Dhravya Shah's banner
Dhravya Shah's profile picture

Dhravya Shah

@DhravyaShah • 60,974 subscribers

founder, CEO, CTO @supermemory the memory/context guy (and it's all OSS: https://t.co/fVMMAL2BHp) prev @cloudflare, @solofounders, @neo finalist

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

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.
1:16
DhravyaShah's profile picture

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.

Dhravya Shah

659,865 views • 1 month ago

Introducing the $100 max plan on supermemory cloud - 7x limit from pro plan and 10x cheaper than self-hosting same amount of usage - Granola, Gmail and other connectors - Most API features enabled - Best for startups, internal team and heavy personal use!
1:13
DhravyaShah's profile picture

Introducing the $100 max plan on supermemory cloud - 7x limit from pro plan and 10x cheaper than self-hosting same amount of usage - Granola, Gmail and other connectors - Most API features enabled - Best for startups, internal team and heavy personal use!

Dhravya Shah

67,200 views • 20 days ago

Behind the scenes for our memory benchmark (we knew)
1:12
DhravyaShah's profile picture

Behind the scenes for our memory benchmark (we knew)

Dhravya Shah

312,731 views • 3 months ago

Filesystems vs Vector search is the new MCP vs CLI. Claude uses agentic search. And Dens Sumesh at mintlify like filesystems too. but Retrieval is still used by Notion, Cursor, and others. We hit the cafes of SF to see what people want. - The debate is hot. Filesystems won by 1 point - filesystems feel very simple and intuitive. - RAG requires embedding, vector search and other stuff filesystems won. Introducing SMFS - Supermemory Filesystem we brought the best of these worlds into one single product - it's a filesystem, but agent can also do semantic search using grep. live today. Try it! Works with any sandbox, you mount and sync with cloud, it has a sync engine built in, all filetypes supported - even images and videos can be grepped. So, what do you choose - Filesystems, or vector search? we have both!
1:17
DhravyaShah's profile picture

Filesystems vs Vector search is the new MCP vs CLI. Claude uses agentic search. And Dens Sumesh at mintlify like filesystems too. but Retrieval is still used by Notion, Cursor, and others. We hit the cafes of SF to see what people want. - The debate is hot. Filesystems won by 1 point - filesystems feel very simple and intuitive. - RAG requires embedding, vector search and other stuff filesystems won. Introducing SMFS - Supermemory Filesystem we brought the best of these worlds into one single product - it's a filesystem, but agent can also do semantic search using grep. live today. Try it! Works with any sandbox, you mount and sync with cloud, it has a sync engine built in, all filetypes supported - even images and videos can be grepped. So, what do you choose - Filesystems, or vector search? we have both!

Dhravya Shah

153,119 views • 2 months ago

The Context Cloud for agents is here. Introducing the new supermemory. A new way to do context, for your agents Everything you need for context - Memory, RAG, Filesystems, Profiles, are now available as blocks you can compose to build something for your use case
5:27
DhravyaShah's profile picture

The Context Cloud for agents is here. Introducing the new supermemory. A new way to do context, for your agents Everything you need for context - Memory, RAG, Filesystems, Profiles, are now available as blocks you can compose to build something for your use case

Dhravya Shah

91,951 views • 1 month ago

the team cooked an insane demo on SMFS dot ai just put in the files (made with css and claude!)
0:30
DhravyaShah's profile picture

the team cooked an insane demo on SMFS dot ai just put in the files (made with css and claude!)

Dhravya Shah

107,396 views • 2 months ago

Introducing webpull instantly pull any website into a directory of clean, searchable markdown files npx webpull
0:38
DhravyaShah's profile picture

Introducing webpull instantly pull any website into a directory of clean, searchable markdown files npx webpull

Dhravya Shah

82,224 views • 2 months ago

Disclaimer: You can call, message, or do ANY task on a locked iPhone yeah. "call 911" or "text mom" or anything else apple security is supposed to be good?
0:33
DhravyaShah's profile picture

Disclaimer: You can call, message, or do ANY task on a locked iPhone yeah. "call 911" or "text mom" or anything else apple security is supposed to be good?

Dhravya Shah

186,367 views • 8 months ago

meta just released llama 3.1 you can now build & deploy a quick chatbot that learns more and more about you as you talk to it. in literally less than 10 minutes. here's how. there's no better time to build and ship stuff. these open models are incredible!
9:26
DhravyaShah's profile picture

meta just released llama 3.1 you can now build & deploy a quick chatbot that learns more and more about you as you talk to it. in literally less than 10 minutes. here's how. there's no better time to build and ship stuff. these open models are incredible!

