Welcome to the Simple Agent API: a robust, production-ready application for serving Agents as an API. It includes:
  • A FastAPI server for handling API requests.
  • A PostgreSQL database for storing Agent sessions, knowledge, and memories.
  • A set of pre-built Agents to use as a starting point.

​
Quickstart

Follow these steps to get your Agent API up and running: Prerequisites: Docker Desktop should be installed and running.
1

Clone the repo

git clone https://github.com/agno-agi/agent-api.git
cd agent-api
2

Export your OpenAI key

export OPENAI_API_KEY=sk-***
3

Start the application

docker compose up -d
4

Test the application

This command starts:
  • The FastAPI server, running on localhost:8000.
  • The PostgreSQL database, accessible on localhost:5432.
Once started, you can:
  • Test the API at localhost:8000/docs.
  • Connect to Agno Playground or Agent UI:
    • Open the Agno Playground app.agno.com/playground/agents.
    • Add http://localhost:8000 as a new endpoint. You can name it Agent API (or any name you prefer).
    • Select your newly added endpoint and start chatting with your Agents.
5

Stop the application

docker compose down

​
Folder structure

The agent-api folder contains the following structure: 
agent-api                     # root directory
├── agents                  # add your Agents here
├── api                     # add fastApi routes here
├── db                      # add database tables here
├── Dockerfile              # Dockerfile for the application
├── pyproject.toml          # python project definition
├── requirements.txt        # python dependencies generated by pyproject.toml
├── scripts                 # helper scripts

​
Prebuilt Agents

The /agents folder contains pre-built agents that you can use as a starting point.
  • Web Search Agent: A simple agent that can search the web.
  • Agno Assist: An Agent that can help answer questions about Agno.
    • Important: Make sure to load the agno_assist knowledge base before using this agent.
  • Finance Agent: An agent that uses the Yahoo Finance API to get stock prices and financial data.

​
Managing Python Dependencies

1

Modify pyproject.toml

Add or update your desired Python package dependencies in the [tool.poetry.dependencies] section of the pyproject.toml file.
2

Generate requirements.txt

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
3

Rebuild Docker Images

Rebuild your Docker images to include the updated dependencies:
docker compose up -d --build

​
Running in Production

This repository includes a Dockerfile for building a production-ready container image of the application. The general process to run in production is:
  1. Update the scripts/build_image.sh file and set your IMAGE_NAME and IMAGE_TAG variables.
  2. Build and push the image to your container registry: 
    ./scripts/build_image.sh
  3. Run in your cloud provider of choice.

​
Detailed Steps

​
1. Configure for Production

  • Ensure your production environment variables (e.g., OPENAI_API_KEY, database connection strings) are securely managed. Most cloud providers offer a way to set these as environment variables for your deployed service.
  • Review the agent configurations in the /agents directory and ensure they are set up for your production needs (e.g., correct model versions, any production-specific settings).

​
2. Build Your Production Docker Image

Update the scripts/build_image.sh script to set your desired IMAGE_NAME and IMAGE_TAG (e.g., your-repo/agent-api:v1.0.0). Run the script to build and push the image: 
./scripts/build_image.sh

​
3. Deploy to a Cloud Service

With your image in a registry, you can deploy it to various cloud services that support containerized applications. Some common options include: Serverless Container Platforms:
  • Google Cloud Run: A fully managed platform that automatically scales your stateless containers.
  • AWS App Runner: Makes it easy to deploy containerized web applications and APIs at scale.
  • Azure Container Apps: Build and deploy modern apps and microservices using serverless containers.
Container Orchestration Services: Platform as a Service (PaaS) with Docker Support:
  • Railway.app: Simple deployment from a Dockerfile.
  • Render: Simplifies deploying Docker containers, databases, and static sites.
  • Heroku: Supports deploying Docker containers.
Specialized Platforms:
  • Modal: Platform for running Python code in the cloud, can serve web endpoints.
The specific deployment steps will vary depending on the chosen provider. Generally, you'll point the service to your container image in the registry and configure port mapping (application runs on port 8000 by default), environment variables, scaling, and database connections.

​
4. Database Configuration

The default docker-compose.yml sets up a PostgreSQL database for local development. In production, use a managed database service (e.g., AWS RDS, Google Cloud SQL, Azure Database for PostgreSQL). Ensure your deployed application is configured with the correct database connection URL for your production database, usually via environment variables.

​
Additional Information

Congratulations on running your Agent API.