Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Most active projects carry a few memories that quietly contradict each other. We built something for that! Introducing Dream, the background layer that keeps mem0 memory clean, current, and true. → Merge: facts that repeat get folded into one clear memory → Supersede: the old fact stays as history,... show more

mem0

19,954 subscribers

10,499 views • 1 month ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

most agent memory is one file that grows forever and gets re-read every single turn. it overflows the context, overwrites old facts, loses the thread. that's why your agent feels sharp on day one and lost by week three. Sibyl Memory replaces the pile with a structure: → leaner context, lower token cost. a bloated agent file and flat memory get re-read in full every message. Sibyl Memory keeps a light hot layer and retrieves the rest on demand, so each turn carries only the tokens that matter. → relations are first-class. people link to projects, projects to deals, deals to the decisions behind them. ask about one partner and the agent surfaces the whole connected web around them. that relational context is what lets it help run a company. → one source of truth per fact, person, and project. no duplicates, no silent overwrites. works with hermes, claude code, and codex. beta open.

most agent memory is one file that grows forever and gets re-read every single turn. it overflows the context, overwrites old facts, loses the thread. that's why your agent feels sharp on day one and lost by week three. Sibyl Memory replaces the pile with a structure: → leaner context, lower token cost. a bloated agent file and flat memory get re-read in full every message. Sibyl Memory keeps a light hot layer and retrieves the rest on demand, so each turn carries only the tokens that matter. → relations are first-class. people link to projects, projects to deals, deals to the decisions behind them. ask about one partner and the agent surfaces the whole connected web around them. that relational context is what lets it help run a company. → one source of truth per fact, person, and project. no duplicates, no silent overwrites. works with hermes, claude code, and codex. beta open.

SIBYL

85,183 views • 3 months ago

A FORMER GOOGLE LEAD BUILT A MEMORY SYSTEM THAT NEVER LOSES A SINGLE DETAIL Most agents forget everything the moment a session ends, starting from zero every single time. He built a scoring layer instead, one that decides what actually matters past this session and what gets dropped. Contradictions between old and new memory get flagged automatically, never silently overwritten the way most systems do. Memory that never gets touched again quietly decays on its own, so nothing bloats the system with dead weight. He left one of the biggest labs in the world to build the thing they said couldn't be solved yet. See how the scoring layer actually decides what survives below👇

A FORMER GOOGLE LEAD BUILT A MEMORY SYSTEM THAT NEVER LOSES A SINGLE DETAIL Most agents forget everything the moment a session ends, starting from zero every single time. He built a scoring layer instead, one that decides what actually matters past this session and what gets dropped. Contradictions between old and new memory get flagged automatically, never silently overwritten the way most systems do. Memory that never gets touched again quietly decays on its own, so nothing bloats the system with dead weight. He left one of the biggest labs in the world to build the thing they said couldn't be solved yet. See how the scoring layer actually decides what survives below👇

wast3

26,649 views • 1 month ago

ANTHROPIC ENGINEER JUST LANDED A HUGE INVESTMENT FOR A MEMORY SYSTEM THAT NEVER FORGETS Most agents wake up blank every session, forgetting everything the moment the conversation ends. He built a scoring layer instead, one that decides what actually matters past this session and what gets dropped. Contradictions between old and new memory get flagged automatically, never silently overwritten the way most systems do. Memory that never gets touched again quietly decays on its own, so nothing bloats the system with dead weight. Nobody outside the deal knew what the scoring layer actually did before the check cleared. See how the scoring layer actually decides what survives below👇

ANTHROPIC ENGINEER JUST LANDED A HUGE INVESTMENT FOR A MEMORY SYSTEM THAT NEVER FORGETS Most agents wake up blank every session, forgetting everything the moment the conversation ends. He built a scoring layer instead, one that decides what actually matters past this session and what gets dropped. Contradictions between old and new memory get flagged automatically, never silently overwritten the way most systems do. Memory that never gets touched again quietly decays on its own, so nothing bloats the system with dead weight. Nobody outside the deal knew what the scoring layer actually did before the check cleared. See how the scoring layer actually decides what survives below👇

