Claude-Flow
Claude-Flow управляет интеллектуальными многолетними роями и автономными рабочими процессами для продвинутого ИИ. Разрабатывайте быстрее с коллективным разумом, 87 MCP-инструментами, DAA и облачной платформой Flow Nexus.
Claude-Flow — это корпоративная платформа оркестрации ИИ, которая позволяет разработчикам создавать и развертывать интеллектуальные мультиагентные рои и автономные рабочие процессы. Она объединяет коллективный разум роя, нейросетевые паттерны и 87 продвинутых инструментов MCP для беспрецедентной разработки на базе ИИ. Благодаря динамической архитектуре агентов, постоянной памяти SQLite, расширенным хукам и нативной поддержке Claude Code, Claude-Flow переосмысляет координацию ИИ для сложных проектов и диалоговых систем, предоставляя надежную основу для корпоративных ИИ-решений.
Ключевые особенности
Варианты использования
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.
- 🐝 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.dbwith 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
🔥 Revolutionary AI Coordination: Build faster, smarter, and more efficiently with AI-powered development orchestration
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 rUv 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 # #732
- 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.
# 1. Initialize Claude Flow with enhanced MCP setup (auto-configures permissions!)
npx claude-flow@alpha init --force
# 2. Explore all revolutionary capabilities
npx claude-flow@alpha --help
# 3a. Quick AI coordination (recommended for most tasks)
npx claude-flow@alpha swarm "build me a REST API" --claude
# 3b. OR launch the full hive-mind system (for complex projects)
npx claude-flow@alpha hive-mind wizard
npx claude-flow@alpha hive-mind spawn "build enterprise system" --claude# 1. Initialize Flow Nexus only (minimal setup)
npx claude-flow 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" })| Feature | swarm Command |
hive-mind Command |
|---|---|---|
| Best For | Quick tasks, single objectives | Complex projects, persistent sessions |
| Setup | Instant - no configuration needed | Interactive wizard setup |
| Session | Temporary coordination | Persistent with resume capability |
| Memory | Task-scoped | Project-wide with SQLite storage |
| Agents | Auto-spawned for task | Manual control with specializations |
| Use When | "Build X", "Fix Y", "Analyze Z" | Multi-feature projects, team coordination |
Quick Rule: Start with swarm for most tasks. Use hive-mind when you need persistent sessions or complex multi-agent coordination.
Confused about .hive-mind and .swarm directories? Not sure when to create new hives? Here are the most common workflow patterns:
# Initialize once per feature/task
npx claude-flow@alpha init --force
npx claude-flow@alpha hive-mind spawn "Implement user authentication" --claude
# Continue working on SAME feature (reuse existing hive)
npx claude-flow@alpha hive-mind status
npx claude-flow@alpha memory query "authentication" --recent
npx claude-flow@alpha swarm "Add password reset functionality" --continue-session# Project-level initialization (once per project)
npx claude-flow@alpha init --force --project-name "my-app"
# Feature 1: Authentication (new hive)
npx claude-flow@alpha hive-mind spawn "auth-system" --namespace auth --claude
# Feature 2: User management (separate hive)
npx claude-flow@alpha hive-mind spawn "user-management" --namespace users --claude
# Resume Feature 1 later (use session ID from spawn output)
npx claude-flow@alpha hive-mind resume session-xxxxx-xxxxx# Start research session
npx claude-flow@alpha hive-mind spawn "Research microservices patterns" --agents researcher,analyst --claude
# Continue research in SAME session
npx claude-flow@alpha memory stats # See what's been learned
npx claude-flow@alpha swarm "Deep dive into API gateway patterns" --continue-session| Situation | Action | Command |
|---|---|---|
| Same objective/feature | Continue existing hive | npx claude-flow@alpha hive-mind resume <session-id> |
| New feature in same project | Create new hive with namespace | npx claude-flow@alpha hive-mind spawn "new-feature" --namespace feature-name |
| Completely different project | New directory + init | mkdir new-project && cd new-project && npx claude-flow@alpha init |
| Experimenting/testing | Temporary hive | npx claude-flow@alpha hive-mind spawn "experiment" --temp |
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 claude-flow@alpha memory stats # See memory data
npx claude-flow@alpha memory list # List all namespaces
