🌊 Claude-Flow: Agent Orchestration Platform for Claude-Code

🎉 What's New in v1.0.41

🚀 Simplified SPARC Syntax: npx claude-flow sparc "build app" (no more double sparc!)
⚡ Auto-Skip Permissions: --dangerously-skip-permissions by default (use --enable-permissions to restore prompts)
🤖 Non-Interactive Mode: JSON output with --non-interactive flag for automation and parallel execution
📁 Directory Safety: Enhanced guidance to prevent files in node_modules
🎯 17+ SPARC Modes: Including new sparc-orchestrator for complex workflows
📂 Local Executable: init now creates ./claude-flow wrapper to ensure correct working directory
🔧 Fixed SPARC Path Resolution: .roomodes now correctly found in project directory
🌐 Remote Environment Support: Improved wrapper script for npm/npx installations
📝 Better SPARC Error Messages: Clear guidance when .roomodes is missing

🎯 Transform Your Development Workflow

Claude-Flow is the ultimate multi-terminal orchestration platform that revolutionizes how you work with Claude Code. Imagine coordinating dozens of AI agents simultaneously, each working on different aspects of your project while sharing knowledge through an intelligent memory bank.

🔥 One command to rule them all: npx claude-flow - Deploy a full AI agent coordination system in seconds!

🌟 Why Claude-Flow?

🚀 10x Faster Development: Parallel AI agent execution with intelligent task distribution
🧠 Persistent Memory: Agents learn and share knowledge across sessions
⚡ SPARC Methodology: Systematic development with Specification → Pseudocode → Architecture → Refinement → Completion
🔄 Zero Configuration: Works out-of-the-box with sensible defaults
🤖 VSCode Native: Seamless integration with your favorite IDE
🔒 Enterprise Ready: Production-grade security, monitoring, and scaling
🌐 MCP Compatible: Full Model Context Protocol support for tool integration

📦 Installation

🚀 Get started in 30 seconds

Step 1. Install Claude Code: npm install -g @anthropic-ai/claude-code
Step 2. Install Claude-Flow npx -y claude-flow@latest --version
Step 3. Initialize Claude-Flow npx -y claude-flow@latest init --sparc
Step 4. Start the orchestrator npx -y claude-flow@latest sparc "build and test my project"

# ⚡ SPARC Development Workflow (NEW: Simplified!)
npx claude-flow sparc "build a todo app" # Orchestrator mode (default)
npx claude-flow sparc modes              # List 17+ development modes
npx claude-flow sparc tdd "user auth"    # Run TDD workflow
npx claude-flow sparc run code "API"     # Specific mode execution

# 🚀 Parallel Execution (requires external tool)
# Example with GNU Parallel:
parallel -j 3 npx claude-flow sparc run {} --non-interactive ::: \
  "code 'frontend'" "code 'backend'" "tdd 'tests'"

# 🤖 Spawn a research team
npx claude-flow agent spawn researcher --name "Senior Researcher"
npx claude-flow agent spawn analyst --name "Data Analyst"
npx claude-flow agent spawn implementer --name "Code Developer"

# 📋 Create and execute tasks
npx claude-flow task create research "Research AI optimization techniques"
npx claude-flow task list

# 📊 Monitor in real-time
npx claude-flow status
npx claude-flow monitor

🏗️ Core Features

🤖 Multi-Agent Orchestration Coordinate dozens of AI agents with different specializations, each running in isolated terminal sessions with intelligent load balancing.	🧠 Intelligent Memory Bank Advanced CRDT-based memory system with SQLite performance and Markdown readability. Agents learn and share knowledge across sessions.	⚡ SPARC Development Systematic AI-assisted development using Specification → Pseudocode → Architecture → Refinement → Completion methodology with 16+ specialized modes.
🎯 Smart Task Scheduling Priority-based task queues with dependency resolution, deadlock detection, and automatic retry with exponential backoff.	🔒 Enterprise Security Token-based authentication, rate limiting, circuit breakers, audit logging, and role-based access control.	🌐 MCP Integration Full Model Context Protocol support with stdio and HTTP transports, enabling seamless integration with external tools.

