AutoGPT: Warning: The file 'auto-gpt.json' does not exist. Local memory would not be saved to a file.
Duplicates
- I have searched the existing issues
Steps to reproduce š¹
Warning: The file āauto-gpt.jsonā does not exist. Local memory would not be saved to a file.

Current behavior šÆ

Expected behavior š¤
No response
Your prompt š
# Paste your prompt here
About this issue
- Original URL
- State: closed
- Created a year ago
- Comments: 68 (2 by maintainers)
If you are having this issue with docker compose:
From the main project directory run
touch auto-gpt.jsonto create the empty file.Then open
Dockerfileand add the following line which will copy the file into the docker container during build:Then build:
I have finally got it, in my case, the issue was that the Mac file extension was for some reason taking the .env as an Adobe Illustrator file type, I removed that file type from the file info and then it worked.
That addressed the issue of the LocalStorage Database not present and effectively keeps the data saved outside the container. Additionally Iāve updated the volumes to look like this:
This is because docker-compose is mounting the app in the root
/appbut the app seems to being run from a stale copy from/home/appuser/autogptwhich I donāt understand why. But for most of the cases just mounting the json file is enough.I solved API issue by copying in cmd(windows)
set OPENAI_API_KEY=your_api_key_here
worked fine after
Just open the AutoGPT file in VScode and create a new file called āauto-gpt.jsonā and save it to the main folder
Found this on a website (https://prinspeter.medium.com/how-to-use-autogpt-using-docker-a-step-by-step-guide-34ad33957de9) and once updated it worked.
It works, thank you. But do I have to use
docker cpcommand to copy it out of the container before I cut it off. @gavinuhmač°č½ęęčå
Iāve created an empty āauto-gpt.jsonā file in project root, but still getting āWarning: The file āauto-gpt.jsonā does not exist.ā:
Edit: missed this comment - https://github.com/Significant-Gravitas/Auto-GPT/issues/1410#issuecomment-1522751914 - which fixes the issue.
OK, whew. Just solved this for myself also. As per above, just to sum up:
Note that Mac, for whatever reason, can keep adding the .template extension after you remove it. You have to command i, look at the properties, remove the extension there and confirm you want to remove the extension.
Woo. Thanks all š I now appear to have this working on my Macbook. M2.
You just need to rename the original ā.env.templateā file to ā.envā, replace it with your key. Then create a new file called āauto-gpt.jsonā in the root directory, as shown in the image below:
Then run the command in the terminalļ¼ python -m autogpt
Finally, it succeeded!
I had the same error and fixed it thanks community!
I just created the auto-gpt.json file saved it, ran python -m autogpt and it worked!
ORIGINAL ERROR Warning: The file āauto-gpt.jsonā does not exist. Local memory would not be saved to a file. Welcome to Auto-GPT! Enter the name of your AI and its role below. Entering nothing will load defaults. Name your AI: For example, āEntrepreneur-GPTā AI Name:
I get this when I run it in a docker container
Well, I setup my billing and still getting the same message, the .env is a env file type not a text or template as my mac was taking it, and the API key is there so not sure what else to try. has anyone got this working on mac?
I have the same issue is there a fix?
just create a new file name auto-gpt.json in main folder