Загрузка видео...

Не удалось загрузить видео

На главную

Career update: i'm joining supermemory to lead Dev GTM. supermemory is the memory layer for AI products, we got the best public results on AI memory by a wide margin, 95% on the leading benchmarks. my role will be to make it easy for everyone to use. demos, walkthroughs,...

Muskanjain0401's profile picture

Muskan Jain

21,522 subscribers

112,065 просмотров • 1 месяц назад •via X (Twitter)

ОбразованиеНовости и политикаНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

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

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

668,992 просмотров • 1 месяц назад

Tried out stripe projects this week! built a customer support bot with hermes from Nous Research + supermemory. bot remembers every customer across sessions. the piece worth highlighting, Stripe projects ships a hermes skill that lets the agent auto-provision supermemory itself. ask hermes to build the bot, it runs stripe projects add supermemory/memory. stripe creates the supermemory account, syncs the api key to .env, and bills it on your stripe invoice. and supermemory is one of 30+ providers. databases ( Neon Postgres, Supabase), hosting ( Vercel , Cloudflare), auth ( Clerk), search ( Exa), analytics ( PostHog). one CLI for the whole stack.
2:59

Tried out stripe projects this week! built a customer support bot with hermes from Nous Research + supermemory. bot remembers every customer across sessions. the piece worth highlighting, Stripe projects ships a hermes skill that lets the agent auto-provision supermemory itself. ask hermes to build the bot, it runs stripe projects add supermemory/memory. stripe creates the supermemory account, syncs the api key to .env, and bills it on your stripe invoice. and supermemory is one of 30+ providers. databases ( Neon Postgres, Supabase), hosting ( Vercel , Cloudflare), auth ( Clerk), search ( Exa), analytics ( PostHog). one CLI for the whole stack.

Muskan Jain

20,335 просмотров • 1 месяц назад

Introducing Memory 101 🧠 Every ai tool you use is a goldfish. brilliant for one chat, close the tab and it forgets you completely. memory is the most underbuilt layer in ai right now. so we're explaining how it actually works, one episode at a time. coming up: → rag vs memory, why most "ai memory" is just search → the 5 things real memory needs: facts, profiles, graphs, time, forgetting → why good memory has to forget things follow along!
0:50

Introducing Memory 101 🧠 Every ai tool you use is a goldfish. brilliant for one chat, close the tab and it forgets you completely. memory is the most underbuilt layer in ai right now. so we're explaining how it actually works, one episode at a time. coming up: → rag vs memory, why most "ai memory" is just search → the 5 things real memory needs: facts, profiles, graphs, time, forgetting → why good memory has to forget things follow along!

supermemory

17,235 просмотров • 1 месяц назад

He sold a company at 16. Then raised $3M at 19 without a co-founder. Today he gave the whole thing away. supermemory now runs fully local, self-contained, and the binary is open source. Solo Founders Podcast ep 14 is live with Dhravya Shah of Supermemory. 00:49 How a side project became a company 08:57 "Building was my way of doing art" 14:35 Saying no to VCs for 9 months 24:44 Launching Supermemory Local 29:29 Killing his own viral hit, mid-fundraise 46:39 Why ChatGPT "fails" memory benchmarks on purpose 52:57 The co-founder breakup that made him go solo 01:10:19 The case for solo founding
1:12:46

He sold a company at 16. Then raised $3M at 19 without a co-founder. Today he gave the whole thing away. supermemory now runs fully local, self-contained, and the binary is open source. Solo Founders Podcast ep 14 is live with Dhravya Shah of Supermemory. 00:49 How a side project became a company 08:57 "Building was my way of doing art" 14:35 Saying no to VCs for 9 months 24:44 Launching Supermemory Local 29:29 Killing his own viral hit, mid-fundraise 46:39 Why ChatGPT "fails" memory benchmarks on purpose 52:57 The co-founder breakup that made him go solo 01:10:19 The case for solo founding

weisser

138,114 просмотров • 1 месяц назад

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

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 просмотров • 1 год назад

For years, I have been building the perfect knowledge assistant. I mean, that's what supermemory originally launched as! Today, we are relaunching the consumer side of supermemory. Fully powered by the supermemory API. After our Claude code, OpenClaw and other launches blew up to millions of views, it was clear: Consumers WANT their context to be interoperable within models they use. They want their AI to truly understand them, have great memory, and build over time. They want to use this truly wherever they are - or with every AI they use - Claude code, or OpenClaw, or Raycast. They want to bring their memories from chatgpt, claude, twitter bookmarks, and teach their AI, about them. This is your knowledge, and supermemory is the assistant. evolving, understanding, growing with time.
0:49

