Post #2972992
2026-04-09 14:49 UTC
1/2 So if you're wondering how #omnimem compares to #MemPalace:
result: single-session-assistant type achieved 94.6% on longMemEval.
However, v5 is bringing in LOTS of changes to help with temporal reasoning and multi-session improvements by allowing users to optionally switch on enrichment queues for remember_document(). This will extract individual facts from larger documents helping with the recall() function.
#opensource #ai #memory #claude #openai
Replies (1)
-
@Ric@mastodon.squarecows.com 2026-04-09 14:50
2/2 Once I finish testing I'll publish all the results and methodology to show that the features in omnimem are helping rather than just a pure retrieval metric from the Valkey data store. You can follow along on the v5 branch and particularly issue #19 at: https://codeberg.org/ric_harvey/omnimem whilst you're there drop me a star please :) It'll all help as I don't have celebrity backers ;) #opensource #aims to #memory #claude #openai