supermemory

@supermemory · San Francisco, CA · joined 13 May 2024

The memory and context cloud for AI agents https://t.co/9JWFW4ca89

27 679Followers

48Following

1 294Posts total

22.9KViews on collected posts

Against accounts of the same size

5 posts from the last 90 days, next to the 10K–100K follower range. shown widely, but few of those viewers react.

Median views3 427this account1 328median for 10K–100K

Reach, %12.38%this account4.18%median for 10K–100K

Engagement, %1.20%this account1.94%median for 10K–100K

Metric	This account	Median for 10K–100K	Ratio
Median views per post	3 427	1 328	2.58×
Reach (views ÷ followers)	12.38%	4.18%	2.96×
Engagement rate	1.20%	1.94%	0.62×

Others in this range → Compare with another account → How these benchmarks are built →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

3.4K25 Aug

2.8K26 Aug

2.5K28 Aug

4K1 Sep

10.2K3 Sep

Last 5 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

1.20%25 Aug

0.51%26 Aug

1.22%28 Aug

1.38%1 Sep

0.48%3 Sep

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.94%.

What the audience does

Likes69.9%167 in total

Reposts5.0%12 in total

Replies3.3%8 in total

Quotes0.8%2 in total

Bookmarks20.9%50 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.

Latest posts

this is so cool! happy to be powering squad's memory 10.2K views · 45 likes · 2 reposts · 2 replies 03 Sep 2026 AI memory is more than embed and search, doing retrieval well means solving a lot of hard problems stacked underneath. that's how @supermemory's architechture is built: a single engine with vector, keyword and graph search, plus a model that figures out what to keep and what to 4K views · 50 likes · 4 reposts · 1 replies 01 Sep 2026 Agents are getting solved, memory is the missing piece. A future where AI actually works for you only matters if it remembers you. That's the building block everything else sits on, and it's what we're building. One memory, for every ai you use. watch the full podcast https:// 2.5K views · 24 likes · 2 reposts · 2 replies 28 Aug 2026 A great product by a great team. Check it out! It's also powered by supermemory 2.8K views · 11 likes · 0 reposts · 3 replies 26 Aug 2026 Why doesn't a bigger context window just solve memory? @sohamdaga22 explains why that intuition breaks: the problem was never storing everything, it's knowing what to store and what to forget. watch the full clip → https://t.co/ULSbT9jxRU 3.4K views · 37 likes · 4 reposts · 0 replies 25 Aug 2026