For years, I have been building the perfect knowledge assistant. I mean, that's what supermemory originally launched as! Today, we are relaunching the consumer side of supermemory. Fully powered by the supermemory API. After our Claude code, OpenClaw and other launches blew up to millions of views, it was clear: Consumers WANT their context to be interoperable within models they use. They want their AI to truly understand them, have great memory, and build over time. They want to use this truly wherever they are - or with every AI they use - Claude code, or OpenClaw, or Raycast. They want to bring their memories from chatgpt, claude, twitter bookmarks, and teach their AI, about them. This is your knowledge, and supermemory is the assistant. evolving, understanding, growing with time.

Dhravya Shah

36,660 просмотров • 5 месяцев назад

Introducing Supermemory - an AI hub for all your bookmarks and notes. content you consume often gets lost. put it in your second brain to make use of it. me and my friends have been working on this open source project for months now - but the story is actually crazy 🧵
0:24

Introducing Supermemory - an AI hub for all your bookmarks and notes. content you consume often gets lost. put it in your second brain to make use of it. me and my friends have been working on this open source project for months now - but the story is actually crazy 🧵

Dhravya Shah

73,249 просмотров • 2 лет назад

every AI tweet writer sounds like chatgpt… so i built one that sounds like me with supermemory! it scrapes viral AI twitter every day, rewrites the bangers in my voice, and posts them straight to X. >> the stack: apify scrapes, perplexity writes, and supermemory is the memory layer that makes it actually sound like me. >> one container learns my voice as its own entity, another remembers everything i've ever shipped, so it writes like me and never repeats a take. want it? comment below ↓
1:37

every AI tweet writer sounds like chatgpt… so i built one that sounds like me with supermemory! it scrapes viral AI twitter every day, rewrites the bangers in my voice, and posts them straight to X. >> the stack: apify scrapes, perplexity writes, and supermemory is the memory layer that makes it actually sound like me. >> one container learns my voice as its own entity, another remembers everything i've ever shipped, so it writes like me and never repeats a take. want it? comment below ↓

Muskan Jain

13,961 просмотров • 20 дней назад

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

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 просмотров • 6 месяцев назад

Memory for OpenClaw is now Native! Our first OpenClaw Memory Skill was a massive success: 30k+ downloads in a week and 500k+ organic impressions overnight for launch post. But we knew memory needed to be native. On March 21, OpenClaw merged PR #50848, allowing us to go beyond the skill layer and integrate directly into the agent’s context assembly flow. We try to make OpenClaw a truly 24/7 employee capable of complex workflows. The technical setup isn’t the hardest part but the real challenge is giving it a "brain" that remembers exact project details, past decisions, and team changes over time. The Native Memory Plugin is now live on NPM & ClawHub. Here is what it brings to your OpenClaw agents: 👉 Native Integration: Automatically manages a Three-Layer Memory architecture (Context Tree, Workspace Memory, Daily Memory). 👉 Git-like Stateful Memory: Organizes memory into a semantic hierarchy of human-readable, diffable Markdown files. You always get updated knowledge and can actually see and fix what your agent learns. 👉 Top Market Accuracy: Achieves an industry-leading 92.2% retrieval accuracy (LoCoMo & LongMemEval benchmarks), maintaining 90% accuracy even with cheap, lightweight models. 👉 Local-first & Portable: Local-by-default, fully portable for multi-agent teams. 👉 Super Easy Setup
1:46

