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.

the perfect AI agent should remember everything. Sam Altman said it: "every conversation. every book. every email. your whole life appending to one context window." memory isn't a feature. it's the definition. I just built the memory layer. open source. install in one command. read the guide tonight. install... show more

Avid

11,997 subscribers

35,772 views • 2 months 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

Sam Altman says no human assistant can remember every word or every small preference AI will, including the tiny patterns you didn't even think to mention Memory is still crude today, but when it remembers your whole life and personalizes everything, that's when it gets powerful

Sam Altman says no human assistant can remember every word or every small preference AI will, including the tiny patterns you didn't even think to mention Memory is still crude today, but when it remembers your whole life and personalizes everything, that's when it gets powerful

Haider.

54,303 views • 6 months ago

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

80,494 views • 1 month ago

An agent's identity shifts with every context. Every prompt. Every data source. So who's actually accountable for what it does? The answer isn't in the agent. It's in the human behind it. Like a surname that carries the weight of everything done under it.

An agent's identity shifts with every context. Every prompt. Every data source. So who's actually accountable for what it does? The answer isn't in the agent. It's in the human behind it. Like a surname that carries the weight of everything done under it.

Billions

38,129 views • 4 months ago

Introducing mem0 CLI 🚀 Give your agents memory from the terminal - add, search, and retrieve memory - remember agents + developers's preference - agent-first, JSON schema-driven We built mem0 CLI to help agents remember Get started npm install -g @mem0/cli Open source 👇

Introducing mem0 CLI 🚀 Give your agents memory from the terminal - add, search, and retrieve memory - remember agents + developers's preference - agent-first, JSON schema-driven We built mem0 CLI to help agents remember Get started npm install -g @mem0/cli Open source 👇

Taranjeet

20,567 views • 3 months ago

📁 Sam Altman says the real AI breakthrough will not be better reasoning, but total memory. An AI will be able to remember every conversation, email, and document across a person’s lifetime, identifying patterns and preferences humans never consciously express. Once memory becomes persistent, the idea of a personal assistant will fundamentally change.

📁 Sam Altman says the real AI breakthrough will not be better reasoning, but total memory. An AI will be able to remember every conversation, email, and document across a person’s lifetime, identifying patterns and preferences humans never consciously express. Once memory becomes persistent, the idea of a personal assistant will fundamentally change.

Jon Hernandez

4,269,363 views • 6 months ago

Imagine a future where you can REMEMBER EVERYTHING. Every email, every person, every conversation. Introducing Engramme. Our vision is to endow humans with perfect and infinite memory. All your memories come to you. No more searching or prompting. 🧠

Imagine a future where you can REMEMBER EVERYTHING. Every email, every person, every conversation. Introducing Engramme. Our vision is to endow humans with perfect and infinite memory. All your memories come to you. No more searching or prompting. 🧠

Gabriel Kreiman

673,380 views • 2 months ago

Every AI agent I've used has the same bug: It forgets everything. Not after a month. Sometimes after a single session. This week I tested Memanto, an open-source memory companion for AI agents, and it completely changed how I think about agent workflows. 👇 Moorcheh.ai #ad

Every AI agent I've used has the same bug: It forgets everything. Not after a month. Sometimes after a single session. This week I tested Memanto, an open-source memory companion for AI agents, and it completely changed how I think about agent workflows. 👇 Moorcheh.ai #ad

Kaitee

37,566 views • 1 month ago

HERMES AGENT IS THE MOST POWERFUL OPEN SOURCE AI AGENT FRAMEWORK AVAILABLE RIGHT NOW — AND MOST PEOPLE HAVE NO IDEA HOW TO USE IT PROPERLY. This masterclass fixes that completely. From zero to a fully operational autonomous agent system in one sitting. Installation. Skills. Memory. MCP servers. Scheduler. Multi-agent operations. Every section builds on the previous one. The people who read this this weekend will have a production-ready autonomous agent operation running by Monday. Read this and bookmark it now.

HERMES AGENT IS THE MOST POWERFUL OPEN SOURCE AI AGENT FRAMEWORK AVAILABLE RIGHT NOW — AND MOST PEOPLE HAVE NO IDEA HOW TO USE IT PROPERLY. This masterclass fixes that completely. From zero to a fully operational autonomous agent system in one sitting. Installation. Skills. Memory. MCP servers. Scheduler. Multi-agent operations. Every section builds on the previous one. The people who read this this weekend will have a production-ready autonomous agent operation running by Monday. Read this and bookmark it now.

