha doctor --fix
-## πŸš€ Available Agents
+# Security scan
+npx claude-flow@v3alpha security scan --depth full
+
+# Performance benchmark
+npx claude-flow@v3alpha performance benchmark --suite all
+\`\`\`
+
+## πŸš€ Available Agents (60+ Types)
### Core Development
\`coder\`, \`reviewer\`, \`tester\`, \`planner\`, \`researcher\`
+### V3 Specialized Agents
+\`security-architect\`, \`security-auditor\`, \`memory-specialist\`, \`performance-engineer\`
+
### Swarm Coordination
\`hierarchical-coordinator\`, \`mesh-coordinator\`, \`adaptive-coordinator\`, \`collective-intelligence-coordinator\`, \`swarm-memory-manager\`
@@ -229,277 +231,67 @@ This project is configured with Claude Flow V3:
### Testing & Validation
\`tdd-london-swarm\`, \`production-validator\`
-## 🎯 Claude Code vs MCP Tools
-
-### Claude Code Handles ALL EXECUTION:
-- **Task tool**: Spawn and run agents concurrently for actual work
-- File operations (Read, Write, Edit, MultiEdit, Glob, Grep)
-- Code generation and programming
-- Bash commands and system operations
-- Implementation work
-- Project navigation and analysis
-- TodoWrite and task management
-- Git operations
-- Package management
-- Testing and debugging
-
-### MCP Tools ONLY COORDINATE:
-- Swarm initialization (topology setup)
-- Agent type definitions (coordination patterns)
-- Task orchestration (high-level planning)
-- Memory management
-- Neural features
-- Performance tracking
-- GitHub integration
-
-**KEY**: MCP coordinates the strategy, Claude Code's Task tool executes with real agents.
-
-## πŸš€ Quick Setup
-
-\`\`\`bash
-# Add MCP servers (Claude Flow required, others optional)
-claude mcp add claude-flow npx claude-flow@v3alpha mcp start
-claude mcp add ruv-swarm npx ruv-swarm mcp start # Optional: Enhanced coordination
-claude mcp add flow-nexus npx flow-nexus@latest mcp start # Optional: Cloud features
-\`\`\`
-
-## MCP Tool Categories
-
-### Coordination
-\`swarm_init\`, \`agent_spawn\`, \`task_orchestrate\`
-
-### Monitoring
-\`swarm_status\`, \`agent_list\`, \`agent_metrics\`, \`task_status\`, \`task_results\`
-
-### Memory & Neural
-\`memory_usage\`, \`neural_status\`, \`neural_train\`, \`neural_patterns\`
-
-### GitHub Integration
-\`github_swarm\`, \`repo_analyze\`, \`pr_enhance\`, \`issue_triage\`, \`code_review\`
-
-### System
-\`benchmark_run\`, \`features_detect\`, \`swarm_monitor\`
-
-## πŸš€ Agent Execution Flow with Claude Code
-
-### The Correct Pattern:
-
-1. **Optional**: Use MCP tools to set up coordination topology
-2. **REQUIRED**: Use Claude Code's Task tool to spawn agents that do actual work
-3. **REQUIRED**: Each agent runs hooks for coordination
-4. **REQUIRED**: Batch all operations in single messages
-
-### Example Full-Stack Development:
-
-\`\`\`javascript
-// Single message with all agent spawning via Claude Code's Task tool
-[Parallel Agent Execution]:
- Task("Backend Developer", "Build REST API with Express. Use hooks for coordination.", "backend-dev")
- Task("Frontend Developer", "Create React UI. Coordinate with backend via memory.", "coder")
- Task("Database Architect", "Design PostgreSQL schema. Store schema in memory.", "code-analyzer")
- Task("Test Engineer", "Write Jest tests. Check memory for API contracts.", "tester")
- Task("DevOps Engineer", "Setup Docker and CI/CD. Document in memory.", "cicd-engineer")
- Task("Security Auditor", "Review authentication. Report findings via hooks.", "reviewer")
-
- // All todos batched together
- TodoWrite { todos: [...8-10 todos...] }
-
- // All file operations together
- Write "backend/server.js"
- Write "frontend/App.jsx"
- Write "database/schema.sql"
-\`\`\`
-
-## πŸ“‹ Agent Coordination Protocol
-
-### Every Agent Spawned via Task Tool MUST:
-
-**1️⃣ BEFORE Work:**
-\`\`\`bash
-npx claude-flow@v3alpha hooks pre-task --description "[task]"
-npx claude-flow@v3alpha hooks session-restore --session-id "swarm-[id]"
-\`\`\`
-
-**2️⃣ DURING Work:**
-\`\`\`bash
-npx claude-flow@v3alpha hooks post-edit --file "[file]" --memory-key "swarm/[agent]/[step]"
-npx claude-flow@v3alpha hooks notify --message "[what was done]"
