Boostrix

I am not sure if the .env is the right place for this, assuming that sub-agents may also need to be constrained accordingly ?

Note that as far as I've seen the command system is in the process of being overhauled (centralized) apparently, and so is the plugin system. Implementing commands on top of...

> Without those plugins, which are basic I/O functions, Auto-GPT would be maimed. Also see #56

After having thought about it a little, here's a proposal (draft really, feedback welcome!) to provide a generic and extensible framework to allow people to set up all sorts of...

regarding commands: it would be useful if there was support for an optional step to prepare commands, but also another step to review the prepared command before it's getting executed....

this seems to be work in progress, according to the logs, commands are going to be moved into plugins and there are going to be ways to enable/disable those individually....

> Whoever thinks they can make dockerfiles into a plugin feel free. sorry, asking for clarification: are you asking for a plugin to generate docker files ?

> With that being said, multiple separate instances that work together is wild. And if they can make it communicate, that would be EVEN better. only in theory, the complexity...

> it looks like the whole AutoGPT architecture could need management agent that manages the other agents and the whole progress. That agent could take up where the progress was...

I think we need a draft PR to summarize the main ideas, collated from different issues/talks