CyrilXBT

34,120 views • 1 month ago

🚨 SOMEONE JUST KILLED THE COACHING INDUSTRY a developer spent 22,000 hours building a Personal AI Operating System on top of Claude Code now anyone with a terminal can install it for FREE it knows your goals, remembers every decision you've made, and prepares your morning briefing while you sleep [ the numbers are insane ]: - hours of dev work in it: 22,000 - sessions logged: 6,000 - time saved per day: 2-3 hours - GitHub stars: 12,100 - skills built in: 45 - workflows wired up: 171 - safety hooks: 37 - cost to install: $0 [ the science is wild too ]: no embeddings, no vector databases, no AI magic you can't read every memory, decision, and context lives in plain markdown files you read it with cat, search it with ripgrep, version it with git 4 memory types compound over time: - work memory (active projects, open decisions) - knowledge memory (domain expertise, research) - people memory (contacts, companies, relationships) - learning memory (patterns, mistakes, what works for YOU) every complex task routes through a 7-step cycle: OBSERVE → THINK → PLAN → BUILD → EXECUTE → VERIFY → LEARN privacy is enforced by CODE, not prompts a hook called ContainmentGuard physically blocks sensitive data from being written outside designated zones [ the grift opportunity is even wilder ]: freelancers are already charging $500-2,000 per personal AI setup for executives, founders, and busy operators one person + one weekend = a consulting business that didn't exist 6 months ago every AI productivity app you're paying $30/month for is replaceable by 4 hours of setup work and this one repo REPO: 100% OPEN SOURCE, FREE

🚨 SOMEONE JUST KILLED THE COACHING INDUSTRY a developer spent 22,000 hours building a Personal AI Operating System on top of Claude Code now anyone with a terminal can install it for FREE it knows your goals, remembers every decision you've made, and prepares your morning briefing while you sleep [ the numbers are insane ]: - hours of dev work in it: 22,000 - sessions logged: 6,000 - time saved per day: 2-3 hours - GitHub stars: 12,100 - skills built in: 45 - workflows wired up: 171 - safety hooks: 37 - cost to install: $0 [ the science is wild too ]: no embeddings, no vector databases, no AI magic you can't read every memory, decision, and context lives in plain markdown files you read it with cat, search it with ripgrep, version it with git 4 memory types compound over time: - work memory (active projects, open decisions) - knowledge memory (domain expertise, research) - people memory (contacts, companies, relationships) - learning memory (patterns, mistakes, what works for YOU) every complex task routes through a 7-step cycle: OBSERVE → THINK → PLAN → BUILD → EXECUTE → VERIFY → LEARN privacy is enforced by CODE, not prompts a hook called ContainmentGuard physically blocks sensitive data from being written outside designated zones [ the grift opportunity is even wilder ]: freelancers are already charging $500-2,000 per personal AI setup for executives, founders, and busy operators one person + one weekend = a consulting business that didn't exist 6 months ago every AI productivity app you're paying $30/month for is replaceable by 4 hours of setup work and this one repo REPO: 100% OPEN SOURCE, FREE

Ronin

612,086 views • 1 month ago

Every glitch. Every memory. Every mistake. It all matters now. THE AMAZING DIGITAL CIRCUS: THE LAST ACT premieres in theatres nationwide TOMORROW!

Every glitch. Every memory. Every mistake. It all matters now. THE AMAZING DIGITAL CIRCUS: THE LAST ACT premieres in theatres nationwide TOMORROW!

Fathom Entertainment

36,697 views • 1 month ago

AI can write a 10,000-word essay in seconds… but forgets you just told it your name yesterday. Engramme is trying to fix that. Memory that sticks. Context that follows you. Across every app. This might be the missing layer AI needed.

AI can write a 10,000-word essay in seconds… but forgets you just told it your name yesterday. Engramme is trying to fix that. Memory that sticks. Context that follows you. Across every app. This might be the missing layer AI needed.

Sripathi Teja

27,799 views • 2 months ago

A LONDON-BASED AI ENGINEER WITH A KNOWLEDGE GRAPH THESIS FROM BIRMINGHAM JUST SHIPPED GRAPHIFY: ONE COMMAND TURNS ANY FOLDER INTO A CLAUDE CODE SECOND BRAIN. Safi Shamsi built it 48 hours after Karpathy posted his LLM wiki idea. It turns any folder, codebase, docs, PDFs, into a knowledge graph Claude reads instead of grepping. Up to 71.5x fewer tokens per query on the right corpus. The trick almost nobody is using yet: one flag exports the entire graph as a fully-linked Obsidian vault. Repo: safishamsi/graphify Setup, end to end: Install: uv tool install graphifyy (or pipx install graphifyy). Verify with graphify --version. Install the skill in Claude Code: graphify claude install. Wires Graphify in as a callable skill. Open the folder you want mapped. In the terminal: graphify . It extracts every concept and builds the graph in graphify-out/. Export to Obsidian: graphify . --obsidian. Writes one note per concept, every relationship as a wikilink, every node linked back to its source. Open the new vault in Obsidian, or drag it as a subfolder into your existing one. Your Claude Code instance now has a navigable map of the codebase that loads instantly instead of re-reading files every session. Full step-by-step build of the Claude + Obsidian second brain in the article below. Bookmark this.

