You should then download Auto-GPT from GitHub: follow the link to the latest version and download the zip file you will find there. When you’ve unzipped the file, duplicate the file named .env.template, rename it .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 an actual API key from your OpenAI account.
You can get an API key from here. You only get a few free API calls with ChatGPT, so you’ll want to set up a payment method—You can see the latest prices at this page (At the time of writing, it’s a few cents for every thousand tokens or bits of information processed.) When you set up your payment method, you can also set payment limits to make sure AutoGPT doesn’t cost you more than you’re comfortable with.
Once you have saved and closed your .env file, you can start Auto-GPT by right-clicking on its folder and choosing Open in Terminal. Type “pip install -r requirements.txt” and press Get into to install the necessary libraries, then when done, type “python -m autogpt” and press Get into to start Auto-GPT itself. Then you can start making Auto-GPT work anonymously for you: just tell it what you want it to do and it goes to work.
Your thought will be displayed on the screen and you will be asked to confirm each action in the Auto-GPT process works. If you’d rather approve multiple actions in a row, type “yx” where x is the number of actions you’re happy for the bot to continue without your approval (remember that all these ChatGPT requests cost you a small amount of money). If you need to end a task before it is complete, 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 as advanced as Auto-GPT, but it’s easier for beginners and gives you an idea of what’s possible with these autonomous AI agents.
As with Auto-GPT, you must get an API key for ChatGPT for AgentGPT to work properly (and again you will be charged based on usage). You can plug this API key into the tool via settings on the left. Give your agent a name and a target using the onscreen input, then choose Deploy Agent to activate it; tasks are displayed on the right as they are generated and completed.