Multi-Agent Systems

┌─────────────────────────┐
│        User             │
└───────────┬─────────────┘
            │
            ▼
┌─────────────────────────┐
│  Project Manager Agent  │ (Local - Planning & Coordination)
│  - Analyzes requests    │
│  - Breaks down tasks    │
│  - Delegates to workers │
│  - Reviews outputs      │
│  - Reports to user      │
└───────────┬─────────────┘
            │
            ▼
┌─────────────────────────┐
│   Developer Agent       │ (Daytona Sandbox - Execution)
│  - Executes code        │
│  - Manages files        │
│  - Runs tests           │
│  - Starts services      │
│  - Provides previews    │
└─────────────────────────┘

import Anthropic from '@anthropic-ai/sdk';
import { createSandbox } from '@daytona/sdk';

// Project Manager Agent (runs locally)
const projectManager = new Anthropic({
  apiKey: process.env.ANTHROPIC_API_KEY,
});

// Create Developer Agent sandbox
const devSandbox = await createSandbox({
  name: 'developer-agent',
  public: true,
});

// Install Claude Agent SDK in sandbox
await devSandbox.exec(
  'curl -fsSL https://claude.ai/agent/install.sh | sh'
);

// Project Manager system prompt
const PM_SYSTEM = `You are a Project Manager Agent.

When you need development work:
1. Analyze the user request
2. Break it into clear tasks
3. Delegate using <developer_task> tags
4. Review the Developer Agent's output
5. Decide if more work is needed
6. Say "TASK_COMPLETE" when finished

Example delegation:
<developer_task>
Create a web game with:
- HTML/CSS/JavaScript
- Canvas graphics
- Physics simulation
- Keyboard controls
- Start on port 80
</developer_task>`;

// Main interaction loop
async function runMultiAgent(userRequest: string) {
  let conversationHistory = [];
  
  conversationHistory.push({
    role: 'user',
    content: userRequest,
  });
  
  while (true) {
    // Project Manager processes request
    const pmResponse = await projectManager.messages.create({
      model: 'claude-sonnet-4-20250514',
      max_tokens: 4096,
      system: PM_SYSTEM,
      messages: conversationHistory,
    });
    
    console.log('[Project Manager]:', pmResponse.content);
    
    // Check if task is complete
    if (pmResponse.content.includes('TASK_COMPLETE')) {
      break;
    }
    
    // Extract developer task if present
    const taskMatch = pmResponse.content.match(
      /<developer_task>([\s\S]*?)<\/developer_task>/
    );
    
    if (taskMatch) {
      const developerTask = taskMatch[1].trim();
      
      console.log('[Delegating to Developer Agent]...');
      
      // Execute in Developer Agent sandbox
      const devResult = await executeDeveloperTask(
        devSandbox,
        developerTask
      );
      
      console.log('[Developer Agent]:', devResult);
      
      // Add to conversation
      conversationHistory.push({
        role: 'assistant',
        content: pmResponse.content,
      });
      conversationHistory.push({
        role: 'user',
        content: `Developer Agent completed the task:\n${devResult}`,
      });
    }
  }
}

// Execute task in Developer Agent
async function executeDeveloperTask(
  sandbox: Sandbox,
  task: string
): Promise<string> {
  // Run Claude agent in sandbox with task
  const result = await sandbox.exec(
    `claude-agent run "${task.replace(/"/g, '\\"')}"`,
    { env: { ANTHROPIC_API_KEY: process.env.SANDBOX_ANTHROPIC_API_KEY } }
  );
  
  return result.stdout;
}

// Example usage
await runMultiAgent('Build a lunar lander web game');

// Cleanup
await devSandbox.delete();

[Project Manager]: I'll help you create a lunar lander web game! 
Let me delegate this to the Developer Agent.

<developer_task>
Create a lunar lander web game with:
- HTML/CSS/JavaScript based
- Canvas graphics for rendering
- Physics simulation (gravity, thrust, velocity)
- Keyboard controls (arrow keys)
- Landing detection (safe vs crash)
- Fuel management system
- Start the game on port 80
</developer_task>

[Delegating to Developer Agent]...