Dhravya Shah

409,226 views • 2 years ago

I built the best memory for voice agents while sponsoring Y Combinator hackathon. Introducing: Voice AI + Memory! We built a deep supermemory integration for Pipecat AI, so now even your agents have great memory With user profiles, these are almost-instant latency as well :)
2:11
DhravyaShah's profile picture

I built the best memory for voice agents while sponsoring Y Combinator hackathon. Introducing: Voice AI + Memory! We built a deep supermemory integration for Pipecat AI, so now even your agents have great memory With user profiles, these are almost-instant latency as well :)

Dhravya Shah

83,207 views • 4 months ago

We went from being the worst, to the best AI memory system in the world. While being students with ~no prior research experience. .... but, how do we measure "good" vs bad memory? Evals (and vibes!) here's a small video on how we think about memory.
3:09
DhravyaShah's profile picture

We went from being the worst, to the best AI memory system in the world. While being students with ~no prior research experience. .... but, how do we measure "good" vs bad memory? Evals (and vibes!) here's a small video on how we think about memory.

Dhravya Shah

120,929 views • 7 months ago

Memory on the harness level after 2 years... i've started writing blogs again! In this post, I dive _very_ deep into the different ways to compose and add memory to the harness for various different use cases. it's interactive. it's fun. you can listen to it too!
0:33
DhravyaShah's profile picture

Memory on the harness level after 2 years... i've started writing blogs again! In this post, I dive _very_ deep into the different ways to compose and add memory to the harness for various different use cases. it's interactive. it's fun. you can listen to it too!

Dhravya Shah

20,621 views • 28 days ago

Introducing the all new supermemory 💥 we killed the AI memory lock-in. A universal memory for all the apps you use: - MCP connect to Claude / Cursor / ChatGPT - Graph view of your life - Projects to organize your life free to use. $9/m for first 100 pro subs. demo below
2:02
DhravyaShah's profile picture

Introducing the all new supermemory 💥 we killed the AI memory lock-in. A universal memory for all the apps you use: - MCP connect to Claude / Cursor / ChatGPT - Graph view of your life - Projects to organize your life free to use. $9/m for first 100 pro subs. demo below

Dhravya Shah

170,604 views • 1 year ago

25 THOUSAND STARS ON GITHUB And the most important feature is yet to release keep an eye....
0:25
DhravyaShah's profile picture

25 THOUSAND STARS ON GITHUB And the most important feature is yet to release keep an eye....

Dhravya Shah

23,300 views • 1 month ago

Introducing supermemory for Codex! give your codex better memory while having it interoperable between every other provider - OpenCode, Claude code, etc 1. Codex can see the timeline 2. It has your profile 3. Both explicit and implicit (dreaming) memory
1:44
DhravyaShah's profile picture

Introducing supermemory for Codex! give your codex better memory while having it interoperable between every other provider - OpenCode, Claude code, etc 1. Codex can see the timeline 2. It has your profile 3. Both explicit and implicit (dreaming) memory

Dhravya Shah

29,816 views • 2 months ago

Introducing supermemory (again). an ai second brain for all your saved stuff - bring bookmarks/tweets/write notes - look for content using the chatbot - discover cool stuff you saved long ago. 6,000 ppl using this now. buildspace
1:28
DhravyaShah's profile picture

Introducing supermemory (again). an ai second brain for all your saved stuff - bring bookmarks/tweets/write notes - look for content using the chatbot - discover cool stuff you saved long ago. 6,000 ppl using this now. buildspace

Dhravya Shah

200,272 views • 2 years ago

Agent observability can be more than logs and traces. Introducing Qualitative Analysis. it's FREE for next 3 months 👇 @Supermemory can now automatically give you reports on your users/agents - which you can tailor and ask questions to! Eg: "What's the split of developers?"
1:10
DhravyaShah's profile picture

Agent observability can be more than logs and traces. Introducing Qualitative Analysis. it's FREE for next 3 months 👇 @Supermemory can now automatically give you reports on your users/agents - which you can tailor and ask questions to! Eg: "What's the split of developers?"

Dhravya Shah

23,702 views • 1 month ago

We scored 99% on LongMemEval to prove a point. Eval results aren't the only thing that matter.
6:48
DhravyaShah's profile picture

We scored 99% on LongMemEval to prove a point. Eval results aren't the only thing that matter.

Dhravya Shah

41,258 views • 3 months ago

build your own memory... only if: - you can top the benchmarks - want to spend more money - have more time. - want to deal with infrastructure, and not actually build a product but for most people, you should just... use supermemory
1:40
DhravyaShah's profile picture

build your own memory... only if: - you can top the benchmarks - want to spend more money - have more time. - want to deal with infrastructure, and not actually build a product but for most people, you should just... use supermemory

Dhravya Shah

58,959 views • 6 months ago

woah this went too viral. In a world of agents, do humans even need to use a UI? Re-introducing the supermemory CLI! agents are now first class citizen. You can create scoped access controls for them, so you never have to visit our console. > npx supermemory setup
3:37
DhravyaShah's profile picture

woah this went too viral. In a world of agents, do humans even need to use a UI? Re-introducing the supermemory CLI! agents are now first class citizen. You can create scoped access controls for them, so you never have to visit our console. > npx supermemory setup

Dhravya Shah

24,469 views • 3 months ago