-\`\`\`
-
-**3️⃣ AFTER Work:**
-\`\`\`bash
-npx claude-flow@v3alpha hooks post-task --task-id "[task]"
-npx claude-flow@v3alpha hooks session-end --export-metrics true
-\`\`\`
-
-## πŸš€ Swarm Lifecycle Management
-
-### Session Start (AUTOMATIC)
-When beginning ANY development task, Claude Code should:
-
-\`\`\`javascript
-// 1. Check for existing swarm session
-mcp__claude-flow__swarm_status({})
-
-// 2. If no active swarm, initialize one
-mcp__claude-flow__swarm_init({ topology: "${topology}", maxAgents: ${maxAgents} })
-
-// 3. Restore previous context if available
-mcp__claude-flow__memory_usage({ action: "retrieve", namespace: "swarm", key: "last-session" })
-\`\`\`
-
-### Task Execution (AUTOMATIC)
-For each significant task:
-
-\`\`\`javascript
-// 1. Create task orchestration
-mcp__claude-flow__task_orchestrate({
- task: "[task description]",
- priority: "high",
- strategy: "adaptive"
-})
-
-// 2. Spawn appropriate agents via Task tool (PARALLEL)
-Task("Agent1", "...", "agent-type")
-Task("Agent2", "...", "agent-type")
-Task("Agent3", "...", "agent-type")
-
-// 3. Monitor progress via MCP
-mcp__claude-flow__swarm_status({ includeAgents: true, includeMetrics: true })
-\`\`\`
-
-### Session End (AUTOMATIC)
-When task completes or user ends session:
-
-\`\`\`javascript
-// 1. Save session state
-mcp__claude-flow__memory_usage({
- action: "store",
- namespace: "swarm",
- key: "last-session",
- value: JSON.stringify({ completedAt: new Date().toISOString(), summary: "..." })
-})
-
-// 2. Export metrics if enabled
-mcp__claude-flow__agent_metrics({})
-
-// 3. Graceful shutdown (only if explicitly requested)
-// mcp__claude-flow__swarm_destroy({ swarmId: "..." })
-\`\`\`
-
-## 🎯 Concurrent Execution Examples
-
-### βœ… CORRECT WORKFLOW: MCP Coordinates, Claude Code Executes
-
-\`\`\`javascript
-// Step 1: MCP tools set up coordination (optional, for complex tasks)
-[Single Message - Coordination Setup]:
- mcp__claude-flow__swarm_init { topology: "${topology}", maxAgents: ${maxAgents} }
- mcp__claude-flow__agent_spawn { type: "researcher" }
- mcp__claude-flow__agent_spawn { type: "coder" }
- mcp__claude-flow__agent_spawn { type: "tester" }
-
-// Step 2: Claude Code Task tool spawns ACTUAL agents that do the work
-[Single Message - Parallel Agent Execution]:
- // Claude Code's Task tool spawns real agents concurrently
- Task("Research agent", "Analyze API requirements and best practices. Check memory for prior decisions.", "researcher")
- Task("Coder agent", "Implement REST endpoints with authentication. Coordinate via hooks.", "coder")
- Task("Database agent", "Design and implement database schema. Store decisions in memory.", "code-analyzer")
- Task("Tester agent", "Create comprehensive test suite with 90% coverage.", "tester")
- Task("Reviewer agent", "Review code quality and security. Document findings.", "reviewer")
-
- // Batch ALL todos in ONE call
- TodoWrite { todos: [
- {id: "1", content: "Research API patterns", status: "in_progress", priority: "high"},
- {id: "2", content: "Design database schema", status: "in_progress", priority: "high"},
- {id: "3", content: "Implement authentication", status: "pending", priority: "high"},
- {id: "4", content: "Build REST endpoints", status: "pending", priority: "high"},
- {id: "5", content: "Write unit tests", status: "pending", priority: "medium"},
- {id: "6", content: "Integration tests", status: "pending", priority: "medium"},
- {id: "7", content: "API documentation", status: "pending", priority: "low"},
- {id: "8", content: "Performance optimization", status: "pending", priority: "low"}
- ]}
-
- // Parallel file operations
- Bash "mkdir -p app/{src,tests,docs,config}"
- Write "app/package.json"
- Write "app/src/server.js"
- Write "app/tests/server.test.js"
- Write "app/docs/API.md"
-\`\`\`
-
-### ❌ WRONG (Multiple Messages):
-\`\`\`javascript
-Message 1: mcp__claude-flow__swarm_init
-Message 2: Task("agent 1")
-Message 3: TodoWrite { todos: [single todo] }
-Message 4: Write "file.js"
-// This breaks parallel coordination!