A LONDON-BASED AI ENGINEER WITH A KNOWLEDGE GRAPH THESIS FROM BIRMINGHAM JUST SHIPPED GRAPHIFY: ONE COMMAND TURNS ANY FOLDER INTO A CLAUDE CODE SECOND BRAIN. Safi Shamsi built it 48 hours after Karpathy posted his LLM wiki idea. It turns any folder, codebase, docs, PDFs, into a knowledge graph Claude reads instead of grepping. Up to 71.5x fewer tokens per query on the right corpus. The trick almost nobody is using yet: one flag exports the entire graph as a fully-linked Obsidian vault. Repo: safishamsi/graphify Setup, end to end: Install: uv tool install graphifyy (or pipx install graphifyy). Verify with graphify --version. Install the skill in Claude Code: graphify claude install. Wires Graphify in as a callable skill. Open the folder you want mapped. In the terminal: graphify . It extracts every concept and builds the graph in graphify-out/. Export to Obsidian: graphify . --obsidian. Writes one note per concept, every relationship as a wikilink, every node linked back to its source. Open the new vault in Obsidian, or drag it as a subfolder into your existing one. Your Claude Code instance now has a navigable map of the codebase that loads instantly instead of re-reading files every session. Full step-by-step build of the Claude + Obsidian second brain in the article below. Bookmark this.

CyrilXBT

31,188 views • 15 days ago

Introducing: Walrus Memory. 🦭 A portable memory layer that lets your AI agents carry context across every app you run them in. No more starting from zero. No more being locked into one platform.…

Introducing: Walrus Memory. 🦭 A portable memory layer that lets your AI agents carry context across every app you run them in. No more starting from zero. No more being locked into one platform.…

Walrus 🦭/acc

39,575,428 views • 1 month ago

Connect Claude, ChatGPT, Cursor, Perplexity, or Codex to Caffeine. The Caffeine MCP server is live. One URL. One browser sign-in. Describe what you want built from inside your AI tool - it sends the prompt straight to Caffeine. Get updates on what's being built without leaving your conversation. When it's done, ask your AI to review it. It reads the Caffeine conversation directly, so it has full context on every decision.

Connect Claude, ChatGPT, Cursor, Perplexity, or Codex to Caffeine. The Caffeine MCP server is live. One URL. One browser sign-in. Describe what you want built from inside your AI tool - it sends the prompt straight to Caffeine. Get updates on what's being built without leaving your conversation. When it's done, ask your AI to review it. It reads the Caffeine conversation directly, so it has full context on every decision.

caffeine

14,238 views • 21 days ago

Sam Altman says AI isn't trained to be like one human. It's trained on the collective archive of all humanity. The good, the bad, every perspective we've ever recorded, encoded into a model.

Sam Altman says AI isn't trained to be like one human. It's trained on the collective archive of all humanity. The good, the bad, every perspective we've ever recorded, encoded into a model.

vitrupo

45,180 views • 9 months ago

okay Higgsfield Supercomputer is genuinely insane 🤯 it scans your competitors every Monday and drafts 3 ads before you open your laptop it's a cloud-native AI agent built for end-to-end creative production no local setup. runs in your browser or Telegram. here's what it actually does: → orchestrates every major model Claude Opus 4.7, GPT-5.5 Pro, Gemini 3.1 Pro, plus every image and video model → three layers of memory brief it once, it remembers context across every session → 40+ built-in tools with Skills you teach once and trigger with a slash command → scheduled tasks daily ad variations, weekly competitor scans, monthly content calendars → connects to Slack, Drive, Notion, Gmail, Figma and 30+ more powered by enhanced Hermes Agent Higgsfield was an AI video tool, this isn't a video tool anymore it's the whole studio.

okay Higgsfield Supercomputer is genuinely insane 🤯 it scans your competitors every Monday and drafts 3 ads before you open your laptop it's a cloud-native AI agent built for end-to-end creative production no local setup. runs in your browser or Telegram. here's what it actually does: → orchestrates every major model Claude Opus 4.7, GPT-5.5 Pro, Gemini 3.1 Pro, plus every image and video model → three layers of memory brief it once, it remembers context across every session → 40+ built-in tools with Skills you teach once and trigger with a slash command → scheduled tasks daily ad variations, weekly competitor scans, monthly content calendars → connects to Slack, Drive, Notion, Gmail, Figma and 30+ more powered by enhanced Hermes Agent Higgsfield was an AI video tool, this isn't a video tool anymore it's the whole studio.

