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.

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

30,556 subscribers

149,868 views • 18 days ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

33 Comments

supermemory18 days ago

>

supermemory18 days ago

read more here

Kevin Rajan18 days ago

i mean it looks cool i guess, but i learned absolutely nothing watching that video

Arnav Mehta18 days ago

supermemory x obsidian wen?

nick18 days ago

how is this not obsidian graph

AxonDB18 days ago

😭

grindyoway18 days ago

this is exact same as @AxonDB_ 😭

Justin.md18 days ago

I have to start blocking every ai reply account

InFlow18 days ago

super cool

AxonDB18 days ago

supermemory 🤝 axondb spot the difference challenge (impossible) 💀

Manish Baghel18 days ago

looks cool but I'd rather have a simpler version - a tree of running context.

supermemory18 days ago

a tree is a graph if you think about it

Manish Baghel18 days ago

it's a graph with constraints, the constraints make it simpler.

Code_of_Kai18 days ago

@obsdmd

Juan Arévalo17 days ago

Where is the open source GitHub repo ?

Almost Tomorrow18 days ago

When a source document is deleted, what happens to facts and links derived from it during background processing? Keeping old versions is useful, but users also need a way to remove information without a derived memory quietly bringing it back.

Lexifina18 days ago

Pretty KG!

Flix Muller18 days ago

Keeping old versions while updating memories is a really smart touch. That kind of context could make AI agents much more reliable over time.

Parijat17 days ago

How much does this cost? Is there a cheaper consumer version?

Mira Synth Tech18 days ago

Love this atomic facts background dreaming is such an elegant way to build memory

Rohan18 days ago

Isn't this too much preprocessing? How will it handle adding new documents?

Lawrence Stark17 days ago

may be technically impressive or not but all i can think of are JELLYFISHEEZ

Sakib🏴󠁧󠁢󠁳󠁣󠁴󠁿17 days ago

Swear we’re all building the same thing lol

Haziq Nordin17 days ago

Sprinkling random context dust into your agent is more likely to hurt than to help

Vidas Kulbis17 days ago

maybe we’ll see a market of ‘supers’ trending

Victor Sletten18 days ago

Why facts and not testimony? Lots of problems I bet you had to solve evaporate with that one simple trick

Clara AI | Tools & Updates18 days ago

A memory graph that evolves and preserves history is a big step forward

Jiang · Sylra16 days ago

A note can contain a fact, a question, or an idea I've already rejected. I'd want a memory graph to preserve those distinctions, so an unfinished thought doesn't quietly become something I supposedly believe.

Mo's fav goat17 days ago

If you're gonna post about your product, try to be less vague and show how this is different than everybody else.

Hao17 days ago

One memory I'd pay attention to: 'I already answered this.' My coding agent keeps reviving old questions after compaction. Remembering the request without remembering it's finished is a very convincing time loop.

rut18 days ago

lfggggg

Maheswar Bora18 days ago

Looks cool. But I’ve never found anything practical from this. Although, I’m ok with this level complexity if the an Agent can give me relevant insights (not the basic ones but something that’s not too easy for humans) from this graph.

retto17 days ago

how do you determine the most relevant fact given the state of the context window?

Related Videos

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, the new fact becomes the truth → Synthesis: not one memory — a pattern built from many, traced back to each one Excited to share that we're live today on Pro and Enterprise!

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, the new fact becomes the truth → Synthesis: not one memory — a pattern built from many, traced back to each one Excited to share that we're live today on Pro and Enterprise!

mem0

10,761 views • 3 months ago

Agents need continual learning. At supermemory, we are doubling down and pushing the frontier for memory and in-context learning, for every agent and use case. Introducing 𝚕𝚎𝚊𝚛𝚗𝚎𝚛-𝟷

Agents need continual learning. At supermemory, we are doubling down and pushing the frontier for memory and in-context learning, for every agent and use case. Introducing 𝚕𝚎𝚊𝚛𝚗𝚎𝚛-𝟷

supermemory

1,868,659 views • 2 months ago

Introducing the new supermemory console. Revamped design, better UX, new functionalities!