⚡ Quick Start

🎯 Option 1: NPX (Recommended)

# Install and run in one command
npx claude-flow

# Or install globally for repeated use
npm install -g claude-flow
claude-flow --version

🦕 Option 2: Deno (For Developers)

# Install via Deno
deno install --allow-all --name claude-flow \
  https://raw.githubusercontent.com/ruvnet/claude-code-flow/main/src/cli/index.ts

# Or run directly
deno run --allow-all \
  https://raw.githubusercontent.com/ruvnet/claude-code-flow/main/src/cli/index.ts

🔧 Option 3: From Source (For Contributors)

git clone https://github.com/ruvnet/claude-code-flow.git
cd claude-code-flow
deno task build && deno task install

📚 Documentation

Comprehensive documentation is available to help you get the most out of Claude-Flow:

Getting Started Guide - Quick setup and first steps
Architecture Overview - System design and components
Configuration Guide - Detailed configuration options
Agent Management - Working with AI agents
Task Coordination - Task scheduling and workflows
Memory Bank Usage - Persistent memory system
MCP Integration - Model Context Protocol tools
Terminal Management - Terminal pooling and sessions
Troubleshooting - Common issues and solutions
Advanced Usage - Power user features
Claude Spawning - Spawning Claude instances
CLI Reference - Complete command documentation

💡 Quick Start Guide

1. Initialize Claude Code Integration

# Basic init (without SPARC modes)
npx claude-flow init

# Recommended: Initialize with SPARC development modes
npx claude-flow init --sparc

The --sparc flag creates:

CLAUDE.md - SPARC-enhanced Claude Code configuration
memory-bank.md - Memory system documentation
coordination.md - Agent coordination documentation
.roomodes - SPARC development mode configurations
.roo/ - SPARC templates and workflows
Memory folder structure with placeholders
./claude-flow - Local executable wrapper (use instead of npx)

2. Start the Orchestrator

# After init, use the local wrapper:
./claude-flow start

# Or run as daemon
./claude-flow start --daemon

# If not initialized yet, use npx:
npx claude-flow start

3. Spawn Agents

# Spawn different agent types with specific capabilities
npx claude-flow agent spawn researcher --name "Research Assistant" --priority 8
npx claude-flow agent spawn implementer --name "Code Developer" --priority 7
npx claude-flow agent spawn analyst --name "Data Analyst" --priority 6
npx claude-flow agent spawn coordinator --name "Project Manager" --priority 9

# List all active agents
npx claude-flow agent list

# Get detailed information about an agent
npx claude-flow agent info agent-123

4. Create and Manage Tasks

# Create tasks with different priorities
npx claude-flow task create research "Analyze authentication best practices" --priority 8
npx claude-flow task create implementation "Build JWT authentication" --priority 9
npx claude-flow task create analysis "Review security vulnerabilities" --priority 10

# Create task with dependencies
npx claude-flow task create implementation "Build user management" \
  --priority 7 --deps task-123,task-456

# Assign tasks to agents
npx claude-flow task assign task-123 agent-456

# List all tasks
npx claude-flow task list
npx claude-flow task list --verbose  # Show detailed task information

# Check specific task status
npx claude-flow task status task-123

# Cancel a task
npx claude-flow task cancel task-789

5. Spawn Claude Instances 🆕

# Spawn Claude with enhanced Claude-Flow guidance
npx claude-flow claude spawn "implement user authentication" --research --parallel

# Backend-only mode with high coverage
npx claude-flow claude spawn "create REST API" --mode backend-only --coverage 95

# Frontend development with feature commits
npx claude-flow claude spawn "build React components" --mode frontend-only --commit feature

# Full stack with all options
npx claude-flow claude spawn "build complete app" --research --parallel --coverage 90 --verbose

# Execute batch workflow
npx claude-flow claude batch examples/claude-workflow.json --dry-run

Enhanced Claude Instances receive:

Detailed Claude-Flow system guidance
Proper npx claude-flow command syntax
Mode-specific instructions (backend/frontend/api/full)
Memory bank operations with examples
Configuration-aware development guidance

