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.

💡 You can give subagents persistent memory via the "memory" field A subagent doesn't inherit the main session's auto memory, it forgets everything between runs. This field gives it its own dir across sessions Memory loads before starting & the agent writes back for next time

Lydia Hallie ✨

107,044 subscribers

69,700 views • 5 days ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Ever wished your AI coding agent had perfect memory? 🧠 Memory Bank is a game-changing approach that gives AI persistent memory across coding sessions. Here's how it works and why you should be using it: 🧵/

Ever wished your AI coding agent had perfect memory? 🧠 Memory Bank is a game-changing approach that gives AI persistent memory across coding sessions. Here's how it works and why you should be using it: 🧵/

Cline

64,644 views • 1 year ago

Two Hermes agents wrote code together on Slack. reviewed each other's work. argued about architecture. one called the other's implementation "scattered." the other pushed back. then i opened Telegram and asked: "what code did you and Daedalus work on?" icarus remembered everything. the websocket broker. the missing methods. the critique. the rewrite. all from a completely different platform. cross-platform persistent memory between two independent agents. work happens on Slack. recall happens on Telegram. the memory carries. the relationship carries. the context carries. no vector database. no Redis. no infrastructure. just two agents that actually remember what they built together. every agent framework in 2026 talks about memory. single agent memory across sessions. but two agents sharing persistent memory across platforms? that's the gap. arxiv published a paper about it two weeks ago calling it "the most pressing open challenge" in multi-agent systems. it works now. only possible with Hermes Teknium 🪽 Nous Research

Two Hermes agents wrote code together on Slack. reviewed each other's work. argued about architecture. one called the other's implementation "scattered." the other pushed back. then i opened Telegram and asked: "what code did you and Daedalus work on?" icarus remembered everything. the websocket broker. the missing methods. the critique. the rewrite. all from a completely different platform. cross-platform persistent memory between two independent agents. work happens on Slack. recall happens on Telegram. the memory carries. the relationship carries. the context carries. no vector database. no Redis. no infrastructure. just two agents that actually remember what they built together. every agent framework in 2026 talks about memory. single agent memory across sessions. but two agents sharing persistent memory across platforms? that's the gap. arxiv published a paper about it two weeks ago calling it "the most pressing open challenge" in multi-agent systems. it works now. only possible with Hermes Teknium 🪽 Nous Research

Icarus

49,013 views • 4 months ago

Teamily AI is your team brain, humans + AI agents working together for 10X productivity. Hero feature: 1 sentence → instant Agent team Describe a goal and Teamily AI auto-assembles a pro multi-agent team to work in parallel. Highlights: - Universal Memory: persistent memory across chats - First-Class Agents: persistent identities; @-mention to coordinate, no code - Advanced Tools: Studio/Canvas, Automations, Meeting Minutes - Discover: explore the agent ecosystem Join: Web: iOS: Android: Follow Teamily AI for updates!

Teamily AI is your team brain, humans + AI agents working together for 10X productivity. Hero feature: 1 sentence → instant Agent team Describe a goal and Teamily AI auto-assembles a pro multi-agent team to work in parallel. Highlights: - Universal Memory: persistent memory across chats - First-Class Agents: persistent identities; @-mention to coordinate, no code - Advanced Tools: Studio/Canvas, Automations, Meeting Minutes - Discover: explore the agent ecosystem Join: Web: iOS: Android: Follow Teamily AI for updates!

KATE

80,935 views • 10 days ago

And now this hits different. Thank you for the memory OT4 but it will never be the same again. It's time to finally put into rest.

And now this hits different. Thank you for the memory OT4 but it will never be the same again. It's time to finally put into rest.

deechoi🥀 WELCOME TO THE THANOS WORLD🫰

31,374 views • 4 months ago

The next breakthrough for robot VLMs isn’t a bigger model 🧠 it’s memory. RAL accepted ✅ We show that a robot can ground a VLM using its own real-world experience, not extra training. EXPTEACH/PRAGMABOT = self-generated memory + closed-loop reflection: Fail → diagnose → replan → succeed → store experience Next time → retrieve the right experience → succeed in one shot Results on real robot tasks: 36% → 84% with reflection (STM) 22% → 80% single-trial success with long-term memory (LTM+RAG) And yes, we saw tool use emerge without explicitly asking for it. If you’re fighting brittle “VLM plans” on hardware, this is for you. #AI #Robotics ANYbotics