Vaibhav Sisinty

17,975 views • 1 month ago

Introducing Ambient Context Aware AI on your computer. I have just scraped the whole Discord with it and made a summary of pain points ppl have Features: - Sees the whole screen ( even parts you need to scroll to) - long context window - Has memory Link:

Introducing Ambient Context Aware AI on your computer. I have just scraped the whole Discord with it and made a summary of pain points ppl have Features: - Sees the whole screen ( even parts you need to scroll to) - long context window - Has memory Link:

Robert Lukoszko

15,383 views • 1 year ago

A 26-YEAR-OLD AI ENGINEER WHOSE BIRMINGHAM THESIS OUTPERFORMED GOOGLE SCHOLAR BY 50% JUST SHIPPED GRAPHIFY: ONE COMMAND TURNS ANY FOLDER INTO A CLAUDE CODE SECOND BRAIN Safi Shamsi built Graphify 48 hours after Karpathy posted his LLM wiki idea. It turns any folder, codebase, docs, PDFs, into a knowledge graph Claude reads instead of grepping. Up to 43x fewer tokens per query. The trick almost nobody is using yet: one flag exports the entire graph as a fully-linked Obsidian vault. Repo: /safishamsi/graphify Setup, end to end: 1. Install: uv tool install graphifyy (or pipx install graphifyy). Verify with graphify --version. 2. Install the skill in Claude Code: graphify claude install. This wires Graphify into Claude Code so you can call it as a skill. 3. Open the folder you want mapped in Claude Code. In the terminal: graphify . It extracts every concept and builds the graph in graphify-out/. 4. Export to Obsidian: graphify . --obsidian. Writes one note per concept, every relationship as a wikilink, every node linked back to its source. 5. Open the new vault in Obsidian (Manage vaults → Open folder as a vault), or drag it as a subfolder into your existing one. That's it. Your Claude Code instance now has a navigable map of the codebase that loads instantly instead of re-reading files every session. Full step-by-step build of the Claude + Obsidian second brain in the article below. Bookmark this

A 26-YEAR-OLD AI ENGINEER WHOSE BIRMINGHAM THESIS OUTPERFORMED GOOGLE SCHOLAR BY 50% JUST SHIPPED GRAPHIFY: ONE COMMAND TURNS ANY FOLDER INTO A CLAUDE CODE SECOND BRAIN Safi Shamsi built Graphify 48 hours after Karpathy posted his LLM wiki idea. It turns any folder, codebase, docs, PDFs, into a knowledge graph Claude reads instead of grepping. Up to 43x fewer tokens per query. The trick almost nobody is using yet: one flag exports the entire graph as a fully-linked Obsidian vault. Repo: /safishamsi/graphify Setup, end to end: 1. Install: uv tool install graphifyy (or pipx install graphifyy). Verify with graphify --version. 2. Install the skill in Claude Code: graphify claude install. This wires Graphify into Claude Code so you can call it as a skill. 3. Open the folder you want mapped in Claude Code. In the terminal: graphify . It extracts every concept and builds the graph in graphify-out/. 4. Export to Obsidian: graphify . --obsidian. Writes one note per concept, every relationship as a wikilink, every node linked back to its source. 5. Open the new vault in Obsidian (Manage vaults → Open folder as a vault), or drag it as a subfolder into your existing one. That's it. Your Claude Code instance now has a navigable map of the codebase that loads instantly instead of re-reading files every session. Full step-by-step build of the Claude + Obsidian second brain in the article below. Bookmark this

Yarchi

138,564 views • 16 days ago

Introducing Membase – portable and persistent memory for your agents. Keep all your context in one place and simply plug it into any agent. We just opened private beta access. Get Membase and make every AI understand you. *Also available in .

Introducing Membase – portable and persistent memory for your agents. Keep all your context in one place and simply plug it into any agent. We just opened private beta access. Get Membase and make every AI understand you. *Also available in .

Joshua Park

18,238 views • 5 months ago

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!

Andrew Ng

200,752 views • 1 year ago