Introducing the new supermemory console. Revamped design, better UX, new functionalities!

supermemory

46,963 views • 1 month ago

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!

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 views • 4 months ago

Episode 1 of memory 101: the anatomy of memory.🧠 real memory isn't one thing. it's five: > facts > profiles > relationships > temporality > forgetting "AI memory" products build one of these primitives and stop. Real memory is when all five compose. Next, stay tuned for RAG ↓

Episode 1 of memory 101: the anatomy of memory.🧠 real memory isn't one thing. it's five: > facts > profiles > relationships > temporality > forgetting "AI memory" products build one of these primitives and stop. Real memory is when all five compose. Next, stay tuned for RAG ↓

supermemory

23,164 views • 4 months ago

Meet the minds building supermemory! 🧠 Our research engineer Prasanna breaks down how memory actually works, in your head, and in AI. inside the episode: → why forgetting is a feature and not a failure → what your hippocampus inside brain is really doing all day → how "dreaming" turns a messy day into long-term memory → what the AI labs get right, and wrong, when they copy the brain → why a bigger context window still isn't memory the line worth sitting with: stop asking where memory is stored. start asking what gets kept, and why the brain chose it. full episode below ↓

Meet the minds building supermemory! 🧠 Our research engineer Prasanna breaks down how memory actually works, in your head, and in AI. inside the episode: → why forgetting is a feature and not a failure → what your hippocampus inside brain is really doing all day → how "dreaming" turns a messy day into long-term memory → what the AI labs get right, and wrong, when they copy the brain → why a bigger context window still isn't memory the line worth sitting with: stop asking where memory is stored. start asking what gets kept, and why the brain chose it. full episode below ↓

supermemory

14,752 views • 3 months 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

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

172,195 views • 1 year ago

Introducing the supermemory company brain A super employee with all the knowledge of your company, lives in your slack. - Learns how the team works and talks - Works across all your tools - Permission controls built-in for big teams 2 mins to set up. just invite to slack 👇

Introducing the supermemory company brain A super employee with all the knowledge of your company, lives in your slack. - Learns how the team works and talks - Works across all your tools - Permission controls built-in for big teams 2 mins to set up. just invite to slack 👇

supermemory

622,272 views • 3 months ago

Magnific Plugin is now on ComfyUI → Generate image and video as native nodes → Upscale, relight, remove background → Stock and your own library, straight into the graph → Your graph stays local. Only the Magnific steps leave your machine Available for Mac and Windows now

Magnific Plugin is now on ComfyUI → Generate image and video as native nodes → Upscale, relight, remove background → Stock and your own library, straight into the graph → Your graph stays local. Only the Magnific steps leave your machine Available for Mac and Windows now

Magnific

12,372 views • 2 months ago

Everyone wants AI with a bigger memory, we think that's the wrong goal.. We sat down with Soham Daga, AI researcher at supermemory, for a deep dive into how machines actually remember you. what we get into: - why every AI forgets you - why forgetting is the hard part, not remembering - memory that understands time - going past reranking with aggregation - buckets for agent memory - SMFS, cutting tokens by 60% A conversation on the future of context, full episode below!

Everyone wants AI with a bigger memory, we think that's the wrong goal.. We sat down with Soham Daga, AI researcher at supermemory, for a deep dive into how machines actually remember you. what we get into: - why every AI forgets you - why forgetting is the hard part, not remembering - memory that understands time - going past reranking with aggregation - buckets for agent memory - SMFS, cutting tokens by 60% A conversation on the future of context, full episode below!