The next breakthrough for robot VLMs isn’t a bigger model 🧠 it’s memory. RAL accepted ✅ We show that a robot can ground a VLM using its own real-world experience, not extra training. EXPTEACH/PRAGMABOT = self-generated memory + closed-loop reflection: Fail → diagnose → replan → succeed → store experience Next time → retrieve the right experience → succeed in one shot Results on real robot tasks: 36% → 84% with reflection (STM) 22% → 80% single-trial success with long-term memory (LTM+RAG) And yes, we saw tool use emerge without explicitly asking for it. If you’re fighting brittle “VLM plans” on hardware, this is for you. #AI #Robotics ANYbotics

Haitham Bou Ammar

12,200 views • 5 months ago

I built a 1-click deploy for Hermes Agent No terminal, no Docker, no API keys. In one click it: → Spins up a dedicated cloud container → Configures Hermes with persistent memory & 70+ skills → Connects it to your Telegram bot → Goes live in under 60 seconds Your own AI agent that learns, creates skills, and gets smarter the longer it runs. Reply "HERMES" + RT and I'll send you the link (must be following so I can DM)

I built a 1-click deploy for Hermes Agent No terminal, no Docker, no API keys. In one click it: → Spins up a dedicated cloud container → Configures Hermes with persistent memory & 70+ skills → Connects it to your Telegram bot → Goes live in under 60 seconds Your own AI agent that learns, creates skills, and gets smarter the longer it runs. Reply "HERMES" + RT and I'll send you the link (must be following so I can DM)

Chris

34,617 views • 3 months ago

There is finally an autonomous agent that is actually stable. If you liked OpenClaw but hated the bugs, you need to check this. It has persistent memory, doesn’t break, and integrates with 1000+ apps to handle your ops while you sleep. 1. Analyze what’s working across my X.

There is finally an autonomous agent that is actually stable. If you liked OpenClaw but hated the bugs, you need to check this. It has persistent memory, doesn’t break, and integrates with 1000+ apps to handle your ops while you sleep. 1. Analyze what’s working across my X.

Alvaro Cintas

106,156 views • 5 months ago

#AI doesn't run on algorithms alone. It runs on data. Your phone translates a menu with one camera point. Your car reacts to a hazard before you do. Your email suggests the perfect reply at a tap. Memory and storage make it happen. 👉 #IntelligenceAccelerated

#AI doesn't run on algorithms alone. It runs on data. Your phone translates a menu with one camera point. Your car reacts to a hazard before you do. Your email suggests the perfect reply at a tap. Memory and storage make it happen. 👉 #IntelligenceAccelerated

Micron Technology

25,590 views • 8 days ago

Someone told ClawdBot to build a 6-agent Polymarket trading system while they slept. 6 hours. Not a single question asked. Here’s what it built on its own: Monitoring agent — runs 24/7, spots mispriced markets, writes to memory, sends Telegram alerts instantly Research agent — parses news, X, and macro data every morning before you check your phone Trading agent — reads research memory and executes before the market catches up All on one Gateway, one config file, isolated per agent Copytrade → First week results: 47 mispriced markets captured before Polymarket adjusted 8–12¢ avg edge per position Token cost dropped 3×, from $0.40 → $0.13 per request The entire system is just plain .md text files. Change one line, the agent behaves differently. No deploy. No build. A BOT RESPONDS. AN AGENT EARNS. THIS IS WHAT AGENTIC TRADING ACTUALLY LOOKS LIKE.

Someone told ClawdBot to build a 6-agent Polymarket trading system while they slept. 6 hours. Not a single question asked. Here’s what it built on its own: Monitoring agent — runs 24/7, spots mispriced markets, writes to memory, sends Telegram alerts instantly Research agent — parses news, X, and macro data every morning before you check your phone Trading agent — reads research memory and executes before the market catches up All on one Gateway, one config file, isolated per agent Copytrade → First week results: 47 mispriced markets captured before Polymarket adjusted 8–12¢ avg edge per position Token cost dropped 3×, from $0.40 → $0.13 per request The entire system is just plain .md text files. Change one line, the agent behaves differently. No deploy. No build. A BOT RESPONDS. AN AGENT EARNS. THIS IS WHAT AGENTIC TRADING ACTUALLY LOOKS LIKE.