npx claude-flow@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)# See what you were working on
npx claude-flow@alpha hive-mind status
npx claude-flow@alpha memory query --recent --limit 5
# List all sessions to find the one you want
npx claude-flow@alpha hive-mind sessions
# Resume specific session by ID
npx claude-flow@alpha hive-mind resume session-xxxxx-xxxxxClaude-Flow v2.0.0 introduces a powerful hooks system that automates coordination and enhances every operation:
# Hooks automatically trigger on operations
npx claude-flow@alpha init --force # Auto-configures MCP servers & hookspre-task: Auto-assigns agents based on task complexitypre-search: Caches searches for improved performancepre-edit: Validates files and prepares resourcespre-command: Security validation before execution
post-edit: Auto-formats code using language-specific toolspost-task: Trains neural patterns from successful operationspost-command: Updates memory with operation contextnotification: Real-time progress updates
session-start: Restores previous context automaticallysession-end: Generates summaries and persists statesession-restore: Loads memory from previous sessions
// .claude/settings.json (auto-configured)
{
"hooks": {
"preEditHook": {
"command": "npx",
"args": ["claude-flow", "hooks", "pre-edit", "--file", "${file}", "--auto-assign-agents", "true"],
"alwaysRun": false
},
"postEditHook": {
"command": "npx",
"args": ["claude-flow", "hooks", "post-edit", "--file", "${file}", "--format", "true"],
"alwaysRun": true
},
"sessionEndHook": {
"command": "npx",
"args": ["claude-flow", "hooks", "session-end", "--generate-summary", "true"],
"alwaysRun": true
}
}
}Hooks integrate seamlessly with Claude Code's workflow:
- Automatic Triggering: Hooks fire automatically during Claude Code operations
- Context Awareness: Each hook receives relevant context (file paths, commands, etc.)
- Non-Blocking: Hooks run asynchronously to maintain performance
- Configurable: Enable/disable specific hooks as needed
# Manual hook execution
npx claude-flow hooks pre-task --description "Build REST API" --auto-spawn-agents
# Post-edit with formatting
npx claude-flow hooks post-edit --file "src/api.js" --format --train-neural
# Session management
npx claude-flow hooks session-end --generate-summary --persist-stateIf you're experiencing issues with ${file} or ${command} variables not working in your hooks (common with Claude Code 1.0.51+), use the fix-hook-variables command:
# Fix all found settings.json files
npx claude-flow@alpha fix-hook-variables
# Fix specific file
npx claude-flow@alpha fix-hook-variables .claude/settings.json
# Create test configuration
npx claude-flow@alpha fix-hook-variables --testThis command automatically transforms legacy variable syntax to working environment variables:
${file}→$CLAUDE_EDITED_FILE${command}→$CLAUDE_COMMAND${tool}→$CLAUDE_TOOL
Claude-Flow v2.0.0 introduces groundbreaking hive-mind architecture where a Queen AI coordinates specialized worker agents in perfect harmony.
# Deploy intelligent swarm coordination
npx claude-flow@alpha swarm "Build a full-stack application" --strategy development
# Launch hive-mind with specific specializations
npx claude-flow@alpha hive-mind spawn "Create microservices architecture" --agents 8 --claude- 👑 Queen Agent: Master coordinator and decision maker
- 🏗️ Architect Agents: System design and technical architecture
- 💻 Coder Agents: Implementation and development
- 🧪 Tester Agents: Quality assurance and validation
- 📊 Analyst Agents: Data analysis and insights
- 🔍 Researcher Agents: Information gathering and analysis
- 🛡️ Security Agents: Security auditing and compliance
- 🚀 DevOps Agents: Deployment and infrastructure
# Neural pattern recognition and training
npx claude-flow@alpha neural train --pattern coordination --epochs 50
npx claude-flow@alpha neural predict --model cognitive-analysis
npx claude-flow@alpha cognitive analyze --behavior "development workflow"# Cross-session memory management with SQLite persistence
npx claude-flow@alpha memory store "project-context" "Full-stack app requirements"
npx claude-flow@alpha memory query "authentication" --namespace sparc
npx claude-flow@alpha memory stats # Shows 12 specialized tables
npx claude-flow@alpha memory export backup.json --namespace default
npx claude-flow@alpha memory import project-memory.json🪟 Windows Users: SQLite will automatically fallback to in-memory storage if native modules fail. All features work normally, but data won't persist between sessions. See Windows guide for persistent storage options.
