Claude-Flow v2.7 is an enterprise-grade AI orchestration platform that combines hive-mind swarm intelligence, persistent memory, and 100+ advanced MCP tools to revolutionize AI-powered development workflows.

• 🧠 ReasoningBank Memory: Persistent SQLite storage with semantic search (2-3ms latency)
• 🔍 Semantic Search: Hash-based embeddings - works without API keys
• 🐝 Hive-Mind Intelligence: Queen-led AI coordination with specialized worker agents
• 🔧 100 MCP Tools: Comprehensive toolkit for swarm orchestration and automation
• 🔄 Dynamic Agent Architecture (DAA): Self-organizing agents with fault tolerance
• 💾 Persistent Memory: .swarm/memory.db with 30+ specialized patterns
• 🪝 Advanced Hooks System: Automated workflows with pre/post operation hooks
• 📊 GitHub Integration: 6 specialized modes for repository management
• 🌐 Flow Nexus Cloud: E2B sandboxes, AI swarms, challenges, and marketplace

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

• 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
claude --dangerously-skip-permissions

# NPX (recommended - always latest)
npx claude-flow@alpha init --force
npx claude-flow@alpha --help
# Or install globally
npm install -g claude-flow@alpha
claude-flow --version
# v2.7.0-alpha.10

Critical bug fix for semantic search returning 0 results:

• ✅ Fixed stale compiled code (dist-cjs/ now uses Node.js backend)
• ✅ Fixed result mapping for retrieveMemories() flat structure
• ✅ Fixed parameter mismatch (namespace vs domain)
• ✅ 2-3ms query latency with hash embeddings
• ✅ Works without API keys (deterministic 1024-dim embeddings)

• Node.js Backend: Replaced WASM with SQLite + better-sqlite3
• Persistent Storage: All memories saved to .swarm/memory.db
• Semantic Search: MMR ranking with 4-factor scoring
• Database Tables: patterns, embeddings, trajectories, links
• Performance: 2ms queries, 400KB per pattern with embeddings

# Semantic search now fully functional
npx claude-flow@alpha memory store test "API configuration" --namespace semantic --reasoningbank
npx claude-flow@alpha memory query "configuration" --namespace semantic --reasoningbank
# ✅ Found 3 results (semantic search) in 2ms

📚 Release Notes: v2.7.0-alpha.10

# Store memories with semantic search
npx claude-flow@alpha memory store api_key "REST API configuration" \
 --namespace backend --reasoningbank
# Query with semantic search (2-3ms latency)
npx claude-flow@alpha memory query "API config" \
 --namespace backend --reasoningbank
# ✅ Found 3 results (semantic search)
# List all memories
npx claude-flow@alpha memory list --namespace backend --reasoningbank
# Check status and statistics
npx claude-flow@alpha memory status --reasoningbank
# ✅ Total memories: 30
# Embeddings: 30
# Storage: .swarm/memory.db

• ✅ No API Keys Required: Hash-based embeddings (1024 dimensions)
• ✅ Persistent Storage: SQLite database survives restarts
• ✅ Semantic Search: MMR ranking with similarity scoring
• ✅ Namespace Isolation: Organize memories by domain
• ✅ Fast Queries: 2-3ms average latency
• ✅ Process Cleanup: Automatic database closing

# For better semantic accuracy (requires API key)
export OPENAI_API_KEY=$YOUR_API_KEY
# Uses text-embedding-3-small (1536 dimensions)

# Quick task execution (recommended)
npx claude-flow@alpha swarm "build REST API with authentication" --claude
# Multi-agent coordination
npx claude-flow@alpha swarm init --topology mesh --max-agents 5
npx claude-flow@alpha swarm spawn researcher "analyze API patterns"
npx claude-flow@alpha swarm spawn coder "implement endpoints"
npx claude-flow@alpha swarm status

# Initialize hive-mind system
npx claude-flow@alpha hive-mind wizard
npx claude-flow@alpha hive-mind spawn "build enterprise system" --claude
# Session management
npx claude-flow@alpha hive-mind status
npx claude-flow@alpha hive-mind resume session-xxxxx