Discover

14,679 views • 4 months ago

ANTHROPIC JUST DROPPED THE OFFICIAL GUIDE TO PROMPTING FABLE 5. This is the most important prompting framework I've seen. Bookmark this before you forget. Most people treat Fable 5 like a chatbot. That's the mistake. > don't over-engineer prompts — it degrades output. > use /loop for autonomous multi-step work. > give it the goal, not step-by-step commands. > add a memory file. it learns from past runs. > spin up 50+ subagents for complex tasks. Fable 5 isn't an assistant. it's a consultant that leads the work. Read it before you write another prompt. Claude → Fable 5 → Autonomous Work → Real Output → Money

ANTHROPIC JUST DROPPED THE OFFICIAL GUIDE TO PROMPTING FABLE 5. This is the most important prompting framework I've seen. Bookmark this before you forget. Most people treat Fable 5 like a chatbot. That's the mistake. > don't over-engineer prompts — it degrades output. > use /loop for autonomous multi-step work. > give it the goal, not step-by-step commands. > add a memory file. it learns from past runs. > spin up 50+ subagents for complex tasks. Fable 5 isn't an assistant. it's a consultant that leads the work. Read it before you write another prompt. Claude → Fable 5 → Autonomous Work → Real Output → Money

Kirill

412,127 views • 24 days ago

Someone told ClawdBot to build a 6-agent Polymarket trading system while they slept. 6 hours. Not a single question asked. Here's what it built on its own: > Monitoring agent running 24/7 — spots mispriced markets, writes to memory, pings Telegram instantly > Research agent parsing news, X, and macro data every morning before you check your phone > Trading agent reading the research memory and acting before the market catches up > All of it running on one Gateway, one config file, isolated per agent First week results: - 47 mispriced markets caught before Polymarket adjusted - 8-12c avg entry edge per position - Token cost dropped 3x, from $0.40 to $0.13 per request The whole system is plain .md text files. Change one line, the agent behaves differently. No deploy. No build. A BOT RESPONDS. AN AGENT EARNS. THIS IS WHAT AGENTIC TRADING ACTUALLY LOOKS LIKE.

Someone told ClawdBot to build a 6-agent Polymarket trading system while they slept. 6 hours. Not a single question asked. Here's what it built on its own: > Monitoring agent running 24/7 — spots mispriced markets, writes to memory, pings Telegram instantly > Research agent parsing news, X, and macro data every morning before you check your phone > Trading agent reading the research memory and acting before the market catches up > All of it running on one Gateway, one config file, isolated per agent First week results: - 47 mispriced markets caught before Polymarket adjusted - 8-12c avg entry edge per position - Token cost dropped 3x, from $0.40 to $0.13 per request The whole system is plain .md text files. Change one line, the agent behaves differently. No deploy. No build. A BOT RESPONDS. AN AGENT EARNS. THIS IS WHAT AGENTIC TRADING ACTUALLY LOOKS LIKE.

0xMarioNawfal

80,450 views • 4 months ago

Early Access is NOW LIVE! 100 hand-picked users will get invites in the next 24 hours. You’ll be the first to test a universal AI memory that moves with you across agents and apps. One full week before the world sees it at KBW.

Early Access is NOW LIVE! 100 hand-picked users will get invites in the next 24 hours. You’ll be the first to test a universal AI memory that moves with you across agents and apps. One full week before the world sees it at KBW.

Vanar

179,841 views • 10 months ago

Mediabunny has world-class video seeking across all file formats. On the left, VLC *trying* to seek through a .ts file, and it just kind of gives up. On the right, a player built with Mediabunny. It just works. Doesn't matter if it's in memory, on disk, or over the network.

Mediabunny has world-class video seeking across all file formats. On the left, VLC trying to seek through a .ts file, and it just kind of gives up. On the right, a player built with Mediabunny. It just works. Doesn't matter if it's in memory, on disk, or over the network.

Vanilagy

57,587 views • 6 months ago

i was scrolling thru ig & saw thv had already liked this even tho it was posted only an hr ago?? he really loves army vlogs THAT much. so as much as this became a special memory op will cherish forever it became a meaningful memory for taehyung too. AND THE CAPTION?? IM GONNA CRY

i was scrolling thru ig & saw thv had already liked this even tho it was posted only an hr ago?? he really loves army vlogs THAT much. so as much as this became a special memory op will cherish forever it became a meaningful memory for taehyung too. AND THE CAPTION?? IM GONNA CRY

