🌊 Claude-Flow v2.5.0 Alpha 140: AI Orchestration Platform

🌟 Overview

Claude-Flow v2 Alpha is an enterprise-grade AI orchestration platform that reimagines how developers build with AI. By combining hive-mind swarm intelligence, neural pattern recognition, and 87 advanced MCP tools, Claude-Flow enables unprecedented AI-powered development workflows.

🎯 Key Features

• 🐝 Hive-Mind Intelligence: Queen-led AI coordination with specialized worker agents
• 🧠 Neural Networks: 27+ cognitive models with WASM SIMD acceleration
• 🔧 87 MCP Tools: Comprehensive toolkit for swarm orchestration, memory, and automation
• 🔄 Dynamic Agent Architecture (DAA): Self-organizing agents with fault tolerance
• 💾 SQLite Memory System: Persistent .swarm/memory.db with 12 specialized tables
• 🪝 Advanced Hooks System: Automated workflows with pre/post operation hooks
• 📊 GitHub Integration: 6 specialized modes for repository management
• 🌐 Flow Nexus Cloud Platform: E2B sandboxes, AI swarms, challenges, and marketplace integration
• 🎯 PreToolUse Modification Hooks: NEW - Claude Code v2.0.10+ intelligent input modification (safety, organization, optimization)

🔥 Revolutionary AI Coordination: Build faster, smarter, and more efficiently with AI-powered development orchestration

🎯 NEW: PreToolUse Modification Hooks Plugin (v2.5.0-alpha.140)

First Claude Code plugin with intelligent tool input modification - automatically enhances commands and files before execution.

Key Features:

• 🛡️ Safety: Auto-adds -i to rm commands, detects sensitive keywords
• 📁 Organization: Auto-routes files (tests→/tests/, src→/src/)
• ⚡ Productivity: Alias expansion (ll→ls -lah), conventional commits

Quick Start:

Option 1: Direct Plugin Installation (Recommended)

# In Claude Code, run:
/plugin samuelmukoti/devflow

Option 2: Via NPM

npx devflow-ai@alpha init --force  # Auto-configures .claude-plugin/hooks/hooks.json

Examples:

rm test.txt          → rm -i test.txt           # Safety
test.js             → src/test.js              # Organization
git commit -m "fix" → [fix] fix + co-author   # Commits

📚 Docs: HOOKS-V2-MODIFICATION.md | Plugin: .claude-plugin/ | Composable with agent-booster

🌐 Flow Nexus Cloud Platform

NEW: Claude-Flow v2.0.0 now includes Flow Nexus integration - a cloud-powered AI development platform featuring:

• E2B Sandboxes: Secure isolated environments for Node.js, Python, React, Next.js
• AI Swarms: Deploy multi-agent systems in cloud infrastructure
• Neural Training: Distributed machine learning with custom model deployment
• Challenges & Marketplace: Coding challenges with Samuel Mukoti credit rewards and template marketplace
• Workflow Automation: Event-driven automation with message queue processing

📚 Complete documentation: Visit flow-nexus.ruv.io for comprehensive guides, tutorials, and API reference. Also see issue # https://github.com/samuelmukoti/devflow/issues/732

⚡ Try v2.0.0 Alpha in 4 Commands

📋 Prerequisites

• Node.js 18+ (LTS recommended)
• npm 9+ or equivalent package manager
• Windows users: See Windows Installation Guide for special instructions

⚠️ IMPORTANT: Claude Code must be installed first:

# 1. Install Claude Code globally
npm install -g @anthropic-ai/claude-code

# 2. (Optional) Skip permissions check for faster setup
# Only use if you understand the security implications
claude --dangerously-skip-permissions

💡 Windows Note: If you encounter SQLite errors, Claude Flow will automatically use in-memory storage. For persistent storage options, see our Windows guide.

🎯 Instant Alpha Testing

Method 1: Plugin Installation (Easiest - includes PreToolUse hooks!)

# In Claude Code:
/plugin samuelmukoti/devflow

Method 2: NPM Installation (For MCP server + CLI)

# 1. Initialize Claude Flow with enhanced MCP setup (auto-configures permissions!)
npx devflow-ai@alpha init --force

# 2. Explore all revolutionary capabilities
npx devflow-ai@alpha --help

# 3a. Quick AI coordination (recommended for most tasks)
npx devflow-ai@alpha swarm "build me a REST API" --claude

# 3b. OR launch the full hive-mind system (for complex projects)
npx devflow-ai@alpha hive-mind wizard
npx devflow-ai@alpha hive-mind spawn "build enterprise system" --claude

🚀 Quick Start with Flow Nexus

# 1. Initialize Flow Nexus only (minimal setup)
npx devflow init --flow-nexus

# 2. Register and login (use MCP tools in Claude Code)
mcp__flow-nexus__user_register({ email: "your@email.com", password: "secure" })
mcp__flow-nexus__user_login({ email: "your@email.com", password: "secure" })

# 3. Deploy your first cloud swarm
mcp__flow-nexus__swarm_init({ topology: "mesh", maxAgents: 5 })
mcp__flow-nexus__sandbox_create({ template: "node", name: "api-dev" })

🤔 Swarm vs Hive-Mind: Which to Use?

Quick Rule: Start with swarm for most tasks. Use hive-mind when you need persistent sessions or complex multi-agent coordination.

🎯 Typical Workflows - Your "Happy Path" Guide

New to Claude-Flow? Start Here!

