[Feature] Allow Batch/On-Demand Memory Extraction Instead of Per-Message Processing

[ssmoon]

Is your feature request related to a problem?

Currently Memory Agent processes every conversation turn immediately. In my use case, this causes unnecessary overhead: real-time extraction isn't critical, and many turns are low-value (greetings, clarifications). Extracting every single message wastes tokens when only 3-4 turns in a 20-turn session contain meaningful user information.

The Solution

Allow memory extraction to run on-demand or in batch mode at conversation boundaries, rather than automatically after every message.

1. Trigger extraction manually or on session end
2. Keep current per-message behavior as default, add batch mode as optional setting

Alternatives Considered

No response

Affected Components

No response

Participation

• I am willing to submit a pull request for this feature.

[AbhinavJD7]

Hi @ssmoon , I’d like to take a look at implementing this!

[vaibhav45sktech]

Greetings @devwdave , Could you please assign this issue to me

[jayyao18]

We are grateful for your help and will get back to you on this soon.

In the meantime, we'd like to invite you to Discord!

You'll be able to:

• Chat with our engineers directly
• Sneak peek to what's coming next
• Collaborate with other contributors
• Be eligible for exclusive giveaways

Looking forward to working with you on improving Memori.

Jay
DevRel