Advanced Agent memory

Open julian-risch opened this issue 9 months ago • 2 comments

We can build on the Agent implementation in haystack-experimental, in particular it's state. Currently there is no serde for state (removed in this commit)

Mar 05 '25 11:03 julian-risch

Just to add my thoughts on this. I think State is part of the memory conversation, but I think we should also talk about/consider how to store the ChatMessages returned by an Agent after it exits the loop. I think these messages are also relevant for memory in multi-turn conversations and for restarting an agent if we were to add break points.

Mar 05 '25 11:03 sjrl

State serialization is coming in https://github.com/deepset-ai/haystack/pull/9345

May 12 '25 08:05 julian-risch

Superseded by https://github.com/deepset-ai/haystack-private/issues/218

Nov 14 '25 08:11 sjrl