6. Monitor System Status

# Check system health
npx claude-flow status

# Real-time monitoring
npx claude-flow monitor

# View MCP tools
npx claude-flow mcp tools

🚀 SPARC Development Methodology

Claude-Flow integrates the SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) methodology for systematic AI-assisted development:

Available SPARC Modes

# List all development modes
npx claude-flow sparc modes

# Key modes include:
# 🏗️ architect      - System design and architecture
# 🧠 code           - Clean, modular implementation  
# 🧪 tdd            - Test-driven development
# 🛡️ security-review - Security analysis
# 📚 docs-writer    - Documentation creation
# 🔗 integration    - System integration

SPARC Workflow

# Simplified orchestration (NEW!)
npx claude-flow sparc "build complete authentication system"

# Or use specific modes:
# 1. Specification - Define requirements
npx claude-flow sparc run spec-pseudocode "user authentication system"

# 2. Architecture - Design system structure  
npx claude-flow sparc run architect "auth service architecture"

# 3. Refinement - TDD implementation
npx claude-flow sparc tdd "implement JWT authentication"

# 4. Integration - Connect components
npx claude-flow sparc run integration "auth with user management"

# 5. Completion - Documentation and validation
npx claude-flow sparc run docs-writer "authentication API docs"

Parallel Execution with External Tools

Claude-Flow's --non-interactive flag enables integration with external orchestration tools for parallel execution:

# Example with hypothetical batchtool (external tool, not included)
# Run multiple SPARC modes concurrently
batchtool run --parallel \
  "npx claude-flow sparc run code 'user service' --non-interactive" \
  "npx claude-flow sparc run code 'auth service' --non-interactive" \
  "npx claude-flow sparc run tdd 'test suite' --non-interactive"

# Or use any parallel execution tool like GNU Parallel:
parallel -j 3 npx claude-flow sparc run {} --non-interactive ::: \
  "code 'user service'" \
  "code 'auth service'" \
  "tdd 'test suite'"

Note: batchtool is not included with claude-flow. The --non-interactive flag outputs JSON for integration with your preferred orchestration tools.

SPARC Features

17+ Specialized AI Modes for different development phases
Memory Persistence across SPARC sessions with namespaced storage
TDD Enforcement with Red-Green-Refactor cycle automation
Modular Design with <500 line file constraints
Environment Safety preventing credential exposure
External Tool Integration via --non-interactive flag for parallel execution
Non-Interactive Mode for automation and CI/CD integration
Auto-Skip Permissions by default (use --enable-permissions to prompt)
Quality Gates with automated code analysis and security review

Architecture

Claude-Flow uses a modular architecture with the following components:

Orchestrator: Central coordinator managing all system components
Terminal Manager: Handles terminal sessions with pooling and recycling
Memory Manager: Persistent storage with caching and indexing
Coordination Manager: Task scheduling and resource management
MCP Server: Tool integration via Model Context Protocol

Configuration

Default configuration file (claude-flow.config.json):

{
  "orchestrator": {
    "maxConcurrentAgents": 10,
    "taskQueueSize": 100,
    "healthCheckInterval": 30000,
    "shutdownTimeout": 30000
  },
  "terminal": {
    "type": "auto",
    "poolSize": 5,
    "recycleAfter": 10,
    "healthCheckInterval": 60000,
    "commandTimeout": 300000
  },
  "memory": {
    "backend": "hybrid",
    "cacheSizeMB": 100,
    "syncInterval": 5000,
    "conflictResolution": "crdt",
    "retentionDays": 30
  },
  "coordination": {
    "maxRetries": 3,
    "retryDelay": 1000,
    "deadlockDetection": true,
    "resourceTimeout": 60000,
    "messageTimeout": 30000
  },
  "mcp": {
    "transport": "stdio",
    "port": 3000,
    "tlsEnabled": false
  },
  "logging": {
    "level": "info",
    "format": "json",
    "destination": "console"
  }
}

Agent Types

Claude-Flow supports multiple agent types:

Coordinator: Plans and delegates tasks to other agents
Researcher: Gathers and analyzes information
Implementer: Writes code and creates solutions
Analyst: Identifies patterns and generates insights
Custom: User-defined agent types

🛠️ CLI Commands

Claude-Flow provides a comprehensive CLI for managing your AI orchestration system. For detailed command documentation, see the CLI Reference.