-\`\`\`
-
-## V3 Performance Targets
-
-- **2.49x-7.47x** Flash Attention speedup
-- **150x-12,500x** search improvements with HNSW
-- **50-75%** memory reduction with quantization
-- **Sub-100ms** MCP response times
-
-## πŸͺ V3 Hooks System (26 Hooks)
-
-Claude Flow V3 provides 26 hooks for comprehensive agent coordination and self-learning.
+## πŸͺ V3 Hooks System (17 Hooks + 12 Workers)
### Hook Categories
| Category | Hooks | Purpose |
|----------|-------|---------|
| **Core** | \`pre-edit\`, \`post-edit\`, \`pre-command\`, \`post-command\`, \`pre-task\`, \`post-task\` | Tool lifecycle |
-| **Routing** | \`route\`, \`metrics\`, \`list\` | Task analysis |
-| **Intelligence** | \`explain\`, \`pretrain\`, \`build-agents\`, \`transfer\`, \`init\` | Neural learning |
| **Session** | \`session-start\`, \`session-end\`, \`session-restore\`, \`notify\` | Context management |
-| **Learning** | \`trajectory-start\`, \`trajectory-step\`, \`trajectory-end\` | Reinforcement learning |
-| **Patterns** | \`pattern-store\`, \`pattern-search\`, \`stats\`, \`learn\`, \`attention\` | Memory & search |
+| **Intelligence** | \`route\`, \`explain\`, \`pretrain\`, \`build-agents\`, \`transfer\` | Neural learning |
+| **Learning** | \`intelligence\` (trajectory-start/step/end, pattern-store/search, stats, attention) | Reinforcement |
+
+### 12 Background Workers
+
+| Worker | Priority | Description |
+|--------|----------|-------------|
+| \`ultralearn\` | normal | Deep knowledge acquisition |
+| \`optimize\` | high | Performance optimization |
+| \`consolidate\` | low | Memory consolidation |
+| \`predict\` | normal | Predictive preloading |
+| \`audit\` | critical | Security analysis |
+| \`map\` | normal | Codebase mapping |
+| \`preload\` | low | Resource preloading |
+| \`deepdive\` | normal | Deep code analysis |
+| \`document\` | normal | Auto-documentation |
+| \`refactor\` | normal | Refactoring suggestions |
+| \`benchmark\` | normal | Performance benchmarking |
+| \`testgaps\` | normal | Test coverage analysis |
### Essential Hook Commands
\`\`\`bash
-# Core hooks for tool coordination
+# Core hooks
npx claude-flow@v3alpha hooks pre-task --description "[task]"
npx claude-flow@v3alpha hooks post-task --task-id "[id]" --success true
npx claude-flow@v3alpha hooks post-edit --file "[file]" --train-patterns
# Session management
npx claude-flow@v3alpha hooks session-start --session-id "[id]"
-npx claude-flow@v3alpha hooks session-end --export-metrics true --persist-patterns
+npx claude-flow@v3alpha hooks session-end --export-metrics true
npx claude-flow@v3alpha hooks session-restore --session-id "[id]"
# Intelligence routing
-npx claude-flow@v3alpha hooks route --task "[task]" --include-explanation
-npx claude-flow@v3alpha hooks explain --topic "[topic]" --depth comprehensive
+npx claude-flow@v3alpha hooks route --task "[task]"
+npx claude-flow@v3alpha hooks explain --topic "[topic]"
# Neural learning
npx claude-flow@v3alpha hooks pretrain --model-type moe --epochs 10
-npx claude-flow@v3alpha hooks build-agents --agent-types coder,tester --config-format yaml
-
-# Trajectory learning (reinforcement)
-npx claude-flow@v3alpha hooks intelligence trajectory-start --session "[session]"
-npx claude-flow@v3alpha hooks intelligence trajectory-step --action "[action]" --reward "[reward]"
-npx claude-flow@v3alpha hooks intelligence trajectory-end --verdict success
