Getting Started with SuperAGI: Infrastructure for building useful Autonomous AI Agents

4 min readMay 23, 2023

SuperAGI is an open-source platform providing infrastructure to build autonomous AI agents. Designed to run multiple agents concurrently, SuperAGI’s diverse set of features and tools allows developers to spawn, deploy, and manage AI agents with ease.

This article will walk you through the initial setup and configuration of SuperAGI. By the end, you will have a working SuperAGI environment ready to run your autonomous AI agents.

⭐️ Key Features of SuperAGI

Extend Agent Capabilities with Tools: You can add capabilities to your agents by selecting tools from an ever-growing library or build your own custom tool.
Run Concurrent Agents Seamlessly: SuperAGI allows you to run multiple agents simultaneously, maximizing efficiency and achieving parallel processing.
Open Source: As an open-source platform, SuperAGI encourages developers to join its community and contribute to making the platform better.
GUI: With a user-friendly graphical interface, managing and interacting with your agents becomes a breeze.
Action Console: This feature lets you interact with agents by providing input, permissions, and more.
Multi-Model Agents: You can customize your agents using different models to tailor their behavior to specific tasks.

Screenshots

CLI

GUI

Prerequisites

SuperAGI requires Pinecone setup. Before proceeding, ensure you have installed and configured Pinecone. Along with this, you will need Python installed on your system.

🛠 Setting Up SuperAGI

1. Download the Repository: Open your terminal and run the following command to clone the SuperAGI repository:

git clone https://github.com/TransformerOptimus/SuperAGI.git

Alternatively, download the repository directly from the GitHub page as a zip file. After downloading, unzip the file in your desired directory.

2. Navigate to the Directory: Once the repository is cloned or unzipped, navigate to the SuperAGI directory using the command:

cd SuperAGI

🖥 Setting up Virtual Environment

A Python virtual environment isolates the packages required for a specific project from other packages installed on your system, preventing potential compatibility issues.

Here’s how you can set up a virtual environment on your system:

For 🐧Linux and 🍎Mac:

Open a terminal window.

2. Install the ‘virtualenv’ package, if not already installed, by running:

pip install virtualenv

3. Navigate to your project directory using the cd command.

4. Create a virtual environment by running:

virtualenv venv

Replace “venv” with your desired virtual environment name.

5. Activate the virtual environment by running:

source venv/bin/activate

For 🪟Windows:

Open a command prompt window.

2. Install the ‘virtualenv’ package, if not already installed, by running:

pip install virtualenv

3. Navigate to your project directory using the cd command.

4. Create a virtual environment by running:

virtualenv venv

Replace “venv” with your desired virtual environment name.

5. Activate the virtual environment by running:

venv\Scripts\activate

Now that you have a dedicated virtual environment set up for SuperAGI, let’s proceed with the rest of the guide.

🛠 Configuring SuperAGI

1. Find the Configuration Template: In the main SuperAGI folder, locate the file named config_template.yaml. This file might be hidden by default on some operating systems. If it's hidden, reveal the file by following these instructions: Windows, macOS.

2. Create a Copy: Make a copy of config_template.yaml and name it config.yaml. If you're using the command prompt or terminal, use the following command:

cp config_template.yaml config.yaml

3. Open the New Configuration File: Open config.yaml in a text editor of your choice.

4. Enter Your API Keys: Locate the line that says OPENAI_API_KEY:. After the :, enter your unique OpenAI API Key, Google key, and Custom search engine ID. Make sure there are no quotes or spaces.

5. Enter Additional API Keys or Tokens: If you have any other API keys or tokens for services you would like to use, enter them in their respective fields.

6. Save and Close: After you’ve entered all necessary details, save and close the config.yaml file.

Running SuperAGI

After completing the setup and configuration process, it’s time to run SuperAGI.

For Linux/MacOS users, use the following command in the terminal:

./run.sh

Windows users should use the following command:

.\run.bat

If you encounter any errors during this process, ensure you have a compatible Python version installed.

Conclusion

You’re all set! You now have a functional SuperAGI environment ready to provision, spawn, and deploy autonomous AI agents. Keep in mind that SuperAGI is currently under active development.

Leave a star on GitHub https://github.com/TransformerOptimus/SuperAGI
Roadmap: https://github.com/users/TransformerOptimus/projects/1/views/1
Website: https://superagi.co/