🌐 Global Options

-c, --config <path>: Path to configuration file
-v, --verbose: Enable verbose logging
--log-level <level>: Set log level (debug, info, warn, error)
--version: Show version information
--help: Show help for any command

📋 Core Commands

`init` - Initialize Claude Code Integration

npx claude-flow@latest init [options]
  -s, --sparc               Initialize with SPARC development environment (recommended)
  -f, --force               Overwrite existing files
  -m, --minimal             Create minimal configuration files

Recommended first-time setup:

npx claude-flow@latest init --sparc

Creates:

CLAUDE.md - AI-readable project instructions
.roomodes - 17 pre-configured SPARC development modes
memory-bank.md - Persistent memory documentation
coordination.md - Agent coordination guide
Complete folder structure for development

`start` - Start Orchestration System

npx claude-flow start [options]
  -d, --daemon              Run as daemon in background
  -p, --port <port>         MCP server port (default: 3000)

`status` - Show System Status

npx claude-flow status [options]
  -v, --verbose             Show detailed status information

`agent` - Manage AI Agents

npx claude-flow agent <subcommand>
  spawn <type>              Spawn a new agent (researcher/implementer/analyst/coordinator)
    --name <name>           Agent name
    --priority <1-10>       Agent priority
    --max-tasks <n>         Max concurrent tasks
  list                      List all active agents
  info <agent-id>          Get detailed agent information
  terminate <agent-id>      Terminate an agent

`task` - Manage Tasks

npx claude-flow task <subcommand>
  create <type> <desc>      Create a new task
    --priority <1-10>       Task priority
    --deps <task-ids>       Comma-separated dependency IDs
  list                      List all tasks
    --verbose               Show task descriptions
  status <task-id>          Get task status
  cancel <task-id>          Cancel a task
  workflow <file>           Execute workflow from file
    --async                 Run workflow asynchronously

`memory` - Manage Memory Bank

npx claude-flow memory <subcommand>
  query <search>            Search memory entries
    --namespace <ns>        Filter by namespace
    --limit <n>             Limit results
  store <key> <value>       Store information
    --namespace <ns>        Target namespace
  export <file>             Export memory to file
  import <file>             Import memory from file
  stats                     Show memory statistics
  cleanup                   Clean up old entries
    --days <n>              Entries older than n days

`mcp` - MCP Server Management

npx claude-flow mcp <subcommand>
  status                    Show MCP server status
  tools                     List available MCP tools
  config                    Show MCP configuration
  logs                      View MCP server logs
    --lines <n>             Number of log lines (default: 50)

`monitor` - Real-time Monitoring

npx claude-flow monitor [options]
  -i, --interval <seconds>  Update interval (default: 2)
  -c, --compact             Compact view mode
  -f, --focus <component>   Focus on specific component

`sparc` - SPARC Development Methodology 🆕

npx claude-flow sparc [subcommand] [options]
  "<task>"                  Run SPARC orchestrator (default mode)
  modes [--verbose]         List available SPARC development modes
  info <mode>               Show detailed mode information
  run <mode> "<task>"       Execute specific SPARC mode
  tdd "<feature>"           Run full TDD workflow
    --namespace <ns>        Use custom memory namespace
    --dry-run               Show configuration without executing
    --verbose               Show detailed output
    --non-interactive       Run with stream-json output (for automation)
    --enable-permissions    Enable permission prompts (default: skip)

Default Behavior Updates:

Simplified syntax: npx claude-flow sparc "build app" (no need for run sparc)
Permissions auto-skipped by default (use --enable-permissions to prompt)
Non-interactive mode for BatchTool orchestration