+npx claude-flow@v3alpha hooks build-agents --agent-types coder,tester
-# Pattern storage (HNSW-indexed)
-npx claude-flow@v3alpha hooks intelligence pattern-store --pattern "[pattern]" --embedding "[json]"
-npx claude-flow@v3alpha hooks intelligence pattern-search --query "[query]" --limit 10
-
-# Learning stats & attention
-npx claude-flow@v3alpha hooks intelligence stats
-npx claude-flow@v3alpha hooks intelligence attention --focus "[task]"
+# Background workers
+npx claude-flow@v3alpha hooks worker list
+npx claude-flow@v3alpha hooks worker dispatch --trigger audit
+npx claude-flow@v3alpha hooks worker status
\`\`\`
-### Intelligence System (RuVector)
+## 🧠 Intelligence System (RuVector)
-V3 includes the RuVector Intelligence System with:
-- **SONA**: Self-Optimizing Neural Architecture
+V3 includes the RuVector Intelligence System:
+- **SONA**: Self-Optimizing Neural Architecture (<0.05ms adaptation)
- **MoE**: Mixture of Experts for specialized routing
-- **HNSW**: 150x faster pattern search
+- **HNSW**: 150x-12,500x faster pattern search
- **EWC++**: Elastic Weight Consolidation (prevents forgetting)
- **Flash Attention**: 2.49x-7.47x speedup
@@ -509,67 +301,112 @@ The 4-step intelligence pipeline:
3. **DISTILL** - Extract key learnings via LoRA
4. **CONSOLIDATE** - Prevent catastrophic forgetting via EWC++
-### Auto-Configured Hooks
-
-The init system configures these hooks in \`.claude/settings.json\`:
-
-\`\`\`json
-{
- "hooks": {
- "PreToolUse": [
- { "matcher": "Task", "commands": ["npx claude-flow@v3alpha hooks pre-task --tool Task"] }
- ],
- "PostToolUse": [
- { "matcher": "Task", "commands": ["npx claude-flow@v3alpha hooks post-task --tool Task --train-patterns"] }
- ],
- "UserPromptSubmit": [
- { "matcher": ".*", "commands": ["npx claude-flow@v3alpha hooks route-task --analyze-complexity"] }
- ],
- "SessionStart": [
- { "commands": ["npx claude-flow@v3alpha hooks session-start --load-context"] }
- ]
- }
-}
+## πŸ“¦ Embeddings Package (v3.0.0-alpha.12)
+
+Features:
+- **sql.js**: Cross-platform SQLite persistent cache (WASM, no native compilation)
+- **Document chunking**: Configurable overlap and size
+- **Normalization**: L2, L1, min-max, z-score
+- **Hyperbolic embeddings**: PoincarΓ© ball model for hierarchical data
+- **75x faster**: With agentic-flow ONNX integration
+- **Neural substrate**: Integration with RuVector
+
+## 🐝 Hive-Mind Consensus
+
+### Topologies
+- \`hierarchical\` - Queen controls workers directly
+- \`mesh\` - Fully connected peer network
+- \`hierarchical-mesh\` - Hybrid (recommended)
+- \`adaptive\` - Dynamic based on load
+
+### Consensus Strategies
+- \`byzantine\` - BFT (tolerates f < n/3 faulty)
+- \`raft\` - Leader-based (tolerates f < n/2)
+- \`gossip\` - Epidemic for eventual consistency
+- \`crdt\` - Conflict-free replicated data types
+- \`quorum\` - Configurable quorum-based
+
+## V3 Performance Targets
+
+| Metric | Target |
+|--------|--------|
+| Flash Attention | 2.49x-7.47x speedup |
+| HNSW Search | 150x-12,500x faster |
+| Memory Reduction | 50-75% with quantization |
+| MCP Response | <100ms |
+| CLI Startup | <500ms |
+| SONA Adaptation | <0.05ms |
+
+## πŸ”§ Environment Variables
+
+\`\`\`bash
+# Configuration
+CLAUDE_FLOW_CONFIG=./claude-flow.config.json
+CLAUDE_FLOW_LOG_LEVEL=info
+
+# Provider API Keys
+ANTHROPIC_API_KEY=sk-ant-...
+OPENAI_API_KEY=sk-...
+GOOGLE_API_KEY=...