# Advanced workflow automation
npx claude-flow@alpha workflow create --name "CI/CD Pipeline" --parallel
npx claude-flow@alpha batch process --items "test,build,deploy" --concurrent
npx claude-flow@alpha pipeline create --config advanced-deployment.jsonPowered by 27+ neural models optimized with WASM SIMD acceleration:
# Train coordination patterns
npx claude-flow@alpha neural train --pattern coordination --data "workflow.json"
# Real-time predictions
npx claude-flow@alpha neural predict --model task-optimizer --input "current-state.json"
# Analyze cognitive behavior
npx claude-flow@alpha cognitive analyze --behavior "development-patterns"- Pattern Recognition: Learns from successful operations
- Adaptive Learning: Improves performance over time
- Transfer Learning: Apply knowledge across domains
- Model Compression: Efficient storage and execution
- Ensemble Models: Combine multiple neural networks
- Explainable AI: Understand decision-making process
Complete programmatic control over agent lifecycle and coordination:
# Create specialized agents
npx claude-flow@alpha daa agent-create --type "specialized-researcher" \
--capabilities "[\"deep-analysis\", \"pattern-recognition\"]" \
--resources "{\"memory\": 2048, \"compute\": \"high\"}"
# Match capabilities to tasks
npx claude-flow@alpha daa capability-match \
--task-requirements "[\"security-analysis\", \"performance-optimization\"]"
# Manage agent lifecycle
npx claude-flow@alpha daa lifecycle-manage --agentId "agent-123" --action "scale-up"- Resource Allocation: Dynamic CPU/memory management
- Inter-Agent Communication: Message passing and coordination
- Consensus Mechanisms: Democratic decision making
- Fault Tolerance: Self-healing with automatic recovery
- Performance Optimization: Real-time bottleneck resolution
swarm_init,agent_spawn,task_orchestrateswarm_monitor,topology_optimize,load_balancecoordination_sync,swarm_scale,swarm_destroy
neural_train,neural_predict,pattern_recognizecognitive_analyze,learning_adapt,neural_compressensemble_create,transfer_learn,neural_explain
memory_usage,memory_search,memory_persistmemory_namespace,memory_backup,memory_restorememory_compress,memory_sync,memory_analytics- SQLite Backend: Persistent
.swarm/memory.dbwith 12 specialized tables
performance_report,bottleneck_analyze,token_usagebenchmark_run,metrics_collect,trend_analysishealth_check,diagnostic_run,usage_stats
workflow_create,workflow_execute,workflow_exportautomation_setup,pipeline_create,scheduler_managetrigger_setup,batch_process,parallel_execute
github_repo_analyze,github_pr_manage,github_issue_trackgithub_release_coord,github_workflow_auto,github_code_review
daa_agent_create,daa_capability_match,daa_resource_allocdaa_lifecycle_manage,daa_communication,daa_consensus
security_scan,backup_create,restore_systemconfig_manage,features_detect,log_analysis
# GitHub workflow orchestration and coordination
npx claude-flow@alpha github gh-coordinator analyze --analysis-type security
npx claude-flow@alpha github pr-manager review --multi-reviewer --ai-powered
npx claude-flow@alpha github release-manager coord --version 2.0.0 --auto-changelog
npx claude-flow@alpha github repo-architect optimize --structure-analysis
npx claude-flow@alpha github issue-tracker manage --project-coordination
npx claude-flow@alpha github sync-coordinator align --multi-packagev2.0.0 Alpha automatically configures MCP servers for seamless Claude Code integration:
# Automatic MCP integration (happens during init)
✅ claude-flow MCP server configured
✅ ruv-swarm MCP server configured
✅ 87 tools available in Claude Code
✅ --dangerously-skip-permissions set as default# Advanced SPARC development with neural enhancement
npx claude-flow@alpha sparc mode --type "neural-tdd" --auto-learn
npx claude-flow@alpha sparc workflow --phases "all" --ai-guided --memory-enhanced- 27+ Cognitive Models: Adaptive learning from successful operations
- Pattern Analysis: Real-time behavior analysis and optimization
- Decision Tracking: Complete audit trail of AI decisions
- Performance Learning: Continuous improvement from past executions
# Automatic error recovery and optimization
npx claude-flow@alpha health check --components all --auto-heal
npx claude-flow@alpha fault tolerance --strategy retry-with-learning
npx claude-flow@alpha bottleneck analyze --auto-optimize- SQLite Persistence: Robust
.swarm/memory.dbstorage with 12 specialized tables - Cross-Session Persistence: Remember context across Claude Code sessions