Memory for OpenClaw is now Native! Our first OpenClaw Memory Skill was a massive success: 30k+ downloads in a week and 500k+ organic impressions overnight for launch post. But we knew memory needed to be native. On March 21, OpenClaw merged PR #50848, allowing us to go beyond the skill layer and integrate directly into the agent’s context assembly flow. We try to make OpenClaw a truly 24/7 employee capable of complex workflows. The technical setup isn’t the hardest part but the real challenge is giving it a "brain" that remembers exact project details, past decisions, and team changes over time. The Native Memory Plugin is now live on NPM & ClawHub. Here is what it brings to your OpenClaw agents: 👉 Native Integration: Automatically manages a Three-Layer Memory architecture (Context Tree, Workspace Memory, Daily Memory). 👉 Git-like Stateful Memory: Organizes memory into a semantic hierarchy of human-readable, diffable Markdown files. You always get updated knowledge and can actually see and fix what your agent learns. 👉 Top Market Accuracy: Achieves an industry-leading 92.2% retrieval accuracy (LoCoMo & LongMemEval benchmarks), maintaining 90% accuracy even with cheap, lightweight models. 👉 Local-first & Portable: Local-by-default, fully portable for multi-agent teams. 👉 Super Easy Setup

andy nguyen

169,136 просмотров • 4 месяцев назад

New short course: Long-Term Agentic Memory with LangGraph. Learn to build an agent with long-term memory in this course developed in collaboration with taught by its Co-Founder and CEO, Harrison Chase! Personal assistance and productivity tasks have become important use cases for agents. An important feature of an AI assistant, such as a coding or calendar assistant, is its ability to keep improving over time from its experience. Agent memory is the key capability that enables this. To add memory to an agent, you must first figure out what to store and what to retrieve when it is time to use the information. Additionally, you’ll have to decide when to update the stored information. For example, you might update in each iteration loop of the agent or perform updates in the background, with a helper agent. In this course, you will learn a mental framework to build agents with long-term memory. You'll create a useful email assistant that can respond, ignore, and notify using writing, scheduling, and memory-management tools. You’ll develop your agent's memory by adding facts to its memory store, provide examples to learn the user's preferences, and optimize system prompts to evolve instructions based on previous responses. In detail, you’ll: - Learn how the three types of memory--semantic, episodic, and procedural–and the two update mechanisms–via hot path and in the background–apply to your agents. - Build an email agent with writing, scheduling, and availability tools, along with a router that triages incoming email and handles it accordingly by ignoring, responding, or notifying the user. - Add tools to your email agent that allow it to operate on semantic memory by learning facts about the user, storing them in a long-term memory store, and searching over them in future interactions. - Incorporate episodic memory, in the form of few-shot examples, in the triage step of your agents to help them learn and update user preferences. - Add procedural memory as system prompts, optimized with feedback to improve the instructions the agent follows. Learn how to approach memory in agents, and start building agents with long-term memory with LangGraph! Please sign up here:
2:06

New short course: Long-Term Agentic Memory with LangGraph. Learn to build an agent with long-term memory in this course developed in collaboration with taught by its Co-Founder and CEO, Harrison Chase! Personal assistance and productivity tasks have become important use cases for agents. An important feature of an AI assistant, such as a coding or calendar assistant, is its ability to keep improving over time from its experience. Agent memory is the key capability that enables this. To add memory to an agent, you must first figure out what to store and what to retrieve when it is time to use the information. Additionally, you’ll have to decide when to update the stored information. For example, you might update in each iteration loop of the agent or perform updates in the background, with a helper agent. In this course, you will learn a mental framework to build agents with long-term memory. You'll create a useful email assistant that can respond, ignore, and notify using writing, scheduling, and memory-management tools. You’ll develop your agent's memory by adding facts to its memory store, provide examples to learn the user's preferences, and optimize system prompts to evolve instructions based on previous responses. In detail, you’ll: - Learn how the three types of memory--semantic, episodic, and procedural–and the two update mechanisms–via hot path and in the background–apply to your agents. - Build an email agent with writing, scheduling, and availability tools, along with a router that triages incoming email and handles it accordingly by ignoring, responding, or notifying the user. - Add tools to your email agent that allow it to operate on semantic memory by learning facts about the user, storing them in a long-term memory store, and searching over them in future interactions. - Incorporate episodic memory, in the form of few-shot examples, in the triage step of your agents to help them learn and update user preferences. - Add procedural memory as system prompts, optimized with feedback to improve the instructions the agent follows. Learn how to approach memory in agents, and start building agents with long-term memory with LangGraph! Please sign up here:

Andrew Ng

131,850 просмотров • 1 год назад

our big bet with WALRUS MEMORY is that memory becomes a fully composable, transactable part of what ai agents need to do in the future and it's going to be an incredibly valuable asset and we've built a primitive that lets you fully own and carry it across every agent you use
1:20

our big bet with WALRUS MEMORY is that memory becomes a fully composable, transactable part of what ai agents need to do in the future and it's going to be an incredibly valuable asset and we've built a primitive that lets you fully own and carry it across every agent you use

Adeniyi.sui

26,501 просмотров • 1 месяц назад

I turned AI agent orchestration into a full fledged game. To start this launch, I’m also hosting a tournament with a growing prize pool (starting at $3k) for the first 24 hours. Two players face off a team of AI agents, armed with strategy prompts - utilizing memory, tool-calling, and inter-agent communication to win. Each agent has a battle memory - they learn and synergize with the playstyle of their commander to produce the best results. I’ve been working on this for the past 2 months, so please check it out, my dms are open for feedback :D Documentation: Project Twitter: aiarena Website:
0:30

I turned AI agent orchestration into a full fledged game. To start this launch, I’m also hosting a tournament with a growing prize pool (starting at $3k) for the first 24 hours. Two players face off a team of AI agents, armed with strategy prompts - utilizing memory, tool-calling, and inter-agent communication to win. Each agent has a battle memory - they learn and synergize with the playstyle of their commander to produce the best results. I’ve been working on this for the past 2 months, so please check it out, my dms are open for feedback :D Documentation: Project Twitter: aiarena Website:

𝕱𝖔𝖗𝕷𝖔𝖔𝖕

10,867 просмотров • 3 месяцев назад

Autonomous AI agents can’t afford a memory problem. After OpenClaw, insane numbers of autonomous agents are coming online, but all of them have a memory layer that's breaking. I have been playing around with SureThing these days. It is an autonomous AI agent designed with a native memory layer. → it learns your patterns → integrates with 1000+ apps → fully autonomous They actually benchmarked memory depth. SureThing: 84.8, ChatGPT: 40, OpenClaw: 60. The gap speaks for itself. SureThing is invitation-only. The crazy part is that you have to talk to SureThing agent itself to get the invite code. The onboarding is the product demo. You feel the memory and judgment before you even have an account. Try it here: Partnered with SureThing for this post. Thanks to the team for the support.
2:06

Autonomous AI agents can’t afford a memory problem. After OpenClaw, insane numbers of autonomous agents are coming online, but all of them have a memory layer that's breaking. I have been playing around with SureThing these days. It is an autonomous AI agent designed with a native memory layer. → it learns your patterns → integrates with 1000+ apps → fully autonomous They actually benchmarked memory depth. SureThing: 84.8, ChatGPT: 40, OpenClaw: 60. The gap speaks for itself. SureThing is invitation-only. The crazy part is that you have to talk to SureThing agent itself to get the invite code. The onboarding is the product demo. You feel the memory and judgment before you even have an account. Try it here: Partnered with SureThing for this post. Thanks to the team for the support.

Pratham

80,634 просмотров • 5 месяцев назад

Yesterday, I joined TBPN to talk about what it really means to give AI a memory. And, why that’s becoming the next big moat. We discussed: - Why today’s AI apps are stateless - How memory is quickly becoming the real moat for AI systems - How Mem0 is decoupling memory from models - Why users should be able to own and carry their AI memories across apps - And, how 200 cold emails changed my life🙂 Appreciate John Coogan, Jordi Hays & the TBPN team for having me and for such a thoughtful discussion around the future of AI infrastructure.
7:08

Yesterday, I joined TBPN to talk about what it really means to give AI a memory. And, why that’s becoming the next big moat. We discussed: - Why today’s AI apps are stateless - How memory is quickly becoming the real moat for AI systems - How Mem0 is decoupling memory from models - Why users should be able to own and carry their AI memories across apps - And, how 200 cold emails changed my life🙂 Appreciate John Coogan, Jordi Hays & the TBPN team for having me and for such a thoughtful discussion around the future of AI infrastructure.

