Victor Dibia
Victor Dibia
I agree that the challenge above can be helped by using a distributed runtime. We will need to create a design doc/discussion around how to support distributed runtimes in AgentChat....
I agree that end users should not be defining tools. However - AGS is a _developer tool_. For debugging. Fair to assume similar exposure with e.g., a notebook? My feeling...
Addressed in #3849 (but will be updated as the api evolves)
@lspinheiro , The AgentChat framework will likely only have the `Memory` protocol, developers should overload it to implement whatever vector, graph or any other type of Just in time memory...
@jackgerrits , thoughts on moving this to core? i agree with Eric that this could be general enough to be used across the framework. If so, any suggestions on location...
Closing, completed in #5261
@mpegram3rd Thanks for the help with the types PR! Might this be an issue that you might be interested in working on? I have a rough sketch above mostly just...
No worries at all, thanks again for the fine contribution! I'll also tag you for a review if I get to it before then.
As part of the work to fully support [Magentic one teams in AGS](https://github.com/microsoft/autogen/issues/5751). (and Ideally add an example impl as a default agent in AGS). Supporting the MagenticOneTeam is already...
Thanks @afourney . I think your input on ComputerTerminal makes a good case for supporting codeexecutor agent directly. I agree that filesurfer may need more design on a filesurfer tool.