Next, you need to Download Auto-GPT from GitHub: Follow the link to the latest release and download the zip file you find there. Once you’ve unzipped the archive, copy the file called .env.template, rename it to .env, and open it in a text editor. Find the line “OPENAI_API_KEY=your-openai-api-key” and replace “your-openai-api-key” with the actual API key from your OpenAI account.
You can get the API key from now. You only get a few free API calls with ChatGPT, so you’ll want to set up one payment methods—you can see the latest prices at this page (at the time of writing, that’s a few cents per thousand tokens or bits of information processed). Once you set up your payment method, you can also configure a payment limit to ensure that AutoGPT doesn’t cost you more than you’re comfortable with.
After you have saved and closed your .env file, you can launch Auto-GPT by right clicking on its folder and selecting Open in Terminal. Type “pip install -r tests.txt” and press Enter to install the required libraries then when done type “python -m autogpt” and press Enter to manually launch Auto-GPT. Then you’re free to start letting Auto-GPT work for you anonymously: Just let it know what you want it to do and it’ll work.
Its thoughts will be displayed on the screen, and you will be asked to confirm each action during Auto-GPT execution—if you want to approve several actions in a row, enter “yx”, in where x is the number of actions you’re happy with the bot takes without your consent (remember all these ChatGPT requests cost you a small amount). If you need to end a task before it completes, use Ctrl+C.
If this seems like a lot of work and you want something simpler to play, AgentGPT is a similar project based on Auto-GPT that works in the browser, no installation required. It’s not quite as advanced as Auto-GPT, but it’s simpler for beginners and it gives you an idea of what can be done with these autonomous AI agents.
As with Auto-GPT, you need to get API key for ChatGPT for AgentGPT to run properly (and again, you will be charged based on usage). You can plug this API key into the tool via Setting left. Give your agent a name and goal using the on-screen input, then choose Deploy Agent to disable it—tasks are shown on the right as they are created and completed.