- Namespace Management: Organized memory with hierarchical access
- Enhanced Schema: Agent interactions, training data, performance metrics, and more
- Memory Compression: Efficient storage of large coordination contexts
- Distributed Sync: Share memory across multiple AI instances
- ✅ 84.8% SWE-Bench Solve Rate: Superior problem-solving through hive-mind coordination
- ✅ 32.3% Token Reduction: Efficient task breakdown reduces costs significantly
- ✅ 2.8-4.4x Speed Improvement: Parallel coordination maximizes throughput
- ✅ 87 MCP Tools: Most comprehensive AI tool suite available
- ✅ Zero-Config Setup: Automatic MCP integration with Claude Code
# Check memory system performance
npx claude-flow@alpha memory stats
npx claude-flow@alpha memory list
# Test GitHub coordination modes
npx claude-flow@alpha github gh-coordinator --help
npx claude-flow@alpha github pr-manager --help
# Workflow orchestration
npx claude-flow@alpha workflow create --name "Development Pipeline" --parallel# Deploy complete development swarm
npx claude-flow@alpha hive-mind spawn "Build e-commerce platform with React, Node.js, and PostgreSQL" \
--agents 10 \
--strategy parallel \
--memory-namespace ecommerce
# Monitor progress in real-time
npx claude-flow@alpha swarm monitor --dashboard --real-time# Deploy research swarm with neural enhancement
npx claude-flow@alpha swarm "Research AI safety in autonomous systems" \
--strategy research \
--neural-patterns enabled \
--memory-compression high
# Analyze results with cognitive computing
npx claude-flow@alpha cognitive analyze --target research-results# Automated security analysis with AI coordination
npx claude-flow@alpha github gh-coordinator analyze --analysis-type security --target ./src
npx claude-flow@alpha github repo-architect optimize --security-focused --compliance SOC2
npx claude-flow@alpha hive-mind spawn "security audit and compliance review" --claude┌─────────────────────────────────────────────────────────┐
│ 👑 Queen Agent │
│ (Master Coordinator) │
├─────────────────────────────────────────────────────────┤
│ 🏗️ Architect │ 💻 Coder │ 🧪 Tester │ 🔍 Research │ 🛡️ Security │
│ Agent │ Agent │ Agent │ Agent │ Agent │
├─────────────────────────────────────────────────────────┤
│ 🧠 Neural Pattern Recognition Layer │
├─────────────────────────────────────────────────────────┤
│ 💾 Distributed Memory System │
├─���───────────────────────────────────────────────────────┤
│ ⚡ 87 MCP Tools Integration Layer │
├─────────────────────────────────────────────────────────┤
│ 🛡️ Claude Code Integration │
└─────────────────────────────────────────────────────────┘
- Hierarchical: Queen-led with specialized worker agents
- Mesh: Peer-to-peer coordination for complex tasks
- Hybrid: Dynamic strategy selection based on task complexity
- Neural-Enhanced: AI-optimized coordination patterns
# Global installation (recommended for testing)
npm install -g claude-flow@alpha
# Or use NPX for instant testing
npx claude-flow@alpha init --force
# Verify installation
claude-flow --version # Should show 2.0.0-alpha.53# Initialize with full alpha features
npx claude-flow@alpha init --force --hive-mind --neural-enhanced
# Configure Claude Code integration
npx claude-flow@alpha mcp setup --auto-permissions --87-tools
# Test hive-mind coordination
npx claude-flow@alpha hive-mind test --agents 5 --coordination-testFor complete command documentation, run:
npx claude-flow@alpha --help # Main help
npx claude-flow@alpha help <command> # Detailed command helpKey Commands:
- Hive-Mind:
hive-mind wizard,hive-mind spawn,hive-mind status - Neural:
neural train,neural predict,cognitive analyze - Memory:
memory store,memory query,memory stats,memory export/import - GitHub:
github <mode>(6 specialized modes available) - Workflows:
workflow create,batch process,pipeline create
- Complete API Reference - Comprehensive API documentation
- CLI Commands Guide - All command-line options
- Architecture Overview - System design and internals
- Examples Directory - Code examples and demos
- 🔒 Git Checkpoint System - Automatic Git checkpoints for Claude Code sessions
- 📊 Real Performance Tracking - Actual metrics collection and analysis
- 🪟 Windows Installation - Special instructions for Windows users
- MCP Server Setup - Model Context Protocol configuration
- Claude Code Integration - Enhanced AI workflows
- GitHub Workflows - Repository automation
MIT License - see LICENSE for details.