Confused about .hive-mind and .swarm directories? Not sure when to create new hives? Here are the most common workflow patterns:

🚀 Pattern 1: Single Feature Development

# Initialize once per feature/task
npx devflow-ai@alpha init --force
npx devflow-ai@alpha hive-mind spawn "Implement user authentication" --claude

# Continue working on SAME feature (reuse existing hive)
npx devflow-ai@alpha hive-mind status
npx devflow-ai@alpha memory query "authentication" --recent
npx devflow-ai@alpha swarm "Add password reset functionality" --continue-session

🏗️ Pattern 2: Multi-Feature Project

# Project-level initialization (once per project)
npx devflow-ai@alpha init --force --project-name "my-app"

# Feature 1: Authentication (new hive)
npx devflow-ai@alpha hive-mind spawn "auth-system" --namespace auth --claude

# Feature 2: User management (separate hive)  
npx devflow-ai@alpha hive-mind spawn "user-management" --namespace users --claude

# Resume Feature 1 later (use session ID from spawn output)
npx devflow-ai@alpha hive-mind resume session-xxxxx-xxxxx

🔍 Pattern 3: Research & Analysis

# Start research session
npx devflow-ai@alpha hive-mind spawn "Research microservices patterns" --agents researcher,analyst --claude

# Continue research in SAME session
npx devflow-ai@alpha memory stats  # See what's been learned
npx devflow-ai@alpha swarm "Deep dive into API gateway patterns" --continue-session

🤔 When Should I Create a New Hive?

📁 Understanding "Empty" Directories

Don't panic if directories seem empty! Claude-Flow uses SQLite databases that may not show files in directory listings:

# Check what's actually stored (even if directories look empty)
npx devflow-ai@alpha memory stats        # See memory data
npx devflow-ai@alpha memory list         # List all namespaces  
npx devflow-ai@alpha hive-mind status    # See active hives

# Your project structure after initialization:
# .hive-mind/     <- Contains config.json + SQLite session data
# .swarm/         <- Contains memory.db (SQLite database)
# memory/         <- Agent-specific memories (created when agents spawn)
# coordination/   <- Active workflow files (created during tasks)

🔄 Continuing Previous Work

# See what you were working on
npx devflow-ai@alpha hive-mind status
npx devflow-ai@alpha memory query --recent --limit 5

# List all sessions to find the one you want
npx devflow-ai@alpha hive-mind sessions

# Resume specific session by ID
npx devflow-ai@alpha hive-mind resume session-xxxxx-xxxxx

🪝 Advanced Hooks System

Automated Workflow Enhancement

Claude-Flow v2.0.0 introduces a powerful hooks system that automates coordination and enhances every operation:

# Hooks automatically trigger on operations
npx devflow-ai@alpha init --force  # Auto-configures MCP servers & hooks

Available Hooks

Pre-Operation Hooks

• pre-task: Auto-assigns agents based on task complexity
• pre-search: Caches searches for improved performance
• pre-edit: Validates files and prepares resources
• pre-command: Security validation before execution

Post-Operation Hooks

• post-edit: Auto-formats code using language-specific tools
• post-task: Trains neural patterns from successful operations
• post-command: Updates memory with operation context
• notification: Real-time progress updates

Session Hooks

• session-start: Restores previous context automatically
• session-end: Generates summaries and persists state
• session-restore: Loads memory from previous sessions

Hook Configuration

// .claude/settings.json (auto-configured)
{
  "hooks": {
    "preEditHook": {
      "command": "npx",
      "args": ["devflow", "hooks", "pre-edit", "--file", "${file}", "--auto-assign-agents", "true"],
      "alwaysRun": false
    },
    "postEditHook": {
      "command": "npx", 
      "args": ["devflow", "hooks", "post-edit", "--file", "${file}", "--format", "true"],
      "alwaysRun": true
    },
    "sessionEndHook": {
      "command": "npx",
      "args": ["devflow", "hooks", "session-end", "--generate-summary", "true"],
      "alwaysRun": true
    }
  }
}

📚 Complete Documentation

For detailed information about all features, advanced usage, and comprehensive guides, visit our GitHub Wiki:

🤖 Core Features

• Neural Module - SAFLA self-learning systems with 4-tier memory architecture
• Goal Module - GOAP intelligent planning with A* pathfinding
• Agent System Overview - Complete catalog of all 64 agents
• Hive-Mind Intelligence - Queen-led AI coordination patterns

⚡ Advanced Topics

• Memory System - SQLite-based persistent memory
• MCP Tools Reference - Complete guide to all 87 tools
• GitHub Integration - Repository management automation
• Performance Benchmarking - Optimization strategies

📋 Configuration & Templates

• CLAUDE.md Templates - Project-specific configurations
• SPARC Methodology - Test-driven development patterns
• Development Patterns - Best practices

🛠️ Setup & Troubleshooting

• Installation Guide - Detailed setup instructions
• Windows Installation - Windows-specific setup
• Troubleshooting - Common issues and solutions
• Non-Interactive Mode - CI/CD automation

🤝 Community & Support

• GitHub Issues: Report bugs or request features
• Discord: Join the Agentics Foundation community
• Wiki: Comprehensive documentation
• Examples: Real-world usage patterns

📊 Performance & Stats

• 84.8% SWE-Bench solve rate - Industry-leading problem-solving capability
• 32.3% token reduction - Efficient context management
• 2.8-4.4x speed improvement - Parallel coordination strategies
• 64 specialized agents - Complete development ecosystem
• 87 MCP tools - Comprehensive automation toolkit

📊 Targets (Month 12)

• 5K+ GitHub stars, 50K npm downloads/month
• $25K MRR, 15 enterprise customers
• 90%+ error prevention, 30+ min saved/dev/week

Star History

Built with ❤️ by Samuel Mukoti | Powered by Revolutionary AI

v2.5.0-alpha.140 - The Future of AI Orchestration with PreToolUse Modification Hooks