# Managing Memory for Agents 2.0

**URL:** <https://discuss.huggingface.co/t/managing-memory-for-agents-2-0/114153>\
**Category:** 🤗Transformers\
**Created:** [October 26, 2024, 7:11pm UTC](https://discuss.huggingface.co/t/managing-memory-for-agents-2-0/114153 "2024-10-26T19:11:26Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![jsemrau](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/jsemrau/32/26919_2.png) [@jsemrau](https://discuss.huggingface.co/u/jsemrau)\
**Post date:** [October 26, 2024, 7:11pm UTC](https://discuss.huggingface.co/t/managing-memory-for-agents-2-0/114153/1 "2024-10-26T19:11:26Z")

</div>

I am working on an Agent 2.0 prototype but noticed that the agent does not remember anything. I.e., after the first “run”, a final answer for the task has been found, but the agent does not take the result into consideration for the next “run”.

How can I handover or maintain a persistent memory state for a Transformers Agent?

Thank you.