Home Artificial Intelligence Tips on how to Easily Install Auto-GPT: The Autonomous GPT-4 Everyone seems to be Talking About

Tips on how to Easily Install Auto-GPT: The Autonomous GPT-4 Everyone seems to be Talking About

Tips on how to Easily Install Auto-GPT: The Autonomous GPT-4 Everyone seems to be Talking About

Image licensed from Shutterstock

Recently a latest AI with more potential than ChatGPT has entered the sport: Auto-GPT, an autonomous GPT-4 experiment.

Auto-GPT is an open-source Python app that uses GPT-4 to act autonomously, so it might perform tasks with little human intervention (and may self-prompt).

Here’s how you’ll be able to install it in 3 steps.

Step 1: Install Python and Git

To run Auto-GPT on our computers, we first must have Python and Git.

To put in Python, go to this website and click on on “Download Python 3.X” (if you happen to’re on Windows, make certain to envision the box “Add python.exe to PATH” when installing Python).

To put in Git on Windows, go to this website and install it. Mac users can install Git using this installer or via Homebrew.

To put in Homebrew, just open the terminal and run the next command.

/bin/bash -c “$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"

Once you’ve Homebrew, install Git with the next command.

brew install git

Step 2: Clone Auto-GPT and install dependencies

Go to this GitHub repo, click on the green button that claims “<> Code” and replica the link that you would be able to also find below.


Then create an empty folder where you would like to clone Auto-GPT (mine goes to be called “gpt.”

Now we open up the terminal or CMD and go to that vacant folder using the cd command. When you’re within the folder type the git clone command, paste the link we copied before and press enter.

The command should seem like this.

git clone https://github.com/Significant-Gravitas/Auto-GPT.git

Essential Note: The master branch may often be in a broken state, so alternatively, you’ll be able to download the latest stable release. Just download the source code (zip) at the underside of the page, move it to the empty folder, and unzip it (this may replace the cloning part)

Once the cloning is complete, in your empty folder there should see a latest folder called “Auto-GPT”

Now it’s time to put in the required dependencies. First, on the terminal, we’ve got to navigate to the directory where the repository was downloaded using the command below.

cd Auto-GPT

Then install the required dependencies with the command below.

pip install -r requirements.txt

After this, a bunch of dependencies might be installed in your computer.


Note: For those who get “pip: command not found” although you’ve Python installed, probably it’s essential to create a virtual environment, activate it after which run the command above.

Once all of the dependencies were successfully installed, we’ve got to configure Auto-GPT.

Step 3: Configure Auto-GPT

First, go to the Auto-GPT folder and rename the file named .env.template to .env. In case you’ll be able to’t find the .env.template file probably it’s hidden. To unhide the file press Command+Shift+Dot on a Mac and your hidden files will develop into visible.

Now right-click the .env file and open it in a text editor. You will have to seek out the OpenAI section.


Now we’ve got to introduce our OpenAI key within the OPENAI_API_KEY variable. To achieve this, we’d like to login into our OpenAI account and generate our API keys.


Do not forget that OpenAI won’t display your secret API key again after you generate it, so make certain you put it aside.

Once you’ve your API key, go to your text editor, and after that OPENAI_API_KEY= paste your unique OpenAI API Key with none quotes or spaces.

Finally, save and shut the .env file.

Congratulation! You will have properly configured the API Keys to your project.

Running Auto-GPT in your computer

To begin working with Auto-GPT, run autogpt Python module in your terminal using the command below

python -m autogpt

Now you must see the next.


Great! Listed below are some options to authorize command(s), exit this system, or provide feedback to the AI.

  • Authorize a single command: y
  • Authorize a series of N continuous commands: y -N
  • Exit this system: n

Now you’ll be able to start working with Auto-GPT. Simply give your AI a reputation, give it a task, and enter as much as 5 goals to your AI.

Soon I’ll create a guide to profit from Auto-GPT, so stay tuned!



Please enter your comment!
Please enter your name here