supermemory

20,600 views • 2 months 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

43,789 views • 2 months ago

the loop is not the whole agent it is only one layer of the system LOOP vs GRAPH vs HARNESS ENGINEERING LOOP ENGINEERING controls iteration turns retries budgets stop conditions success checks stalled progress use durable execution when the run must survive crashes → GRAPH ENGINEERING controls structure nodes edges state branches checkpoints routing handoffs build stateful agents as explicit graphs → inspect the topology without putting a model in the loop → HARNESS ENGINEERING controls exposure tools permissions memory sandboxes evals traces humans isolate generated code from the host machine → test behavior before users ever see it → preserve one trace across every model step and tool call → without loop control it keeps running without graph structure the path stays invisible without harness control it can reach anything the loop runs inside the graph the graph runs inside the harness the model is only one component debug the layer that actually owns the failure save this then read the article below

the loop is not the whole agent it is only one layer of the system LOOP vs GRAPH vs HARNESS ENGINEERING LOOP ENGINEERING controls iteration turns retries budgets stop conditions success checks stalled progress use durable execution when the run must survive crashes → GRAPH ENGINEERING controls structure nodes edges state branches checkpoints routing handoffs build stateful agents as explicit graphs → inspect the topology without putting a model in the loop → HARNESS ENGINEERING controls exposure tools permissions memory sandboxes evals traces humans isolate generated code from the host machine → test behavior before users ever see it → preserve one trace across every model step and tool call → without loop control it keeps running without graph structure the path stays invisible without harness control it can reach anything the loop runs inside the graph the graph runs inside the harness the model is only one component debug the layer that actually owns the failure save this then read the article below

rari

20,934 views • 3 months ago

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.

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

701,947 views • 5 months ago

Andrew Ng built agentic knowledge graph that runs agents loops from scratch: his agents searched thousands of tools through the graph, found the "right" one by meaning, and called it agent efficiency increased by 90% here's how: step 1 → embed every tool, search by meaning - not just keywords step 2 → but "similar" ≠ "correct" - it grabs the wrong one, skips the step before it step 3 → map tools as a graph - nodes are tools, edges are what runs before what step 4 → retrieve the path, not one tool - every tool the task needs, in order step 5 → bake the process into the graph - the sequence becomes data, not a guess most agents fail here and no one knows why - 1-hour brilliant course about it watch & bookmark - then read full course about graph engineering ↓

Andrew Ng built agentic knowledge graph that runs agents loops from scratch: his agents searched thousands of tools through the graph, found the "right" one by meaning, and called it agent efficiency increased by 90% here's how: step 1 → embed every tool, search by meaning - not just keywords step 2 → but "similar" ≠ "correct" - it grabs the wrong one, skips the step before it step 3 → map tools as a graph - nodes are tools, edges are what runs before what step 4 → retrieve the path, not one tool - every tool the task needs, in order step 5 → bake the process into the graph - the sequence becomes data, not a guess most agents fail here and no one knows why - 1-hour brilliant course about it watch & bookmark - then read full course about graph engineering ↓

codila

17,040 views • 3 months ago

I've updated the post for the fake liquid effect for BIRP and made a new post for the Shader Graph URP version :) Update has some fixes like no longer needing a pivot in the center and working with timescale 0 Links in reply with source code/graph! #gamedev #unity3d

I've updated the post for the fake liquid effect for BIRP and made a new post for the Shader Graph URP version :) Update has some fixes like no longer needing a pivot in the center and working with timescale 0 Links in reply with source code/graph! #gamedev #unity3d

Joyce(MinionsArt)

74,646 views • 3 years ago

Google just showed how AI engineers are moving from simple "RAG" to "graphs", memory and multimodal agents • 15:32 - setting up the production agent stack • 28:00 - turning disconnected data into a knowledge graph • 41:00 - Graph RAG with semantic + hybrid search • 58:00 - extracting graph context from images, text and video • 1:09:00 - orchestrating specialized agents with ADK • 1:20:00 - giving agents persistent memory across sessions 94-minute Google Cloud workshop, and it’s one of the clearest hands-on examples of the shift from -> RAG → Graph RAG → Memory → Multimodal Agent Graphs. The workshop uses Spanner Graph, Gemini, ADK and Memory Bank to build that stack. Watch it today, then read the full “From RAG to Context Graphs” roadmap below.