`claude` - Spawn Claude Instances with Enhanced Guidance 🆕

npx claude-flow claude <subcommand>
  spawn <task>              Spawn Claude with enhanced Claude-Flow guidance
    -t, --tools <tools>     Allowed tools (comma-separated)
    --no-permissions        Use --dangerously-skip-permissions flag
    -c, --config <file>     MCP config file path
    -m, --mode <mode>       Development mode (full/backend-only/frontend-only/api-only)
    --parallel              Enable parallel execution with multi-agent support
    --research              Enable web research with WebFetchTool
    --coverage <n>          Test coverage target percentage (default: 80)
    --commit <freq>         Commit frequency (phase/feature/manual)
    -v, --verbose           Enable verbose output
    -d, --dry-run           Show what would be executed without running
    
  batch <workflow-file>     Execute multiple Claude instances from workflow
    --dry-run               Show what would be executed without running

Each spawned Claude instance receives comprehensive guidance including:

Claude-Flow memory operations (npx claude-flow memory store/query)
System management commands (npx claude-flow status/monitor)
Agent coordination (when --parallel is used)
Mode-specific development focus
Coverage and commit strategy awareness
Example commands ready to use with the Bash tool

`config` - Configuration Management

npx claude-flow config <subcommand>
  show                      Show current configuration
  get <path>                Get specific config value
  set <path> <value>        Set config value
  init [file]               Initialize config file
  validate <file>           Validate config file

`session` - Session Management

npx claude-flow session <subcommand>
  list                      List active sessions
  info <session-id>         Get session information
  terminate <session-id>    End a session

`workflow` - Workflow Execution

npx claude-flow workflow <file> [options]
  --validate                Validate workflow without executing
  --async                   Run workflow asynchronously
  --watch                   Watch workflow progress

`help` - Get Help

npx claude-flow help [command]

🎯 Common Use Cases

Complete Agent & Task Workflow:

# Initialize and start the system
npx claude-flow init
npx claude-flow start --daemon

# Spawn a team of agents
npx claude-flow agent spawn researcher --name "Senior Researcher" --priority 8
npx claude-flow agent spawn analyst --name "Data Analyst" --priority 7
npx claude-flow agent spawn implementer --name "Lead Developer" --priority 9

# Create research task
TASK1=$(npx claude-flow task create research "Analyze authentication patterns" --priority 8 | grep "Task ID" | awk '{print $3}')

# Create analysis task dependent on research
TASK2=$(npx claude-flow task create analysis "Security audit findings" --priority 7 --deps $TASK1 | grep "Task ID" | awk '{print $3}')

# Create implementation task dependent on analysis
TASK3=$(npx claude-flow task create implementation "Build secure auth system" --priority 9 --deps $TASK2 | grep "Task ID" | awk '{print $3}')

# Assign tasks to appropriate agents
npx claude-flow task assign $TASK1 $(npx claude-flow agent list | grep researcher | awk '{print $2}')
npx claude-flow task assign $TASK2 $(npx claude-flow agent list | grep analyst | awk '{print $2}')
npx claude-flow task assign $TASK3 $(npx claude-flow agent list | grep implementer | awk '{print $2}')

# Monitor the workflow
npx claude-flow monitor

Code Development Workflow:

npx claude-flow agent spawn implementer --name "Backend Dev" --max-tasks 3
npx claude-flow agent spawn implementer --name "Frontend Dev" --max-tasks 3
npx claude-flow agent spawn coordinator --name "Tech Lead"
npx claude-flow workflow development-pipeline.json --watch

SPARC Development Workflow:

# Initialize SPARC environment
npx claude-flow init --sparc

# Complete feature development using SPARC methodology
npx claude-flow sparc run spec-pseudocode "user authentication system"
npx claude-flow sparc run architect "JWT auth service design"
npx claude-flow sparc tdd "implement secure authentication"
npx claude-flow sparc run security-review "auth vulnerability scan"
npx claude-flow sparc run integration "connect auth to user service"

# TDD-focused development
npx claude-flow sparc tdd "payment processing system"
npx claude-flow sparc tdd "real-time notifications"

# Architecture and design
npx claude-flow sparc run architect "microservices architecture"
npx claude-flow sparc run docs-writer "API documentation"

Enhanced Claude Spawn Examples:

# Backend API development with high test coverage
npx claude-flow claude spawn "build REST API with authentication" \
  --mode backend-only --coverage 95 --commit feature

# Frontend development with research capabilities
npx claude-flow claude spawn "create responsive dashboard" \
  --mode frontend-only --research --verbose

