"It's like AutoGPT got a brew install
", made possible by Kurtosis.
Assuming you have Kurtosis installed, simply run the following with your OpenAI API key:
kurtosis run github.com/kurtosis-tech/autogpt-package --enclave autogpt '{"OPENAI_API_KEY": "<YOUR_API_KEY_HERE>"}'
kurtosis service shell autogpt autogpt --exec "python -m autogpt"
We use the Redis
memory backend by default.
To run this on Kurtosis on GitPod click here. This doesn't require a local installation of Kurtosis.
Follow along the official guide here
To pass any other configuration listed here; pass the argument like you pass the OPENAI_API_KEY
kurtosis run github.com/kurtosis-tech/autogpt-package --enclave autogpt '{"OPENAI_API_KEY": "<YOUR_API_KEY_HERE>", "RESTRICT_TO_WORKSPACE": "False"}'
Note - This package spins up AutoGPT using the Redis
backend. To use the local backend instead set MEMORY_BACKEND
to local
in args
. For pinecone
and milvus
you will need to get API keys for it and pass it. Weaviate
isn't supported yet. For any other backend apart from redis
; the Redis
server will still be spun up but won't be used.
Let us know in our Discord or on Twitter @KurtosisTech!