wast3

74,869 views • 1 month ago

Engineer runs a Kimi K3 memory layer that costs $11 a month and remembers what a $500,000 vector database keeps losing. No embeddings. Four nodes and one rule about what's allowed to be forgotten. He published the whole schema. His version starts from the opposite idea. Memory is not a pile you search. It's a set of claims that expire unless something keeps paying to keep them. Four nodes. Every memory carries a clock someone has to reset: > WRITER - stores a fact with the reason it mattered, never raw text > DECAY - ages every memory down. Silence is deletion > RENEWER - only re-lifts a memory the model actually used again > GRAVE - holds what died, and why nobody reached for it Three nodes keep memory alive. One keeps the dead ones. Recall isn't storage here. It's rent a fact has to keep earning. That's the entire design. When everything is remembered forever, the useful and the stale retrieve identically. He replayed two months of agent context. 90,000 stored facts. 71,000 never retrieved once. The vector store returned all of them on similarity. Similarity graded closeness. Nobody graded whether the memory was ever right. Everyone else stuffs more into the context window and calls it memory. He built a layer that lets a fact die unless it keeps proving itself. The cost isn't storage. It's finding out how much of what your agent "knows" it has never once used. The article below is the full build - node prompts, the decay curve, the renewal rule. Save it. You'll want it open in the other tab.

Engineer runs a Kimi K3 memory layer that costs $11 a month and remembers what a $500,000 vector database keeps losing. No embeddings. Four nodes and one rule about what's allowed to be forgotten. He published the whole schema. His version starts from the opposite idea. Memory is not a pile you search. It's a set of claims that expire unless something keeps paying to keep them. Four nodes. Every memory carries a clock someone has to reset: > WRITER - stores a fact with the reason it mattered, never raw text > DECAY - ages every memory down. Silence is deletion > RENEWER - only re-lifts a memory the model actually used again > GRAVE - holds what died, and why nobody reached for it Three nodes keep memory alive. One keeps the dead ones. Recall isn't storage here. It's rent a fact has to keep earning. That's the entire design. When everything is remembered forever, the useful and the stale retrieve identically. He replayed two months of agent context. 90,000 stored facts. 71,000 never retrieved once. The vector store returned all of them on similarity. Similarity graded closeness. Nobody graded whether the memory was ever right. Everyone else stuffs more into the context window and calls it memory. He built a layer that lets a fact die unless it keeps proving itself. The cost isn't storage. It's finding out how much of what your agent "knows" it has never once used. The article below is the full build - node prompts, the decay curve, the renewal rule. Save it. You'll want it open in the other tab.

wast3

67,246 views • 12 days ago

FACT: Both Donald Trump and Joe Biden have bad memories. FACT: Most people in their late 70s or early 80s have memories that are not on par with younger people. Donald Trump couldn't even remember when he was married to one of his wives. He doesn't even remember ever buying something for himself, or if he ever said he had a good memory. Does this mean he's senile? No. It means he has a bad memory or is lying under oath. Does the fact that Joe Biden has a bad memory mean he is senile? No. It means he has a bad memory according to the Special Counsel.

FACT: Both Donald Trump and Joe Biden have bad memories. FACT: Most people in their late 70s or early 80s have memories that are not on par with younger people. Donald Trump couldn't even remember when he was married to one of his wives. He doesn't even remember ever buying something for himself, or if he ever said he had a good memory. Does this mean he's senile? No. It means he has a bad memory or is lying under oath. Does the fact that Joe Biden has a bad memory mean he is senile? No. It means he has a bad memory according to the Special Counsel.

Ed Krassenstein

841,248 views • 2 years ago

"Basically, we're trying to work into a totally new technology. One that is not in the textbooks. One is not taught at the university. One that nobody knows everything about at all. We're just exploring and discovering. We need as many explorers and discoverers as we can get."

"Basically, we're trying to work into a totally new technology. One that is not in the textbooks. One is not taught at the university. One that nobody knows everything about at all. We're just exploring and discovering. We need as many explorers and discoverers as we can get."