# Full-stack development with parallel execution
npx claude-flow claude spawn "implement user management system" \
  --parallel --coverage 90 --commit phase

# API design focus with custom tools
npx claude-flow claude spawn "design GraphQL schema" \
  --mode api-only --tools "View,Edit,GrepTool,LS"

Workflow Execution:

# Execute a predefined workflow
npx claude-flow workflow examples/development-config.json

# Execute workflow with monitoring
npx claude-flow workflow examples/research-workflow.json --watch

# Validate workflow before execution
npx claude-flow workflow my-workflow.json --validate

Workflow Example

Create a workflow file (example-workflow.json):

{
  "name": "Research and Analysis Workflow",
  "tasks": [
    {
      "id": "research-1",
      "type": "research",
      "description": "Research quantum computing basics",
      "assignTo": "researcher"
    },
    {
      "id": "analyze-1",
      "type": "analysis",
      "description": "Analyze research findings",
      "dependencies": ["research-1"],
      "assignTo": "analyst"
    },
    {
      "id": "report-1",
      "type": "report",
      "description": "Generate summary report",
      "dependencies": ["analyze-1"],
      "assignTo": "coordinator"
    }
  ]
}

Execute the workflow:

claude-flow task workflow example-workflow.json

Development

Prerequisites

Deno 1.38+ or Node.js 16+ (Install Deno: https://deno.land/#installation)
Git

Setup

git clone https://github.com/ruvnet/claude-code-flow.git
cd claude-flow
deno task dev

Testing

deno task test

Building

deno task build

API Usage

Claude-Flow can also be used programmatically:

import { Orchestrator } from 'claude-flow';

const orchestrator = new Orchestrator(config);
await orchestrator.initialize();

// Spawn an agent
const sessionId = await orchestrator.spawnAgent({
  id: 'agent-1',
  name: 'Research Agent',
  type: 'researcher',
  // ... other properties
});

// Create and assign a task
await orchestrator.assignTask({
  id: 'task-1',
  type: 'research',
  description: 'Research AI trends',
  // ... other properties
});

Contributing

Contributions are welcome! Please read our Contributing Guide for details.

License

MIT License - see LICENSE file for details.

🔌 Integration with Claude Code

Claude-Flow seamlessly integrates with Claude Code through the CLAUDE.md file created by npx claude-flow init. This enables:

Automatic Context Loading: Claude Code reads your project configuration
Build Command Integration: All build/test commands are available to Claude
Memory Persistence: Claude remembers context across sessions
Enhanced Guidance: Spawned Claude instances receive detailed Claude-Flow instructions
SPARC Methodology: Built-in support for systematic development with 16+ specialized AI modes

Use with Claude Code:

# Initialize integration
npx claude-flow init

# Spawn Claude with enhanced Claude-Flow guidance
npx claude-flow claude spawn "your task here" --research --parallel

# Claude receives:
# - Instructions on using npx claude-flow commands
# - Memory operations (store/query)
# - Agent coordination capabilities
# - Mode-specific development guidance

🏢 Enterprise Features

🔐 Security: Token-based auth, rate limiting, audit logging
📊 Monitoring: Real-time metrics, performance tracking, health checks
🔄 Reliability: Circuit breakers, automatic retries, graceful degradation
📈 Scalability: Horizontal scaling, load balancing, resource pooling
🛡️ Compliance: Audit trails, data retention policies, access controls

📖 Resources

Documentation

Complete Documentation - All guides and references
API Documentation - Programmatic usage
Examples - Sample configurations and workflows
Memory System Docs - In-depth memory bank documentation

Community & Support

GitHub Issues - Bug reports and feature requests
GitHub Discussions - Community forum
Discord Server - Real-time chat and support
Stack Overflow - Q&A

Tutorials & Guides

Video Tutorials - Step-by-step video guides
Blog Posts - Tips, tricks, and use cases
Case Studies - Real-world implementations

🚀 Roadmap

Q1 2025

Initial release with core orchestration
Memory bank implementation
MCP integration
Claude Code integration (init command)
Web UI for visual orchestration
Plugin system for custom agent types

Q2 2025

Distributed orchestration support
Enhanced monitoring dashboard
Integration with more AI models
Workflow templates library
Cloud deployment options

Q3 2025

🤝 Contributing

We welcome contributions! See our Contributing Guide for:

Code of Conduct
Development setup
Submission guidelines
Coding standards
Testing requirements

📄 License

MIT License - see LICENSE file for details.

