worldmemarena

Here is 1 public repository matching this topic...

previously-lab / benchmark-data

Seeded conversation datasets for Previously — 20 complete personas with 600 multi-turn conversations across 3–4 year timelines. Derived from the WorldMemArena benchmark (CC BY-NC 4.0).

benchmark ai memory dataset conversation episodic-memory llm worldmemarena

Updated Jul 27, 2026
JavaScript

Improve this page

Add a description, image, and links to the worldmemarena topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the worldmemarena topic, visit your repo's landing page and select "manage topics."

Learn more