Taranjeet

14,913 просмотров • 9 месяцев назад

I spent today turning a blank Hermes install into a sovereign local agent on my RTX 5090. always-on, reachable over telegram, fully local. here's everything it can do. it runs Qwen3.6-27B on the 5090 and answers from my phone over telegram. ~~~ I first made it faster. switched to the MTP build for self-speculative decoding: 62 > 115 tokens/sec. ~~~ it now benchmarks models on command. I ask it to speed-test a gguf and it stops its own model server to free the gpu, runs llama-bench, renders a card, sends it to my phone, then restarts itself. it's never left offline. ~~~ it also knows me very well. I pointed it to my private HF repo where I store all my AI traces since I started using it. I created a local markdown memory vault, seeded from my own history, with semantic search over it. ~~~ the whole stack stays home: weights on disk, inference on the 5090, the agent in my pocket. here is the video it created to showcase everything it has now.
0:32

I spent today turning a blank Hermes install into a sovereign local agent on my RTX 5090. always-on, reachable over telegram, fully local. here's everything it can do. it runs Qwen3.6-27B on the 5090 and answers from my phone over telegram. ~~~ I first made it faster. switched to the MTP build for self-speculative decoding: 62 > 115 tokens/sec. ~~~ it now benchmarks models on command. I ask it to speed-test a gguf and it stops its own model server to free the gpu, runs llama-bench, renders a card, sends it to my phone, then restarts itself. it's never left offline. ~~~ it also knows me very well. I pointed it to my private HF repo where I store all my AI traces since I started using it. I created a local markdown memory vault, seeded from my own history, with semantic search over it. ~~~ the whole stack stays home: weights on disk, inference on the 5090, the agent in my pocket. here is the video it created to showcase everything it has now.

witcheer

15,041 просмотров • 2 месяцев назад

The creator of High Bandwidth Memory (HBM) put a number on the AI build that should stop every infra investor cold. A cluster of a million GPUs runs at roughly 10-20% utilization (Save this). Kim Jung-ho spent thirty years building what feeds the GPU, and his claim is that the GPU is barely working. Here is what is actually happening. Every time a model generates output, the data has to be read out of memory, computed, and written back. The read and the write swallow almost the entire cycle. While that data moves, the GPU does nothing. It sits there, fully powered, fully paid for, waiting. By Kim's estimate the memory is doing only about 30 percent of the work it needs to do. The processor idles the rest. So a million installed GPUs run at 10 to 20 percent. You are not compute constrained. You are memory constrained, and the expensive part is standing around. Adding more GPUs does not fix this. It gives you more processors starving for the same data. Here is the part that decides the next decade. Memory can grow. When a cell cannot shrink any further, you stack it into a high-rise, layer on layer. A GPU cannot be stacked. It runs too hot and needs a cooler bolted to its back, so the one move that rescues memory is closed to the processor. The thing that can keep stacking compounds. The thing that cannot plateaus. The marginal dollar in an AI build now buys more by fixing the memory path than by bolting on another idle GPU. Which is why the companies that control memory bandwidth and supply are not suppliers to the AI trade. They are the AI trade.
0:50

The creator of High Bandwidth Memory (HBM) put a number on the AI build that should stop every infra investor cold. A cluster of a million GPUs runs at roughly 10-20% utilization (Save this). Kim Jung-ho spent thirty years building what feeds the GPU, and his claim is that the GPU is barely working. Here is what is actually happening. Every time a model generates output, the data has to be read out of memory, computed, and written back. The read and the write swallow almost the entire cycle. While that data moves, the GPU does nothing. It sits there, fully powered, fully paid for, waiting. By Kim's estimate the memory is doing only about 30 percent of the work it needs to do. The processor idles the rest. So a million installed GPUs run at 10 to 20 percent. You are not compute constrained. You are memory constrained, and the expensive part is standing around. Adding more GPUs does not fix this. It gives you more processors starving for the same data. Here is the part that decides the next decade. Memory can grow. When a cell cannot shrink any further, you stack it into a high-rise, layer on layer. A GPU cannot be stacked. It runs too hot and needs a cooler bolted to its back, so the one move that rescues memory is closed to the processor. The thing that can keep stacking compounds. The thing that cannot plateaus. The marginal dollar in an AI build now buys more by fixing the memory path than by bolting on another idle GPU. Which is why the companies that control memory bandwidth and supply are not suppliers to the AI trade. They are the AI trade.

Fireside Alpha

38,370 просмотров • 1 месяц назад

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

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 просмотров • 7 месяцев назад