Alpha Disclaimer: This is an alpha release intended for testing and feedback. Use in production environments is not recommended.
- 🧠 Hive-Mind Architecture: Inspired by natural swarm intelligence
- ⚡ Neural Computing: Advanced AI coordination patterns
- 🛡️ Claude Code Integration: Seamless AI development workflow
- 🚀 Performance Optimization: 2.8-4.4x speed improvements through parallel coordination
npx claude-flow@alpha init --forceJoin the alpha testing revolution!
Built with ❤️ by rUv | Powered by Revolutionary AI
v2.0.0 Alpha - The Future of AI Orchestration
Claude-Flow v2.0.0 Alpha — платформа оркестрации AI
Claude-Flow — это инструмент для организации работы множества AI-агентов, объединённых в «рой» или «улей» под управлением одного ведущего агента (Queen AI). Система предоставляет 87 MCP-инструментов, нейронные механизмы распознавания паттернов и постоянное хранилище на SQLite. Подходит для сложных задач разработки, исследовательских проектов и автоматизации воркфлоу.
Репозиторий: https://github.com/ruvnet/claude-flow
Пакет npm: https://www.npmjs.com/package/claude-flow
Документация Flow Nexus: https://flow-nexus.ruv.io
Лицензия: MIT
Установка и первый запуск
Предварительно установите Claude Code глобально:
npm install -g @anthropic-ai/claude-code
Для быстрого тестирования альфа-версии выполните четыре команды:
npx claude-flow@alpha init --force
npx claude-flow@alpha --help
npx claude-flow@alpha swarm "создай REST API" --claude
npx claude-flow@alpha hive-mind spawn "разработай enterprise-систему" --claude
Важно: Требуется Node.js 18+ и npm 9+.
Пользователям Windows — ознакомьтесь с руководством по установке.
При проблемах с SQLite используется in-memory хранилище автоматически.
Первые шаги с Flow Nexus
Если нужна минимальная настройка для облачной платформы Flow Nexus:
npx claude-flow init --flow-nexus
После инициализации зарегистрируйтесь и войдите через MCP-инструменты в Claude Code:
mcp__flow-nexus__user_register({ email: "your@example.com", password: "secure" })
mcp__flow-nexus__user_login({ email: "your@example.com", password: "secure" })
Затем разверните первый облачный рой:
mcp__flow-nexus__swarm_init({ topology: "mesh", maxAgents: 5 })
mcp__flow-nexus__sandbox_create({ template: "node", name: "api-dev" })
Ключевые понятия: swarm vs hive-mind
| Команда | Когда использовать | Особенности |
|---|---|---|
swarm |
Быстрые задачи, локальные правки | Мгновенный запуск, временная сессия, память только на время задачи |
hive-mind |
Сложные проекты, длительные сессии | Настройка через мастер, постоянная память (SQLite), управление специализированными агентами |
Простое правило: для большинства задач начинайте с swarm. Если нужна постоянная сессия с возможностью возобновления — используйте hive-mind.