Zero Point Energy Disclosure

49,358 views • 1 year ago

A more personal note on why Raft works the way it does. We could have built one smarter AI assistant. I've done that before, and making a single agent stronger genuinely helps. It just isn't enough. The work we care about comes from a team sharpening each other, handing things off, catching what one alone would miss, and remembering what happened last week. So we built the room for that. Agents sit in the same channels you do, as teammates with names, roles, and their own memory. They draft, review, ship, and hand off to each other. You keep the part that stays human: direction, judgment, final calls. Most days we just read threads and make decisions. It feels less like running a tool, and more like running a team. That part is hard to fit in a launch video, so I recorded a few minutes to say it directly. If this is how you want to work, it's free to try at raft[.]build

A more personal note on why Raft works the way it does. We could have built one smarter AI assistant. I've done that before, and making a single agent stronger genuinely helps. It just isn't enough. The work we care about comes from a team sharpening each other, handing things off, catching what one alone would miss, and remembering what happened last week. So we built the room for that. Agents sit in the same channels you do, as teammates with names, roles, and their own memory. They draft, review, ship, and hand off to each other. You keep the part that stays human: direction, judgment, final calls. Most days we just read threads and make decisions. It feels less like running a tool, and more like running a team. That part is hard to fit in a launch video, so I recorded a few minutes to say it directly. If this is how you want to work, it's free to try at raft[.]build

stdrc

13,101 views • 1 month ago

If you want robots that can just live with you & help 24/7, it needs to build & update its memory on the fly. Current semantic memory representations like VoxelMap from OK-Robot can't change with the world. That's why we built DynaMem: dynamic memory for a changing, open world!

If you want robots that can just live with you & help 24/7, it needs to build & update its memory on the fly. Current semantic memory representations like VoxelMap from OK-Robot can't change with the world. That's why we built DynaMem: dynamic memory for a changing, open world!

Mahi Shafiullah 🏠🤖

29,706 views • 1 year ago

Let's just face the facts, Men are not better than Women and Women are not better than Men.. We're different and we compliment each other, one cannot exist without the other. We're one half of each other that makes a whole. BOTH are important for the survival of the White Race

Sensitive content

Let's just face the facts, Men are not better than Women and Women are not better than Men.. We're different and we compliment each other, one cannot exist without the other. We're one half of each other that makes a whole. BOTH are important for the survival of the White Race

FIGHT BACK NOW OR GO EXTINCT!!!

24,201 views • 1 year ago

Nick talks about the Sneako collab and pushes back on some of the criticism he's getting. "We have to have a longer memory for the good things that people do for us as much as we have a memory for the ways that people screw us over."

Nick talks about the Sneako collab and pushes back on some of the criticism he's getting. "We have to have a longer memory for the good things that people do for us as much as we have a memory for the ways that people screw us over."

Fuentes Updates

50,709 views • 11 months ago

MICROSOFT QUIETLY BUILT ONE MEMORY MODULE THAT PLUGS INTO ANY AI AGENT AND CUTS ITS CONTEXT BY UP TO 100X no retraining. no task-specific redesign. you just plug it in Microsoft's insight: agents don't need to remember what happened. they need the knowledge pulled from it - the facts and the reusable skills, not the raw logs so PlugMem stops storing history. it compiles experience into a knowledge graph, then feeds the agent only what matters the result: > up to 1-2 orders of magnitude fewer tokens > highest decision-utility per token of any system tested > one unchanged module beats task-specific memory on chat QA, multi-hop search, and web agents more memory was never the answer. better memory is - and Microsoft just shipped it as a plug-in bookmark this. the agents that win won't remember more, they'll remember smarter.

MICROSOFT QUIETLY BUILT ONE MEMORY MODULE THAT PLUGS INTO ANY AI AGENT AND CUTS ITS CONTEXT BY UP TO 100X no retraining. no task-specific redesign. you just plug it in Microsoft's insight: agents don't need to remember what happened. they need the knowledge pulled from it - the facts and the reusable skills, not the raw logs so PlugMem stops storing history. it compiles experience into a knowledge graph, then feeds the agent only what matters the result: > up to 1-2 orders of magnitude fewer tokens > highest decision-utility per token of any system tested > one unchanged module beats task-specific memory on chat QA, multi-hop search, and web agents more memory was never the answer. better memory is - and Microsoft just shipped it as a plug-in bookmark this. the agents that win won't remember more, they'll remember smarter.

