supermemory

Pushing the frontier of memory and continual learning for agents.

Add memory to your agents today

[supermemory @supermemory]

Introducing API v5, the agent-first memory API

- container tags are now namespaces, and they live in the url
- output from the API is now optimized for agent context
- one prompt to migrate
- Markdown negotiation in API results

[Mahesh @MaheshtheDev]

@reginaldandreas @supermemory this is live, Andreas. Please try and lmk any feedback

[supermemory @supermemory]

@reginaldandreas Got it. We're working on making this experience better!

[supermemory @supermemory]

@Cloudflare 👀

[supermemory @supermemory]

@ManishBaghelz a tree is a graph if you think about it

[supermemory @supermemory]

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 ↓

[supermemory @supermemory]

@0xDevShah thank you!

[Dev Shah @0xDevShah]

supermemory does such gorgeous stuff

[edison @grindsets]

@DhravyaShah @supermemory we're glad we stuck with supermemory, since transitioning over, we never got a single complaint about Fae remembering stuff since! our signals for "forgetting" on @raindrop_ai dropped by 30% to single digits!

[supermemory @supermemory]

read more here https://t.co/hFLjmxKBOA

[Dhravya Shah @DhravyaShah]

Introducing supermemory's graph engine

yes. I did a graph. and yes, im against graphs. guess what
It's built ground-up from first principles (its not a real graph)

ALL you need for memory is:
- Keeping track of changing knowledge
- Forgetfulness on specific information
- Connections between information

We boiled the entire logic down into a single data structure. it can be represented as a filesystem, facts system, pages, or anything your agent / setup needs

This also allows us to magically find and inject tokens into the model harness without the model having to come looking for that information. Because

memory should be magical

and super intelligence needs @supermemory

[supermemory @supermemory]

> https://t.co/J56yN4V81h

[Dhravya Shah @DhravyaShah]

Introducing supermemory's graph engine

yes. I did a graph. and yes, im against graphs. guess what
It's built ground-up from first principles (its not a real graph)

ALL you need for memory is:
- Keeping track of changing knowledge
- Forgetfulness on specific information
- Connections between information

We boiled the entire logic down into a single data structure. it can be represented as a filesystem, facts system, pages, or anything your agent / setup needs

This also allows us to magically find and inject tokens into the model harness without the model having to come looking for that information. Because

memory should be magical

and super intelligence needs @supermemory

[supermemory @supermemory]

@grindyoway @MonidHQ noooo @MonidHQ are friends

[supermemory @supermemory]

@Pulkit_Kudiwal Banger

[adam @theCTO]

this is all it takes to get a @Lovable iMessage agent in production with @supermemory @browserbase @daytonaio BYOK

[supermemory @supermemory]

one command and persistent memory for your coding agents 🧠

𝚗𝚙𝚡 𝚜𝚞𝚙𝚎𝚛𝚖𝚎𝚖𝚘𝚛𝚢 𝚙𝚕𝚞𝚐𝚒𝚗𝚜

[supermemory @supermemory]

> https://t.co/6wIWOTehw2

[supermemory @supermemory]

one command and persistent memory for your coding agents 🧠

𝚗𝚙𝚡 𝚜𝚞𝚙𝚎𝚛𝚖𝚎𝚖𝚘𝚛𝚢 𝚙𝚕𝚞𝚐𝚒𝚗𝚜

[Dhravya Shah @DhravyaShah]

i ran some numbers. Markdown memory is 40x more expensive than @supermemory

let that sink in.

teams never realize this because token spend is not well attributed, so it feels like the users are using the model too much, when in reality it was just your memory consolidation step

[Dhravya Shah @DhravyaShah]

so... we have a foundation model in the house

[supermemory @supermemory]

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)