[Developer Agent]: I'll build a complete lunar lander game.
🔨 Write /home/daytona/index.html
🔨 Write /home/daytona/game.js
🔨 Write /home/daytona/style.css
🔨 Bash: python3 -m http.server 80

Your Lunar Lander game is live at:
🌐 https://80-17ac1c0f-d684-4122-93b5-8f52fd5393f8.proxy.daytona.works

[Project Manager]: Excellent! The Developer Agent has successfully 
created your lunar lander web game. The implementation includes:

✓ Physics simulation with gravity and thrust
✓ Canvas-based graphics
✓ Keyboard controls
✓ Landing detection
✓ Fuel management
✓ Web server running on port 80

TASK_COMPLETE

// Manager runs locally with user credentials
const manager = new Agent({ 
  apiKey: process.env.MANAGER_API_KEY,
  runLocation: 'local'
});

// Worker runs in isolated sandbox
const worker = await createAgentSandbox({
  apiKey: process.env.WORKER_API_KEY,  // Separate key
  isolated: true,
  resources: {
    cpu: '2',
    memory: '4Gi'
  }
});

// Manager: Lightweight, always running
const manager = createManager({ 
  model: 'claude-haiku-4',  // Fast, cheap
  maxTokens: 1024
});

// Workers: Powerful, ephemeral
const worker = await createWorker({
  model: 'claude-sonnet-4',  // Capable, thorough
  maxTokens: 8192,
  sandbox: {
    autoDelete: true,  // Clean up after task
    timeout: '30m'
  }
});

const tasks = [
  { type: 'frontend', description: 'Build React UI' },
  { type: 'backend', description: 'Create API server' },
  { type: 'tests', description: 'Write test suite' },
];

// Create specialized sandboxes
const workers = await Promise.all([
  createSandbox({ name: 'frontend-agent', image: 'node:20' }),
  createSandbox({ name: 'backend-agent', image: 'python:3.11' }),
  createSandbox({ name: 'test-agent', image: 'node:20' }),
]);

// Execute tasks in parallel
const results = await Promise.all(
  tasks.map((task, i) => 
    executeAgentTask(workers[i], task.description)
  )
);

// Manager integrates results
const integration = await manager.integrate(results);

const team = {
  architect: await createAgent({
    role: 'Software Architect',
    expertise: 'System design, patterns, best practices',
    sandbox: architectSandbox,
  }),
  
  developer: await createAgent({
    role: 'Developer',
    expertise: 'Implementation, coding, debugging',
    sandbox: devSandbox,
  }),
  
  tester: await createAgent({
    role: 'QA Engineer',
    expertise: 'Testing, validation, quality assurance',
    sandbox: testSandbox,
  }),
  
  devops: await createAgent({
    role: 'DevOps Engineer',
    expertise: 'Deployment, monitoring, infrastructure',
    sandbox: opsSandbox,
  }),
};

// Workflow coordination
async function buildFeature(requirement: string) {
  // 1. Architect designs system
  const design = await team.architect.design(requirement);
  
  // 2. Developer implements
  const code = await team.developer.implement(design);
  
  // 3. Tester validates
  const testResults = await team.tester.test(code);
  
  // 4. DevOps deploys
  if (testResults.passed) {
    return await team.devops.deploy(code);
  }
}

const manager = createManager({
  system: `When handling complex requests:
  
  1. Analyze requirements
  2. Identify required expertise
  3. Delegate to appropriate specialist
  4. Validate each step's output
  5. Coordinate dependencies
  6. Integrate final solution
  
  Available specialists:
  - data_analyst: For data processing and analysis
  - ml_engineer: For model training and deployment
  - backend_dev: For API and server development
  - frontend_dev: For UI/UX implementation`
});

// Manager uses XML tags for clear delegation
const managerPrompt = `Use these tags to delegate:

<data_analysis>
Task description for data analyst
</data_analysis>

<code_implementation>
Task description for developer
</code_implementation>

<testing>
Task description for tester
</testing>`;

