supermemory

1.2K posts

supermemory banner
supermemory

supermemory

@supermemory

The memory and context cloud for AI agents https://t.co/9JWFW4cHXH

San Francisco, CA Katılım Mayıs 2024
45 Takip Edilen26.3K Takipçiler
Sabitlenmiş Tweet
supermemory
supermemory@supermemory·
You can now run supermemory locally. Just one command - npx supermemory local Open source binary, available now - git.new/memory
Dhravya Shah@DhravyaShah

You can now run @supermemory locally. Introducing the supermemory local - Fully self-contained. Comes with our graph engine, embedding model, etc. - Run on any machine, with your @openclaw, hermes, claude, etc. - SDKs to add memory to your agent, or build your company brain.

English
2
5
58
28.8K
supermemory
supermemory@supermemory·
Meet the first set of judges for 🔎 it's the supermemory team itself, the people who actually built the memory layer you're hacking on. founder, product, infra, research, the whole crew. your builds are in good hands. and this is just batch one, more judges dropping soon 👀 JOIN our hackathon ↓
supermemory tweet media
English
4
1
26
2.3K
supermemory
supermemory@supermemory·
The prize pool just got a lot bigger, @dodopayments is adding $17,500 in dodo credits 🤝 - 1st: $7,500 - 2nd: $5,000 - 3rd: $2,500 - people's choice: $2,500 build your project with @supermemory, then use the credits to actually ship and sell it with dodo. come build with us👇
supermemory tweet media
English
10
6
89
5K
AADITYANSHA
AADITYANSHA@aadityansha_06·
@supermemory Hey @supermemory I have applied to your startup for research yesterday along with that 60sec video attached in it,through the form u given on X, hope to get the reply soon
English
1
0
1
67
supermemory
supermemory@supermemory·
The build period for hackathon is live! for the next few days, builders are shipping anything they want on supermemory local, one command, and the whole memory layer runs on their own machine. Also our kickoff event is tomorrow, do join in. genuinely excited to see what comes out of this. not too late to jump in 👇
supermemory tweet media
English
2
2
17
3.3K
Ayush Agarwal
Ayush Agarwal@ayushagarwal·
we have joined hands with @supermemory for localhost:6767 as the official payments partner. build it with supermemory. sell it with @dodopayments. winners get sponsored credits. july 9-13. come build with us.
Ayush Agarwal tweet media
English
8
5
109
4.9K
supermemory
supermemory@supermemory·
Excited to have @dodopayments backing , our winners are getting dodo credits 🤝 they're the billing & payments platform for AI companies, a merchant of record trusted by 50,000+ builders across 220+ countries. payments, taxes, and global payouts, all handled. so you build it with @supermemory, then start selling it with dodo. come build with us, july 9-13💙
supermemory tweet media
English
7
7
42
7K
supermemory
supermemory@supermemory·
To kick off <localhost:6767> hackathon we're hosting a kickoff hangout 🎙️ come hang out with the team and ask us anything, hackathon ideas, setup, @supermemory local, all of it. july 10 · 9am PST, join in our discord 👇
supermemory tweet media
English
1
3
22
12.7K
supermemory retweetledi
Shardul Mane
Shardul Mane@shardul_mane·
we shipped the hackathon name into the codebase before we announced it. now we're shipping you an invite! localhost:6767 is happening, come build on @supermemory
GIF
Dhravya Shah@DhravyaShah

Introducing , supermemory's first ever hackathon. we made @supermemory run entirely on your own machine, and now we want to see what you'll build with it. 5 days, build anything on supermemory local, then show us what you built. - cash prizes & supermemory credits for the winners - build july 9–13, fully online in our discord - solo or teams of up to 4 - plus a people's choice prize, voted by the community register & join the discord for all info ↓

English
5
1
18
2.5K
supermemory retweetledi
Muskan Jain
Muskan Jain@Muskanjain0401·
Launching our first ever hackathon for the community! you can now run supermemory entirely on your own machine, so naturally, we had to throw one to see what you'll build 😌 it's all in the video, come build with us ↓
Dhravya Shah@DhravyaShah

Introducing , supermemory's first ever hackathon. we made @supermemory run entirely on your own machine, and now we want to see what you'll build with it. 5 days, build anything on supermemory local, then show us what you built. - cash prizes & supermemory credits for the winners - build july 9–13, fully online in our discord - solo or teams of up to 4 - plus a people's choice prize, voted by the community register & join the discord for all info ↓

English
11
12
145
13.7K
Dhravya Shah
Dhravya Shah@DhravyaShah·
Introducing , supermemory's first ever hackathon. we made @supermemory run entirely on your own machine, and now we want to see what you'll build with it. 5 days, build anything on supermemory local, then show us what you built. - cash prizes & supermemory credits for the winners - build july 9–13, fully online in our discord - solo or teams of up to 4 - plus a people's choice prize, voted by the community register & join the discord for all info ↓
Dhravya Shah tweet media
English
31
9
420
49.6K
supermemory
supermemory@supermemory·
COME TO OUR HACKATHONN
Dhravya Shah@DhravyaShah

Introducing , supermemory's first ever hackathon. we made @supermemory run entirely on your own machine, and now we want to see what you'll build with it. 5 days, build anything on supermemory local, then show us what you built. - cash prizes & supermemory credits for the winners - build july 9–13, fully online in our discord - solo or teams of up to 4 - plus a people's choice prize, voted by the community register & join the discord for all info ↓

English
2
0
15
1.7K
supermemory
supermemory@supermemory·
Fair warning: picking an embedding model based on benchmark performance alone is how you end up debugging 7-second retrieval latency in production. Embeddings are the hidden engine behind RAG and memory systems. The better they are, the more relevant your results, and the smarter your app feels. But here's the gap most teams hit: You chose between precision and recall when you picked your search method. → BM25 nails exact entity matches but completely misses semantic similarity → Vector search handles conceptual queries beautifully but fumbles on product SKUs and technical identifiers → Your users send both query types Production agents need more than semantic retrieval. They need hybrid search, reranking layers, user context tracking, and extraction logic that doesn't break under load. That's why we built supermemory as a complete context engine, not just another vector database. You get embedding pipelines, extraction tooling, connectors, and memory management out of the box. If you're building AI features that need to remember and retrieve accurately, we've done the infrastructure work for you. Docs here: supermemory.ai
English
0
1
23
1.9K
supermemory retweetledi
stanleyweb3
stanleyweb3@theStanleyweb3·
I’ve been exploring different AI projects lately, and one project that genuinely caught my attention is @supermemoryai. AI is becoming more powerful every day, but one thing it still struggles with is memory. Most AI tools forget previous conversations and make you repeat yourself every time. That’s a huge problem, especially as AI agents become more common. This is where Supermemory stands out. They’re building the memory layer for AI, making it possible for AI applications and agents to remember context, conversations, documents, and user preferences to deliver much smarter and more personalized experiences. I believe infrastructure projects like this will play a major role in the future of AI. They’re not just building another AI app they’re building technology that other AI products can rely on. As Stanley Web3, I enjoy discovering early stage projects with real potential and helping them gain visibility through content, community moderator and strategic marketing. I’ll be keeping a close eye on @supermemoryai because I believe they’re building something valuable, and I’d love the opportunity to contribute to their growth if the chance comes. Definitely a project worth watching @shardul_mane
stanleyweb3 tweet media
English
9
2
19
980