Agent App: FastAPI, Streamlit and Postgres

The Agent App is our go-to workspace for building agentic systems. It contains:

• A FastAPI server for serving Agents, Teams and Workflows.
• A streamlit application for debugging and testing. This streamlit app is very versatile and can be used as an admin interface for the agentic system and shows all sorts of data.
• A postgres database for session and vector storage.

It’s designed to run locally using docker and in production on AWS.

Setup

1. Create and activate a virtual environment

   Mac

   python3 -m venv .venv
   source .venv/bin/activate
   

2. Install Agno

   Mac

   pip install -U "agno[aws]"
   

3. Install uv and docker

   • Install uv for managing your python environment.

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

   • Install docker desktop to run your app locally
4. Export your OpenAI key

   Mac

   export OPENAI_API_KEY=sk-***
   

   Agno is compatible with any model provider; simply update the agents in the workspace.

Create your Agent App codebase

Create your codebase using the agent-app template, give it any name you like.

Mac

ag ws create --template agent-app --name agent-app

This will create a folder named agent-app with the following structure:

agent-app                     # root directory
├── agents                  # your Agents go here
├── api                     # your Api routes go here
├── ui                      # your Streamlit apps go here
├── db                      # your database tables go here
├── Dockerfile              # Dockerfile for the application
├── pyproject.toml          # python project definition
├── requirements.txt        # python dependencies generated using pyproject.toml
├── scripts                 # helper scripts
├── utils                   # shared utilities
└── workspace               # Agno workspace directory
    ├── dev_resources.py    # dev resources running locally
    ├── prd_resources.py    # production resources running on AWS
    ├── secrets             # secrets
    └── settings.py         # Agno workspace settings

Run your Agent App locally

cd into the agent-app folder

cd agent-app

Start your Agent App using the following command:

terminal

ag ws up

Press Enter to confirm and give a few seconds for the image to download (only the first time). Verify container status and view logs on the docker dashboard.

• Open localhost:8501 to view the streamlit UI.
• Open localhost:8000/docs to view the FastAPI routes.

Notes:

• The Agents are defined in the agents folder.
• The streamlit apps are defined in the ui folder
• The API routes are defined in the api folder.

Stop local workspace

Play around and stop the workspace using:

terminal

ag ws down

Next

Congratulations on running your AI App locally. Next Steps:

• Run your Agent App on AWS
• Read how to update workspace settings
• Read how to create a git repository for your workspace
• Read how to manage the development application
• Read how to format and validate your code
• Read how to add python libraries
• Chat with us on discord