Pushing the frontier of memory and continual learning for agents. Add memory to your agents today
San Francisco, CA
Joined May 2024
- Tweets1.4K
- Following51
- Followers30.1K
- Likes1.7K
Introducing the supermemory memory graph
every document becomes atomic facts, and dreaming keeps building the graph in the background
- extracting facts
- linking related memories
- resolving updates, the old version stays as history
get one for yourself in the console β
one command and persistent memory for your coding agents π§
πππ‘ πππππππππππ’ πππππππ
supermemory local v0.0.9 is out!
- API v5 support
- Better security
- about 40% faster
- you can use it with docker now
(we heard you! The next version of local will be 10x less resource intensive)
An UNFORGETTABLE #SFTechWeek, the Supermemory way!
We teamed up with @agi_inc to host a pitch night, a robotics hackathon, and a cafΓ© pop-up.
Loved seeing what everyone is building, hearing the pitches, and getting to know people over coffee.
Thanks to everyone who came through!
Over mcp, the model usually types your file out as text 6.7m characters for a 5 mb pdf and one wrong one corrupts it...
the supermemory mcp app skips that
- pick the file in a widget
- one click sends it straight to supermemory on a one-time ticket
- the model gets a receipt
supermemory makes agent context into one API. everything built in
πππ π πππππππππππ’
memory, filesystems, retrieval, profile, connectors and data extraction.
ask your agent to use supermemory :)
You can break down every memory implementation into two axes
- time: what changed, and when
- connections: what links to what
supermemory's graph keeps both on atomic facts, the latest fact wins, the old one stays as history, and you never draw an edge
We made an implementation of @cognition's dreaming memory repo architecture, here's our founder @DhravyaShah talking about it and the (open source) code!
Introducing MemoryRepo.dev.
an open source implementation of Cognition's dreaming memory system, same as Instinct, Muse, Openclaw, etc., built on @cloudflare Artifacts, Durable objects, Alchemy and Effect.
I've been exploring agent memory for a long time and this is one of the more popular ways to do it, and I'm happy to see cognition putting out a detailed spec of how they perceive this.
In a way, it's beautifully simple and encapsulates what a good memory system should have.
There's many pros and cons, here's a video of me talking about it β
If you're thinking about agent memory you should probably use @supermemory - we think a lot about the very specific details about all of this. But, if you're curious, github.com/supermemoryai/mem⦠is a great place to start with the cognition memory thing as well.
we're actually going to incorporate some of the learnings from the research we're doing here into supermemory (soon-ish). but open sourcing it for public benefit :)
sorry for the bad audio quality, did it as a quick thing