/Tech1h ago

EngramLab releases persistent memory system that matches frontier model performance while using 1% to 10% of standard tokens

Microsoft, Notion, and Harvey are currently piloting the system.

84561210.8K

#866

Original post

Kleiner Perkins@kleinerperkins

The models we use every day are brilliant strangers. They forget your organization the moment a chat ends, then relearn it on the next query.

@EngramLab fixes that. It learns your world once and reuses that memory, matching frontier systems on 1-10% of the tokens.

@Microsoft, @NotionHQ, and @Harvey are already testing it within their organizations.

Congratulations to the team, and hear directly from @dan_biderman (CEO and co-founder) and Sabri Eyuboglu (CTO and co-founder) with @LM_Braswell ⬇️

Engram@EngramLab

http://x.com/i/article/2069463677733142528

7:22 AM · Jun 24, 2026 · 7.7K Views

Sentiment

Users are excited about EngramLab's persistent AI memory because it delivers frontier-level performance using just 1-10% of tokens and appreciate the new term tokenmaxxing for capturing that efficiency.

Pos

100.0%

Neg

0.0%

2 comments with sentiment.

Cluster Engagement

Digg Deeper

No Digg Deeper questions have been answered for this story yet.

X (FORMERLY TWITTER)Via

Posts from X

Most Activity

VIEWS1.7KBOOKMARKS2LIKES15RETWEETS2REPLIES2

"Leigh Marie" Braswell@LM_Braswell

Discussing @EngramLab's technical approach, the story of the Microsoft partnership, and how to remedy "tokenmaxxing" with the brilliant @dan_biderman & @EyubogluSabri --

Kleiner Perkins@kleinerperkins

The models we use every day are brilliant strangers. They forget your organization the moment a chat ends, then relearn it on the next query.

@EngramLab fixes that. It learns your world once and reuses that memory, matching frontier systems on 1-10% of the tokens.

@Microsoft, @NotionHQ, and @Harvey are already testing it within their organizations.

Congratulations to the team, and hear directly from @dan_biderman (CEO and co-founder) and Sabri Eyuboglu (CTO and co-founder) with @LM_Braswell ⬇️

1h1.7K152

Dan Biderman@dan_biderman

Discussing @EngramLab's technical bets with @LM_Braswell at @kleinerperkins's Amazon room.

Kleiner Perkins@kleinerperkins

The models we use every day are brilliant strangers. They forget your organization the moment a chat ends, then relearn it on the next query.

@EngramLab fixes that. It learns your world once and reuses that memory, matching frontier systems on 1-10% of the tokens.

@Microsoft, @NotionHQ, and @Harvey are already testing it within their organizations.

Congratulations to the team, and hear directly from @dan_biderman (CEO and co-founder) and Sabri Eyuboglu (CTO and co-founder) with @LM_Braswell ⬇️

2h2.3K205

Engram@EngramLab

Dan and Sabri sat down with @LM_Braswell to talk about our technical direction. Thanks for having us!

Kleiner Perkins@kleinerperkins

The models we use every day are brilliant strangers. They forget your organization the moment a chat ends, then relearn it on the next query.

@EngramLab fixes that. It learns your world once and reuses that memory, matching frontier systems on 1-10% of the tokens.

@Microsoft, @NotionHQ, and @Harvey are already testing it within their organizations.

Congratulations to the team, and hear directly from @dan_biderman (CEO and co-founder) and Sabri Eyuboglu (CTO and co-founder) with @LM_Braswell ⬇️

17m30520

Ziwen Xu 🔶@z1vex

@LM_Braswell @EngramLab @dan_biderman @EyubogluSabri i actually love the term tokenmaxxing. never heard it before but it perfectly captures the whole race to use more tokens than necessary.

1h6

SethiLiam@SethiLiam

@LM_Braswell @EngramLab @dan_biderman @EyubogluSabri hitting 1-10% of tokens while keeping frontier-level memory is wild efficiency

45m3

Sir Nodebridge@chessieowl

@kleinerperkins @EngramLab @Microsoft The token economics are the interesting bit. If the memory holds up in production, this gets compelling quite quickly.

1h1