Welcome to Agent OS AWS: a robust, production-ready application for serving Agentic Applications as an API. It includes:

• An AgentOS instance: An API-based interface for production-ready Agentic Applications.
• A PostgreSQL database for storing Agent sessions, knowledge, and memories.
• A set of pre-built Agents, Teams and Workflows to use as a starting point.

For more information, checkout Agno and give it a ⭐️

Follow these steps to get your Agent OS up and running:

Get Docker Desktop should be installed and running. Get OpenAI API key

git clone https://github.com/agno-agi/agent-infra-aws.git
cd agent-infra-aws

We use GPT 5 Mini as the default model, please export the OPENAI_API_KEY environment variable to get started.

export OPENAI_API_KEY="YOUR_API_KEY_HERE"

Note: You can use any model provider, just update the agents in the /agents folder and add the required libraries to the pyproject.toml and requirements.txt files.

This examples includes 2 environments, dev and prd.

ag infra up --env dev

This command starts:

• The AgentOS instance, which is a FastAPI server, running on http://localhost:8000.
• The PostgreSQL database, accessible on localhost:5432.

Once started, you can:

• Test the API at http://localhost:8000/docs.

• Open the Agno AgentOS UI.
• Connect your OS with http://localhost:8000 as the endpoint. You can name it AgentOS (or any name you prefer).
• Explore all the features of AgentOS or go straight to the Chat page to interact with your Agents.

To load the knowledge base, you can use the following command:

docker exec -it agent-infra-aws-agentos python -m agents.agno_assist

When you're done, stop the application using:

ag infra down

ag infra up --env prd

• AWS Security Groups
• AWS Secrets
• AWS Db Subnet Group
• AWS RDS Instance
• AWS Load Balancer
• AWS Target Group
• AWS Listener
• AWS ECS Cluster
• AWS ECS Service
• AWS ECS Task
• AWS ECS Task Definition

Your ECS tasks are already enabled with SSH access. SSH into the production containers using:

ECS_CLUSTER=agent-infra-aws-prd-cluster
TASK_ARN=$(aws ecs list-tasks --cluster agent-infra-aws-prd-cluster --query "taskArns[0]" --output text)
CONTAINER_NAME=agent-infra-aws-agentos

aws ecs execute-command --cluster $ECS_CLUSTER \
    --task $TASK_ARN \
    --container $CONTAINER_NAME \
    --interactive \
    --command "zsh"

After SSHing into the container, run the following command to load the knowledge base:

python -m agents.agno_assist

Note: Please update the ECS cluster and the container name to match your prd resources.

The /agents folder contains pre-built agents, teams, and workflows that you can use as a starting point.

• Agno Assist: An Agent that can help answer questions about Agno and provide support for developers working with Agno.
• Web Search Agent: A Agent that can search the web based on the user's query.

The /teams folder contains pre-built teams that you can use as a starting point.

• Multilingual Team: A team consisting of member agents that specialize in different languages and can translate and provide cultural insights.
• Reasoning Research Team: A team consisting of member agents that can research and provide insights.

The /workflows folder contains pre-built workflows that you can use as a starting point.

• Investment Workflow: A workflow that creates a comprehensive investment strategy report based on the user's request.
• Research Workflow: A workflow that creates a comprehensive research report based on the user's request and provides a summary of the research findings.

To setup your local virtual environment:

We use uv for python environment and package management. Install it by following the the uv documentation or use the command below for unix-like systems:

curl -LsSf https://astral.sh/uv/install.sh | sh

Run the dev_setup.sh script. This will create a virtual environment and install project dependencies:

./scripts/dev_setup.sh

Activate the created virtual environment:

source .venv/bin/activate

(On Windows, the command might differ, e.g., .venv\Scripts\activate)

If you need to add or update python dependencies:

Add or update your desired Python package dependencies in the [dependencies] section of the pyproject.toml file.

The requirements.txt file is used to build the application image. After modifying pyproject.toml, regenerate requirements.txt using:

./scripts/generate_requirements.sh

To upgrade all existing dependencies to their latest compatible versions, run:

./scripts/generate_requirements.sh upgrade

Rebuild your Docker images to include the updated dependencies, set build_images to true in the infra/settings.py file and run the following command:

ag infra up -f

Need help, have a question, or want to connect with the community?

• 📚 Read the Agno Docs for more in-depth information.
• 🚀 Read the Deployment Guide for more in-depth information.
• 💬 Chat with us on Discord for live discussions.
• ❓ Ask a question on Discourse for community support.
• 🐛 Report an Issue on GitHub if you find a bug or have a feature request.