+
+# MCP Server
+CLAUDE_FLOW_MCP_PORT=3000
+CLAUDE_FLOW_MCP_HOST=localhost
+CLAUDE_FLOW_MCP_TRANSPORT=stdio
+
+# Memory
+CLAUDE_FLOW_MEMORY_BACKEND=hybrid
+CLAUDE_FLOW_MEMORY_PATH=./data/memory
\`\`\`
-### Agent Coordination via Hooks
+## πŸ” Doctor Health Checks
-Every spawned agent should use hooks for coordination:
+Run \`npx claude-flow@v3alpha doctor\` to check:
+- Node.js version (20+)
+- npm version (9+)
+- Git installation
+- Config file validity
+- Daemon status
+- Memory database
+- API keys
+- MCP servers
+- Disk space
+- TypeScript installation
-\`\`\`javascript
-// In agent prompt instructions
-Task("Coder", \`
- BEFORE starting: npx claude-flow@v3alpha hooks pre-task --description "Implement feature X"
+## πŸš€ Quick Setup
+
+\`\`\`bash
+# Add MCP servers
+claude mcp add claude-flow npx claude-flow@v3alpha mcp start
+claude mcp add ruv-swarm npx ruv-swarm mcp start # Optional
+claude mcp add flow-nexus npx flow-nexus@latest mcp start # Optional
- DURING work:
- - After each file edit: npx claude-flow@v3alpha hooks post-edit --file "[file]"
- - To notify others: npx claude-flow@v3alpha hooks notify --message "[update]"
+# Start daemon
+npx claude-flow@v3alpha daemon start
- AFTER completing: npx claude-flow@v3alpha hooks post-task --success true
-\`, "coder")
+# Run doctor
+npx claude-flow@v3alpha doctor --fix
\`\`\`
-## Advanced Features (V3)
+## 🎯 Claude Code vs MCP Tools
-- πŸš€ Automatic Topology Selection
-- ⚑ Parallel Execution (2.8-4.4x speed)
-- 🧠 Neural Training with ReasoningBank
-- πŸ“Š Bottleneck Analysis
-- πŸ€– Smart Auto-Spawning
-- πŸ›‘οΈ Self-Healing Workflows
-- πŸ’Ύ Cross-Session Memory with AgentDB
-- πŸ”— GitHub Integration
-- πŸ” Security-Hardened Architecture
+### Claude Code Handles ALL EXECUTION:
+- **Task tool**: Spawn and run agents concurrently
+- File operations (Read, Write, Edit, MultiEdit, Glob, Grep)
+- Code generation and programming
+- Bash commands and system operations
+- TodoWrite and task management
+- Git operations
-## Integration Tips
+### MCP Tools ONLY COORDINATE:
+- Swarm initialization (topology setup)
+- Agent type definitions
+- Task orchestration
+- Memory management
+- Neural features
+- Performance tracking
-1. Start with basic swarm init
-2. Scale agents gradually
-3. Use memory for context
-4. Monitor progress regularly
-5. Train patterns from success
-6. Enable hooks automation
-7. Use GitHub tools first
+**KEY**: MCP coordinates the strategy, Claude Code's Task tool executes with real agents.
## Support
@@ -586,6 +423,7 @@ NEVER create files unless they're absolutely necessary for achieving your goal.
ALWAYS prefer editing an existing file to creating a new one.
NEVER proactively create documentation files (*.md) or README files. Only create documentation files if explicitly requested by the User.
Never save working files, text/mds and tests to the root folder.
+After spawning a swarm, wait, don't continuously check status.
`;
}
@@ -593,13 +431,15 @@ Never save working files, text/mds and tests to the root folder.
* Generate minimal CLAUDE.md content
*/
export function generateMinimalClaudeMd(options: InitOptions): string {
- return `# Claude Code Configuration
+ return `# Claude Code Configuration - Claude Flow V3
## Quick Reference
- **Topology**: ${options.runtime.topology}
- **Max Agents**: ${options.runtime.maxAgents}
- **Memory**: ${options.runtime.memoryBackend}
+- **HNSW**: ${options.runtime.enableHNSW ? 'Enabled' : 'Disabled'}
+- **Neural**: ${options.runtime.enableNeural ? 'Enabled' : 'Disabled'}
## Key Rules
@@ -617,6 +457,22 @@ Task("Coder", "Implement features...", "coder")
Task("Tester", "Write tests...", "tester")
\`\`\`
+## 26 CLI Commands
+
+\`\`\`bash
+# Core
+npx claude-flow@v3alpha init --wizard
+npx claude-flow@v3alpha agent spawn -t coder
+npx claude-flow@v3alpha swarm init --v3-mode
+npx claude-flow@v3alpha memory search -q "query"
+
+# Advanced
+npx claude-flow@v3alpha daemon start
+npx claude-flow@v3alpha doctor --fix
+npx claude-flow@v3alpha security scan
+npx claude-flow@v3alpha performance benchmark
+\`\`\`
+
## MCP Setup
\`\`\`bash