Telegram client - long memory for personal assistent

[adapt7]

Just starting working with the framework, maybe it's a basic question: how to keep long memory?

For example I want agent to remember something. Then I exchange many new messages. Then I want to get back to the thing I wanted agent to remember. Unfortunately it can only relate to some recent 20-40 (?) messages back.

Is it a configuration thing? I use default configs.

or this requires custom plugin that will remember "todo" list?

which memory to use for that?

if there are more items over the time - does it mean the openai or anthropic costs will increase due to bigger context or something similar?

any ideas how to handle this?

[github-actions]

This issue has been automatically marked as stale due to 30 days of inactivity.
If no further activity occurs within 7 days, it will be closed automatically. Please take action if this issue is still relevant.