- Run the
autogpt
Python module in your terminal.
- On Linux/MacOS:
./run.sh
- On Windows:
Running with
.\run.bat
--help
after.\run.bat
lists all the possible command line arguments you can pass.
- After each response from Auto-GPT, choose from the options to authorize command(s),
exit the program, or provide feedback to the AI.
- Authorize a single command by entering
y
- Authorize a series of N continuous commands by entering
y -N
. For example, enteringy -10
would run 10 automatic iterations. - Enter any free text to give feedback to Auto-GPT.
- Exit the program by entering
n
- Authorize a single command by entering
Here are some common arguments you can use when running Auto-GPT:
Replace anything in angled brackets (<>) to a value you want to specify
- View all available command line arguments
python -m autogpt --help
- Run Auto-GPT with a different AI Settings file
python -m autogpt --ai-settings <filename>
- Specify a memory backend
python -m autogpt --use-memory <memory-backend>
NOTE: There are shorthands for some of these flags, for example
-m
for--use-memory
. Usepython -m autogpt --help
for more information
Enter this command to use TTS (Text-to-Speech) for Auto-GPT
python -m autogpt --speak
Run the AI without user authorization, 100% automated. Continuous mode is NOT recommended. It is potentially dangerous and may cause your AI to run forever or carry out actions you would not usually authorize. Use at your own risk.
-
Run the
autogpt
python module in your terminal:python -m autogpt --continuous
-
To exit the program, press Ctrl + C
If you don't have access to the GPT4 api, this mode will allow you to use Auto-GPT!
python -m autogpt --gpt3only
If you do have access to the GPT4 api, this mode will allow you to use Auto-GPT solely using the GPT-4 API for increased intelligence (and cost!)
python -m autogpt --gpt4only
Activity and error logs are located in the ./output/logs
To print out debug logs:
python -m autogpt --debug