🙏 Acknowledgments

Built on top of Claude Code and Anthropic's Claude AI
Inspired by the SPARC methodology
Thanks to all contributors and the Claude community

📊 Stats

Built with ❤️ by rUv for the Claude community

Name		Name	Last commit message	Last commit date
Latest commit History 35 Commits
.github		.github
.roo		.roo
bin		bin
coordination		coordination
docs		docs
examples		examples
mcp_config		mcp_config
memory		memory
plans		plans
research		research
scripts		scripts
src		src
test-results		test-results
tests		tests
.gitignore		.gitignore
.npmignore		.npmignore
.releaserc.json		.releaserc.json
.roomodes		.roomodes
CLAUDE.md		CLAUDE.md
LICENSE		LICENSE
README.md		README.md
claude-flow-1.0.2.tgz		claude-flow-1.0.2.tgz
codecov.yml		codecov.yml
coordination.md		coordination.md
deno.json		deno.json
deno.lock		deno.lock
memory-bank.md		memory-bank.md
package-lock.json		package-lock.json
package.json		package.json
tsconfig.json		tsconfig.json

License

corticalstack/claude-code-flow

Folders and files

Latest commit

History

Repository files navigation

🌊 Claude-Flow: Agent Orchestration Platform for Claude-Code

🎉 What's New in v1.0.41

🎯 Transform Your Development Workflow

🌟 Why Claude-Flow?

📦 Installation

🚀 Get started in 30 seconds

🏗️ Core Features

🤖 Multi-Agent Orchestration

🧠 Intelligent Memory Bank

⚡ SPARC Development

🎯 Smart Task Scheduling

🔒 Enterprise Security

🌐 MCP Integration

⚡ Quick Start

🎯 Option 1: NPX (Recommended)

🦕 Option 2: Deno (For Developers)

🔧 Option 3: From Source (For Contributors)

📚 Documentation

💡 Quick Start Guide

1. Initialize Claude Code Integration

2. Start the Orchestrator

3. Spawn Agents

4. Create and Manage Tasks

5. Spawn Claude Instances 🆕

6. Monitor System Status

🚀 SPARC Development Methodology

Available SPARC Modes

SPARC Workflow

Parallel Execution with External Tools

SPARC Features

Architecture

Configuration

Agent Types

🛠️ CLI Commands

🌐 Global Options

📋 Core Commands

init - Initialize Claude Code Integration

start - Start Orchestration System

status - Show System Status

agent - Manage AI Agents

task - Manage Tasks

memory - Manage Memory Bank

mcp - MCP Server Management

monitor - Real-time Monitoring

sparc - SPARC Development Methodology 🆕

claude - Spawn Claude Instances with Enhanced Guidance 🆕

config - Configuration Management

session - Session Management

workflow - Workflow Execution

help - Get Help

🎯 Common Use Cases

Workflow Example

Development

Prerequisites

Setup

Testing

Building

API Usage

Contributing

License

🔌 Integration with Claude Code

🏢 Enterprise Features

📖 Resources

Documentation

Community & Support

Tutorials & Guides

🚀 Roadmap

Q1 2025

Q2 2025

Q3 2025

🤝 Contributing

📄 License

🙏 Acknowledgments

📊 Stats

`init` - Initialize Claude Code Integration

`start` - Start Orchestration System

`status` - Show System Status

`agent` - Manage AI Agents

`task` - Manage Tasks

`memory` - Manage Memory Bank

`mcp` - MCP Server Management

`monitor` - Real-time Monitoring

`sparc` - SPARC Development Methodology 🆕

`claude` - Spawn Claude Instances with Enhanced Guidance 🆕

`config` - Configuration Management

`session` - Session Management

`workflow` - Workflow Execution

`help` - Get Help

Packages