Google just showed how AI engineers are moving from simple "RAG" to "graphs", memory and multimodal agents • 15:32 - setting up the production agent stack • 28:00 - turning disconnected data into a knowledge graph • 41:00 - Graph RAG with semantic + hybrid search • 58:00 - extracting graph context from images, text and video • 1:09:00 - orchestrating specialized agents with ADK • 1:20:00 - giving agents persistent memory across sessions 94-minute Google Cloud workshop, and it’s one of the clearest hands-on examples of the shift from -> RAG → Graph RAG → Memory → Multimodal Agent Graphs. The workshop uses Spanner Graph, Gemini, ADK and Memory Bank to build that stack. Watch it today, then read the full “From RAG to Context Graphs” roadmap below.

Morlex

74,975 views • 2 months ago

Okay, ClaudeDevs mods are wild. Made one for Omnigraph and now I watch every query on the graph as Claude works. Plus a full graph browser right inside Claude Code

Okay, ClaudeDevs mods are wild. Made one for Omnigraph and now I watch every query on the graph as Claude works. Plus a full graph browser right inside Claude Code

Roman Pronskiy

19,045 views • 1 month ago

LOOP + GRAPH + CONTEXT ENGINEERING = THE KIMI K3 STACK THAT KEEPS RUNNING 300 Kimi K3 agents built one graph out of 100 companies. no 300 documents to read yourself kimi-swarm/ ├── swarm_launch.md task, sources, stop condition ├── CONSTRAINTS.md corrections from every past run ├── graph/ 384 entities, 1,064 typed edges, 8 closed verbs └── cron/ re-fires the swarm on schedule > one node sits at the center with 12 inbound edges - the vendor everyone depends on and nobody flagged in the prompt > 2 hops already answers most of what you'd actually ask it loop decides when it fires -> graph decides what's kept -> context decides what survives after the session closes how people are getting paid on this: > one build sold as a competitive teardown - replaces a four-figure analyst contract, done in an hour, unattended > the same graph on retainer - charge weekly for every new edge that shows up > wire the stack for someone else's market once it's proven on your own full version of this tree is in the article below

LOOP + GRAPH + CONTEXT ENGINEERING = THE KIMI K3 STACK THAT KEEPS RUNNING 300 Kimi K3 agents built one graph out of 100 companies. no 300 documents to read yourself kimi-swarm/ ├── swarm_launch.md task, sources, stop condition ├── CONSTRAINTS.md corrections from every past run ├── graph/ 384 entities, 1,064 typed edges, 8 closed verbs └── cron/ re-fires the swarm on schedule > one node sits at the center with 12 inbound edges - the vendor everyone depends on and nobody flagged in the prompt > 2 hops already answers most of what you'd actually ask it loop decides when it fires -> graph decides what's kept -> context decides what survives after the session closes how people are getting paid on this: > one build sold as a competitive teardown - replaces a four-figure analyst contract, done in an hour, unattended > the same graph on retainer - charge weekly for every new edge that shows up > wire the stack for someone else's market once it's proven on your own full version of this tree is in the article below

Mr. Buzzoni

15,462 views • 2 months ago

Have you checked out your Memory Graph in the Hermes Desktop? Team at Nous Research ships so much that even I miss some new features 😅 I think this has been out for a while, but the Memory Graph lets you see how your agent has developed, and how memories impacted skills. Check it out!

Have you checked out your Memory Graph in the Hermes Desktop? Team at Nous Research ships so much that even I miss some new features 😅 I think this has been out for a while, but the Memory Graph lets you see how your agent has developed, and how memories impacted skills. Check it out!

tonbi

136,038 views • 3 months ago

Introducing Entelligence AI Memory: One shared memory for every coding agent on your team - Sessions, PRs, tickets and incidents in one graph - Agents have full memory access for all new sessions - 53% fewer repeat errors Available today for Claude Code, Codex and Cursor

Introducing Entelligence AI Memory: One shared memory for every coding agent on your team - Sessions, PRs, tickets and incidents in one graph - Agents have full memory access for all new sessions - 53% fewer repeat errors Available today for Claude Code, Codex and Cursor

Aiswarya Sankar

47,728 views • 6 days ago