Video wird geladen...
Video konnte nicht geladen werden
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 ↓
147,223 Aufrufe • vor 7 Tagen •via X (Twitter)
33 Kommentare
>
read more here
i mean it looks cool i guess, but i learned absolutely nothing watching that video
supermemory x obsidian wen?
how is this not obsidian graph
😭
this is exact same as @AxonDB_ 😭
I have to start blocking every ai reply account
super cool
supermemory 🤝 axondb spot the difference challenge (impossible) 💀
looks cool but I'd rather have a simpler version - a tree of running context.
a tree is a graph if you think about it
it's a graph with constraints, the constraints make it simpler.
@obsdmd
Where is the open source GitHub repo ?
When a source document is deleted, what happens to facts and links derived from it during background processing? Keeping old versions is useful, but users also need a way to remove information without a derived memory quietly bringing it back.
Pretty KG!
Keeping old versions while updating memories is a really smart touch. That kind of context could make AI agents much more reliable over time.
How much does this cost? Is there a cheaper consumer version?
Love this atomic facts background dreaming is such an elegant way to build memory
Isn't this too much preprocessing? How will it handle adding new documents?
may be technically impressive or not but all i can think of are JELLYFISHEEZ
Swear we’re all building the same thing lol
Sprinkling random context dust into your agent is more likely to hurt than to help
maybe we’ll see a market of ‘supers’ trending
Why facts and not testimony? Lots of problems I bet you had to solve evaporate with that one simple trick
A memory graph that evolves and preserves history is a big step forward
A note can contain a fact, a question, or an idea I've already rejected. I'd want a memory graph to preserve those distinctions, so an unfinished thought doesn't quietly become something I supposedly believe.
If you're gonna post about your product, try to be less vague and show how this is different than everybody else.
One memory I'd pay attention to: 'I already answered this.' My coding agent keeps reviving old questions after compaction. Remembering the request without remembering it's finished is a very convincing time loop.
lfggggg
Looks cool. But I’ve never found anything practical from this. Although, I’m ok with this level complexity if the an Agent can give me relevant insights (not the basic ones but something that’s not too easy for humans) from this graph.
how do you determine the most relevant fact given the state of the context window?
