Deploy: AWS

Deploy agents to AWS ECS/Fargate using praisonai deploy

Deploy agents to AWS ECS/Fargate using praisonai deploy run --type cloud --provider aws.

Quick Start - CLI

1. Install PraisonAI

   pip install praisonai
   
2. Set Environment Variables

   export OPENAI_API_KEY="your-key"
   export AWS_ACCESS_KEY_ID="your-aws-key"
   export AWS_SECRET_ACCESS_KEY="your-aws-secret"
   
3. Initialize AWS Config

   praisonai deploy init --file agents.yaml --type cloud --provider aws
   
4. Check Readiness

   praisonai deploy doctor --provider aws
   
5. Deploy to AWS

   praisonai deploy run --file agents.yaml --type cloud --provider aws
   

   Expected Output:

   🚀 Starting deployment...
   
   ☁️  Deploying to AWS ECS/Fargate
     • Region: us-east-1
     • Service: praisonai-service
     • CPU: 256
     • Memory: 512MB
   
   📦 Building and pushing Docker image...
   🚀 Creating ECS task definition...
   🔄 Deploying to Fargate...
   
   ✅ Deployment successful!
   🔗 URL: https://praisonai-service.us-east-1.amazonaws.com
   
   Metadata:
     • provider: aws
     • region: us-east-1
     • cluster: praisonai-cluster
     • service: praisonai-service
     • task_definition: praisonai-task:1
   
6. Verify

   curl https://praisonai-service.us-east-1.amazonaws.com/health
   

Quick Start - SDK

1. Create Deploy Script

   from praisonai.deploy import Deploy, DeployConfig, DeployType, CloudProvider
   from praisonai.deploy.models import CloudConfig
   
   config = DeployConfig(
       type=DeployType.CLOUD,
       cloud=CloudConfig(
           provider=CloudProvider.AWS,
           region="us-east-1",
           service_name="praisonai-service",
           cpu="256",
           memory="512",
           min_instances=1,
           max_instances=10
       )
   )
   
   deploy = Deploy(config, "agents.yaml")
   result = deploy.deploy()
   
   print(f"URL: {result.url}")
   
2. Run

   python deploy_aws.py
   

agents.yaml with AWS Config

framework: praisonai
topic: helpful assistant
roles:
  assistant:
    role: Assistant
    goal: Help users with their questions
    backstory: You are a helpful assistant
    tasks:
      help_task:
        description: Answer user questions
        expected_output: Helpful response

deploy:
  type: cloud
  cloud:
    provider: aws
    region: "us-east-1"
    service_name: "praisonai-service"
    cpu: "256"
    memory: "512"
    min_instances: 1
    max_instances: 10
    cluster_name: "praisonai-cluster"
    env_vars:
      OPENAI_API_KEY: "${OPENAI_API_KEY}"

AWS Cloud Config Options

Field	Type	Default	Description
provider	string	-	Must be aws
region	string	-	AWS region (e.g., us-east-1)
service_name	string	-	ECS service name
cpu	string	256	CPU units (256, 512, 1024, etc.)
memory	string	512	Memory in MB
min_instances	int	1	Minimum running instances
max_instances	int	10	Maximum instances for scaling
cluster_name	string	null	ECS cluster name
task_definition	string	null	Task definition name
env_vars	dict	null	Environment variables

Check Deployment Status

praisonai deploy status --file agents.yaml

Expected Output:

📊 Checking deployment status...

╭─────────────────────────────────────────────────────────────────────────────╮
│                            Deployment Status                                 │
├─────────────────┬───────────────────────────────────────────────────────────┤
│ Property        │ Value                                                     │
├─────────────────┼───────────────────────────────────────────────────────────┤
│ State           │ RUNNING                                                   │
│ Service Name    │ praisonai-service                                         │
│ Provider        │ aws                                                       │
│ Region          │ us-east-1                                                 │
│ URL             │ https://praisonai-service.us-east-1.amazonaws.com         │
│ Healthy         │ ✅ Yes                                                    │
│ Instances       │ 1/1                                                       │
╰─────────────────┴───────────────────────────────────────────────────────────╯

Destroy Deployment

praisonai deploy destroy --file agents.yaml --yes

Troubleshooting

Issue	Fix
AWS credentials	export AWS_ACCESS_KEY_ID=...
Region not set	Add region to agents.yaml
Permission denied	Check IAM permissions for ECS
Deploy failed	Run praisonai deploy doctor --provider aws

Manual AWS CLI Validation (Optional)

These commands are for manual validation only. Use praisonai deploy for deployment.

# Verify AWS CLI
aws sts get-caller-identity

# List ECS clusters
aws ecs list-clusters

# Describe service
aws ecs describe-services --cluster praisonai-cluster --services praisonai-service

# View logs
aws logs get-log-events --log-group-name /ecs/praisonai-service --log-stream-name <stream>

Related

• Deploy CLI Overview - All deploy commands
• API Deploy - Deploy as local API server
• Docker Deploy - Deploy to Docker
• GCP Deploy - Deploy to Google Cloud Run