Типовые сценарии работы
Одна функция/задача
npx claude-flow@alpha init --force
npx claude-flow@alpha hive-mind spawn "реализовать аутентификацию" --claude
# Продолжить в той же сессии:
npx claude-flow@alpha swarm "добавить сброс пароля" --continue-session
Многофункциональный проект
npx claude-flow@alpha init --force --project-name "my-app"
npx claude-flow@alpha hive-mind spawn "auth-system" --namespace auth --claude
npx claude-flow@alpha hive-mind spawn "user-management" --namespace users --claude
# Вернуться к первой задаче:
npx claude-flow@alpha hive-mind resume session-xxxxx-xxxxx
Исследование
npx claude-flow@alpha hive-mind spawn "исследовать паттерны микросервисов" --agents researcher,analyst --claude
npx claude-flow@alpha memory stats
npx claude-flow@alpha swarm "глубокий анализ API Gateway" --continue-session
Полезные команды для восстановления контекста
npx claude-flow@alpha hive-mind status
npx claude-flow@alpha memory query --recent --limit 5
npx claude-flow@alpha hive-mind sessions
npx claude-flow@alpha hive-mind resume session-xxxxx-xxxxx
Структура директорий
После инициализации создаются:
.hive-mind/— конфигурация и SQLite данные сессий.swarm/—memory.db(база памяти)memory/— индивидуальные памяти агентов (создаются при появлении агентов)coordination/— файлы активных воркфлоу (создаются в процессе задач)
Не пугайтесь, если каталоги кажутся пустыми — данные хранятся в SQLite. Используйте npx claude-flow@alpha memory stats для просмотра содержимого.
Система хуков (автоматизация воркфлоу)
Хуки позволяют автоматически выполнять действия до/после операций. Настраиваются в .claude/settings.json:
{
"hooks": {
"preEditHook": {
"command": "npx",
"args": ["claude-flow", "hooks", "pre-edit", "--file", "${file}", "--auto-assign-agents", "true"],
"alwaysRun": false
},
"postEditHook": {
"command": "npx",
"args": ["claude-flow", "hooks", "post-edit", "--file", "${file}", "--format", "true"],
"alwaysRun": true
},
"sessionEndHook": {
"command": "npx",
"args": ["claude-flow", "hooks", "session-end", "--generate-summary", "true"],
"alwaysRun": true
}
}
}
Доступные хуки
- pre-task — автоназначение агентов по сложности
- pre-search — кэширование поисковых запросов
- pre-edit — валидация файлов
- pre-command — проверка безопасности перед выполнением
- post-edit — автоформатирование кода
- post-task — обучение нейронных паттернов
- post-command — обновление памяти
- session-start/end — восстановление/сохранение контекста
Если хуки не работают (проблемы с ${file})
В новых версиях Claude Code переменные ${file} могут не интерполироваться. Используйте команду исправления:
npx claude-flow@alpha fix-hook-variables
# Или для конкретного файла
npx claude-flow@alpha fix-hook-variables .claude/settings.json
Она заменит `
Примечание: раздел «87 Advanced MCP Tools» обрезан в исходном тексте. Полный список инструментов доступен в документации.
Как Flow Nexus Cloud Platform интегрируется с Claude-Flow?
Flow Nexus предоставляет интегрированную облачную среду с E2B-песочницами для различных сред выполнения, облачное развертывание AI-роев, нейрообучение и автоматизацию рабочих процессов для комплексной разработки ИИ.
Когда следует использовать команду 'swarm' вместо 'hive-mind'?
Используйте `swarm` для быстрых одноцелевых AI-задач. Выбирайте `hive-mind` при управлении сложными проектами с множеством функций, требующими постоянных сессий и детального контроля агентов.
Что такое Claude-Flow?
Claude-Flow — это платформа оркестрации ИИ корпоративного уровня, которая позволяет разработчикам создавать продвинутые AI-системы с использованием интеллектуальных мультиагентных роев и автономных рабочих процессов.
Каковы основные возможности Claude-Flow для разработки ИИ?
Ключевые возможности включают Hive-Mind Swarm Intelligence с Queen-Led AI Coordination, Dynamic Agent Architecture (DAA), 87 продвинутых MCP-инструментов для оркестрации и постоянную систему памяти на SQLite.
Источник: https://mcpmarket.com/server/claude-flow
Комментарии
Комментариев пока нет. Будьте первым.