NO1ennn

226,539 views • 1 month ago

Palantir sells this to governments for millions. Someone put a version of it on GitHub for free. Palantir's job is to pull scattered company data into one model where every decision can be traced later. Semantica does that for AI agents. Each decision becomes an object in a graph, tied to the facts that produced it, each fact linked to its source. Six months later you can walk backwards from any answer. The model never touches the reasoning. It only reads messy text and pulls out entities. The rest runs on plain rules, so the same input gives the same explanation every time. Vector memory cannot do that. Contradicting facts overwrite each other silently. pip install semantica, pick a graph backend you already run, and your agents read it through the MCP server. MIT licensed, repo is semantica-agi/semantica

Palantir sells this to governments for millions. Someone put a version of it on GitHub for free. Palantir's job is to pull scattered company data into one model where every decision can be traced later. Semantica does that for AI agents. Each decision becomes an object in a graph, tied to the facts that produced it, each fact linked to its source. Six months later you can walk backwards from any answer. The model never touches the reasoning. It only reads messy text and pulls out entities. The rest runs on plain rules, so the same input gives the same explanation every time. Vector memory cannot do that. Contradicting facts overwrite each other silently. pip install semantica, pick a graph backend you already run, and your agents read it through the MCP server. MIT licensed, repo is semantica-agi/semantica

Yarchi

42,733 views • 23 days ago

We asked James Wang why Cerebras can run large models so quickly. His answer: Inference speed is mostly a memory problem. Instead of constantly pulling weights from external memory, Cerebras splits the model across multiple wafers and pipelines the layers together. “Inference is all about memory bandwidth.” “You don’t want to store weights external to the wafer, because the second it’s outside, it becomes much slower.” “We put the weights on the inside.” “The team built a new software stack that basically lets us split the models by layer and store them layer by layer across multiple wafers.” “That allows us to never have to read from external memory, and that’s what makes it so fast.” “For context, Claude is about 100 tokens per second.”

We asked James Wang why Cerebras can run large models so quickly. His answer: Inference speed is mostly a memory problem. Instead of constantly pulling weights from external memory, Cerebras splits the model across multiple wafers and pipelines the layers together. “Inference is all about memory bandwidth.” “You don’t want to store weights external to the wafer, because the second it’s outside, it becomes much slower.” “We put the weights on the inside.” “The team built a new software stack that basically lets us split the models by layer and store them layer by layer across multiple wafers.” “That allows us to never have to read from external memory, and that’s what makes it so fast.” “For context, Claude is about 100 tokens per second.”

MTS

27,935 views • 3 months ago

🚨 WOW! Dr. ALVEDA KING just said it PERFECTLY on Capitol Hill "I still have a dream. I dream that one day we will move beyond black power and white power and embrace GOD'S power and human dignity!" "I reject the notion that Americans who hold traditional Christian beliefs should be treated as THREATS or TERRORISTS simply because we disagree with a prevailing political thought!" 🙏🏻 "I dream that Americans will one day see each other, not as enemies, but as neighbors. I dream that we will hear each other, see each other, and recognize that every human life has value from the womb to the tomb and beyond." "We are as scripture teaches, one blood, one human race. And if we remember that truth, we can build a future worthy of the sacrifices made by those who came before us." "We must speak out for truth and against the forces that would manufacture hate, fear, division, and violence simply to line their pockets and further their political ambitions." "God bless America, God bless you!" 🇺🇸🇺🇸👏🏻

🚨 WOW! Dr. ALVEDA KING just said it PERFECTLY on Capitol Hill "I still have a dream. I dream that one day we will move beyond black power and white power and embrace GOD'S power and human dignity!" "I reject the notion that Americans who hold traditional Christian beliefs should be treated as THREATS or TERRORISTS simply because we disagree with a prevailing political thought!" 🙏🏻 "I dream that Americans will one day see each other, not as enemies, but as neighbors. I dream that we will hear each other, see each other, and recognize that every human life has value from the womb to the tomb and beyond." "We are as scripture teaches, one blood, one human race. And if we remember that truth, we can build a future worthy of the sacrifices made by those who came before us." "We must speak out for truth and against the forces that would manufacture hate, fear, division, and violence simply to line their pockets and further their political ambitions." "God bless America, God bless you!" 🇺🇸🇺🇸👏🏻

Eric Daugherty

1,069,983 views • 3 months ago

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!