When to Use:

# Add Claude Flow MCP server (required)
claude mcp add claude-flow npx claude-flow@alpha mcp start
# Optional: Enhanced coordination
claude mcp add ruv-swarm npx ruv-swarm mcp start
# Optional: Cloud features (requires registration)
claude mcp add flow-nexus npx flow-nexus@latest mcp start

Core Tools:

• swarm_init, agent_spawn, task_orchestrate
• memory_usage, memory_search
• neural_status, neural_train, neural_patterns

Memory Tools:

• mcp__claude-flow__memory_usage - Store/retrieve persistent memory
• mcp__claude-flow__memory_search - Pattern-based search

GitHub Tools:

• github_repo_analyze, github_pr_manage, github_issue_track

Performance Tools:

• benchmark_run, performance_report, bottleneck_analyze

📚 Full Reference: MCP Tools Documentation

Claude-Flow automatically configures hooks for enhanced operations:

# Auto-configures hooks during init
npx claude-flow@alpha init --force

Pre-Operation:

• pre-task: Auto-assigns agents by complexity
• pre-edit: Validates files and prepares resources
• pre-command: Security validation

Post-Operation:

• post-edit: Auto-formats code
• post-task: Trains neural patterns
• post-command: Updates memory

Session Management:

• session-start: Restores previous context
• session-end: Generates summaries
• session-restore: Loads memory

# Initialize once per feature
npx claude-flow@alpha init --force
npx claude-flow@alpha hive-mind spawn "Implement authentication" --claude
# Continue same feature (reuse hive)
npx claude-flow@alpha memory query "auth" --recent
npx claude-flow@alpha swarm "Add password reset" --continue-session

# Project initialization
npx claude-flow@alpha init --force --project-name "my-app"
# Feature 1: Authentication
npx claude-flow@alpha hive-mind spawn "auth-system" --namespace auth --claude
# Feature 2: User management
npx claude-flow@alpha hive-mind spawn "user-mgmt" --namespace users --claude

# Start research session
npx claude-flow@alpha hive-mind spawn "Research microservices" \
 --agents researcher,analyst --claude
# Check learned knowledge
npx claude-flow@alpha memory stats
npx claude-flow@alpha memory query "microservices patterns" --reasoningbank

• 84.8% SWE-Bench solve rate - Industry-leading problem-solving
• 32.3% token reduction - Efficient context management
• 2.8-4.4x speed improvement - Parallel coordination
• 2-3ms query latency - ReasoningBank semantic search
• 64 specialized agents - Complete development ecosystem
• 100 MCP tools - Comprehensive automation toolkit

• Installation Guide - Setup instructions
• Memory System Guide - ReasoningBank usage
• MCP Tools Reference - Complete tool catalog
• Agent System - All 64 agents

• v2.7.0-alpha.10 - Semantic search fix
• v2.7.0-alpha.9 - Process cleanup
• Changelog - Full version history

• Neural Module - SAFLA self-learning
• Goal Module - GOAP intelligent planning
• Hive-Mind Intelligence - Queen-led coordination
• GitHub Integration - Repository automation

• CLAUDE.md Templates - Project configs
• SPARC Methodology - TDD patterns
• Windows Installation - Windows setup

• GitHub Issues: Report bugs or request features
• Discord: Join the Agentics Foundation community
• Documentation: Complete guides and tutorials
• Examples: Real-world usage patterns

• ✅ Semantic search fix (v2.7.0-alpha.10)
• ✅ ReasoningBank Node.js backend
• 🔄 Enhanced embedding models
• 🔄 Multi-user collaboration features

• Advanced neural pattern recognition
• Cloud swarm coordination
• Real-time agent communication
• Enterprise SSO integration

• 5K+ GitHub stars, 50K npm downloads/month
• 25ドルK MRR, 15 enterprise customers
• 90%+ error prevention
• 30+ minutes saved per developer per week

MIT License - see LICENSE for details

Built with ❤️ by rUv | Powered by Revolutionary AI

v2.7.0-alpha.10 - Semantic Search Fixed + ReasoningBank Node.js Backend