// Parse and route
function routeTask(response: string) {
  if (response.includes('<data_analysis>')) {
    return { agent: 'data_analyst', task: extractTag(response, 'data_analysis') };
  }
  // ... other routing logic
}

interface TaskHandoff {
  from: string;
  to: string;
  task: string;
  context: Record<string, any>;
  artifacts: string[];
}

async function handoff(params: TaskHandoff) {
  console.log(`[${params.from}] → [${params.to}]: ${params.task}`);
  
  return await agents[params.to].execute({
    task: params.task,
    context: params.context,
    artifacts: params.artifacts,
  });
}

const roles = {
  manager: {
    responsibilities: [
      'Analyze user requests',
      'Plan task breakdown',
      'Delegate to specialists',
      'Review outputs',
      'Coordinate integration'
    ],
    capabilities: ['planning', 'coordination', 'review'],
    constraints: ['no code execution', 'no direct file access']
  },
  
  worker: {
    responsibilities: [
      'Execute assigned tasks',
      'Implement solutions',
      'Report progress',
      'Handle errors'
    ],
    capabilities: ['code_execution', 'file_management', 'testing'],
    constraints: ['task scope only', 'no planning']
  }
};

async function resilientDelegation(
  task: string,
  maxRetries = 3
) {
  for (let attempt = 1; attempt <= maxRetries; attempt++) {
    try {
      const result = await worker.execute(task);
      
      // Manager validates result
      if (await manager.validate(result)) {
        return result;
      }
      
      // Invalid result - provide feedback
      task = await manager.provideFeedback(result);
      
    } catch (error) {
      console.log(`Attempt ${attempt} failed:`, error);
      
      if (attempt === maxRetries) {
        return await manager.handleFailure(task, error);
      }
      
      // Manager adjusts task based on error
      task = await manager.adjustTask(task, error);
    }
  }
}

class AgentPool {
  private workers: Sandbox[] = [];
  
  async getWorker(): Promise<Sandbox> {
    // Reuse idle worker or create new one
    const idle = this.workers.find(w => w.status === 'idle');
    if (idle) return idle;
    
    const worker = await createSandbox();
    this.workers.push(worker);
    return worker;
  }
  
  async cleanup() {
    // Clean up all workers
    await Promise.all(
      this.workers.map(w => w.delete())
    );
  }
}

interface TaskProgress {
  taskId: string;
  agent: string;
  status: 'queued' | 'in_progress' | 'completed' | 'failed';
  progress: number;  // 0-100
  output?: string;
  error?: string;
}

class MultiAgentOrchestrator {
  private tasks = new Map<string, TaskProgress>();
  
  async delegate(agent: string, task: string) {
    const taskId = generateId();
    
    this.tasks.set(taskId, {
      taskId,
      agent,
      status: 'queued',
      progress: 0,
    });
    
    // Execute with progress updates
    await this.executeWithTracking(taskId, agent, task);
  }
  
  getProgress(taskId: string): TaskProgress {
    return this.tasks.get(taskId);
  }
}

// Manager coordinates full-stack build
const result = await manager.run(`
  Build a todo app with:
  - React frontend
  - Node.js API
  - PostgreSQL database
  - Full test coverage
`);

// Manager delegates to specialists:
// 1. Frontend agent → React UI
// 2. Backend agent → API server
// 3. Database agent → Schema & migrations
// 4. Test agent → Integration tests
// 5. DevOps agent → Deployment

// Data processing workflow
const pipeline = await manager.orchestrate([
  { agent: 'ingestion', task: 'Fetch data from API' },
  { agent: 'cleaning', task: 'Clean and validate data' },
  { agent: 'analysis', task: 'Generate insights' },
  { agent: 'visualization', task: 'Create dashboards' },
  { agent: 'reporting', task: 'Write summary report' },
]);

// R&D workflow with specialists
const research = await manager.coordinate({
  literature_review: 'Research agent surveys papers',
  experimentation: 'ML agent runs experiments',
  analysis: 'Stats agent analyzes results',
  documentation: 'Writer agent creates report',
});