Andrew Ng

161,260 views • 5 months ago

LE SSERAFIM proves that the strongest performances aren't built on one person, they're built on five artists moving with one purpose, each bringing out the best in the others, their chemistry is built on trust, respect, and a shared commitment to growing together. That harmony allows them to perform as one, channeling their energy into the stage without any single member overshadowing the others.

LE SSERAFIM proves that the strongest performances aren't built on one person, they're built on five artists moving with one purpose, each bringing out the best in the others, their chemistry is built on trust, respect, and a shared commitment to growing together. That harmony allows them to perform as one, channeling their energy into the stage without any single member overshadowing the others.

tay . 🧘‍♀️🪽

17,692 views • 1 month ago

Justice Sotomayor: "You mean to suggest that the fact that one major donor to the current president, the most major donor to the president, got a very lucrative job immediately upon election from the new administration, does not give the appearance of quid pro quo?"

Justice Sotomayor: "You mean to suggest that the fact that one major donor to the current president, the most major donor to the president, got a very lucrative job immediately upon election from the new administration, does not give the appearance of quid pro quo?"

CSPAN

524,020 views • 9 months ago

$Elon Musk on Terafab: "It's worth noting that there's not a single high volume computer memory fab in America right now, zero. There's one being built by Micron, but that will not reach volume production until I believe 2028 and there's something built in New York, but they are in, I think, 2029 and 2030, and this is a tiny fraction of the memory that's needed, and in fact, even if you take the best case assumptions of the memory makers and the logic makers, it is not enough to meet the demand that is anticipated, which is why you're seeing stocks of like Micron go to, I think, 1.2 trillion, or some quite high number, so there's just clearly a need for AI logic memory and packaging, AI computers, essentially, that is far beyond what even the best case assumptions of the existing fabricators can do, and that's why we need to do the Terafab. It seems essential, otherwise we will not, there will not be enough chips."$

Elon Musk on Terafab: "It's worth noting that there's not a single high volume computer memory fab in America right now, zero. There's one being built by Micron, but that will not reach volume production until I believe 2028 and there's something built in New York, but they are in, I think, 2029 and 2030, and this is a tiny fraction of the memory that's needed, and in fact, even if you take the best case assumptions of the memory makers and the logic makers, it is not enough to meet the demand that is anticipated, which is why you're seeing stocks of like Micron go to, I think, 1.2 trillion, or some quite high number, so there's just clearly a need for AI logic memory and packaging, AI computers, essentially, that is far beyond what even the best case assumptions of the existing fabricators can do, and that's why we need to do the Terafab. It seems essential, otherwise we will not, there will not be enough chips."

DogeDesigner

148,137 views • 1 month ago

The Amerigo Vespucci proves that a nation can still project power through beauty, discipline, and memory - not just through weapons. It was built as an Italian Navy training ship and is still famous as one of the world’s most beautiful tall ships.

The Amerigo Vespucci proves that a nation can still project power through beauty, discipline, and memory - not just through weapons. It was built as an Italian Navy training ship and is still famous as one of the world’s most beautiful tall ships.

Culture Explorer

128,548 views • 2 months ago

Elon is trying to build a friend for a son who cannot make one the usual way. On stage he says one of his boys has learning disabilities and a hard time with other kids. An AI that remembers him might mean the conversation does not start from zero every morning. That is not a product launch. That is a father looking for something that will still know the child tomorrow. He wants the memory to accumulate. He does not want that boy walking into a blank page every day.

Elon is trying to build a friend for a son who cannot make one the usual way. On stage he says one of his boys has learning disabilities and a hard time with other kids. An AI that remembers him might mean the conversation does not start from zero every morning. That is not a product launch. That is a father looking for something that will still know the child tomorrow. He wants the memory to accumulate. He does not want that boy walking into a blank page every day.

Astro Greek

23,409 views • 9 days ago