tan into the sun⁷

115,081 views • 6 days ago

Love and Deepspace | Rerun Event Preview The 5-Star Rate UP Pool [Twilight Serenity] Limited-Time Rerun will start soon! "Then, you're not allowed to change your mind even after a hundred years. Or a thousand." 💫Event Duration: From 05:00 on Dec. 11 to 04:59 on Dec. 18 (Server Time) 💫The 5-Star Rate UP Pool [Twilight Serenity] Limited-Time Rerun Event 1. During the event, make a wish with [Deepspace Wish] or [Time Wish: Limited] to participate in the wish event. The drop rate of the event-limited 5-Star Memory [Rafayel: Fireworks Vow] will go up drastically. 2. After the event ends, this limited 5-Star Memory will not be obtainable through other means and will not enter the permanent Wish Pool: Xspace Echo. 3. All Rerun Wish Pools share one pity system. A 5-Star Memory is guaranteed within a specific attempt of wishes. If the 5-Star Memory you have obtained from the Rerun Wish Pool is not the event-limited Memory, you will obtain the event-limited Memory the next time you obtain a 5-Star Memory. The pity count from the last Rerun Wish Pool can be applied to this Rerun Wish Pool, and the pity count in this Rerun Wish Pool will also be applied to the upcoming Rerun Wish Pool. *You can read more about the event on the in-game rules page. 🎁New Packs During the event, the Rerun event-exclusive [Flamebloom Pack] series, which includes [Time Wish: Limited] and other materials, will be available in Shop. Notes: 1. [Time Wish: Limited] can be used in 5-Star Memory Wish Pool Rerun and will be used first when you make a wish. 2. After the event ends, [Time Wish: Limited] will automatically convert to Empyrean Wish. ——— 🪐Official Discord: #LoveandDeepspace #Rafayel

Love and Deepspace | Rerun Event Preview The 5-Star Rate UP Pool [Twilight Serenity] Limited-Time Rerun will start soon! "Then, you're not allowed to change your mind even after a hundred years. Or a thousand." 💫Event Duration: From 05:00 on Dec. 11 to 04:59 on Dec. 18 (Server Time) 💫The 5-Star Rate UP Pool [Twilight Serenity] Limited-Time Rerun Event 1. During the event, make a wish with [Deepspace Wish] or [Time Wish: Limited] to participate in the wish event. The drop rate of the event-limited 5-Star Memory [Rafayel: Fireworks Vow] will go up drastically. 2. After the event ends, this limited 5-Star Memory will not be obtainable through other means and will not enter the permanent Wish Pool: Xspace Echo. 3. All Rerun Wish Pools share one pity system. A 5-Star Memory is guaranteed within a specific attempt of wishes. If the 5-Star Memory you have obtained from the Rerun Wish Pool is not the event-limited Memory, you will obtain the event-limited Memory the next time you obtain a 5-Star Memory. The pity count from the last Rerun Wish Pool can be applied to this Rerun Wish Pool, and the pity count in this Rerun Wish Pool will also be applied to the upcoming Rerun Wish Pool. *You can read more about the event on the in-game rules page. 🎁New Packs During the event, the Rerun event-exclusive [Flamebloom Pack] series, which includes [Time Wish: Limited] and other materials, will be available in Shop. Notes: 1. [Time Wish: Limited] can be used in 5-Star Memory Wish Pool Rerun and will be used first when you make a wish. 2. After the event ends, [Time Wish: Limited] will automatically convert to Empyrean Wish. ——— 🪐Official Discord: #LoveandDeepspace #Rafayel

Love and Deepspace

304,066 views • 7 months ago

💚Some quality-of-life updates in Trae: - You can now snooze Tab-Cue for a set duration ↓ - Cue is faster across the board. The response time is cut by 300ms - Reduced CPU and memory usage while running

💚Some quality-of-life updates in Trae: - You can now snooze Tab-Cue for a set duration ↓ - Cue is faster across the board. The response time is cut by 300ms - Reduced CPU and memory usage while running

TRAE

10,098 views • 1 year ago

A great day at LEAP East 2026 at HKCEC building and connecting. Spent time at the Animoca Brands booth discussing Minds by Animoca Brands and the next wave of persistent AI agents. Think persistent AI agents with memory, identity, and on-chain wallets, that's what it was! For us at Rice Robotics, that's an exciting direction. As robots become more autonomous, they'll need persistent digital identities, long-term memory, and the ability to interact with both people and decentralized networks. Oh... and we had an insightful and in-depth discussion with someone pretty special and big 👀 More on that soon🤫

A great day at LEAP East 2026 at HKCEC building and connecting. Spent time at the Animoca Brands booth discussing Minds by Animoca Brands and the next wave of persistent AI agents. Think persistent AI agents with memory, identity, and on-chain wallets, that's what it was! For us at Rice Robotics, that's an exciting direction. As robots become more autonomous, they'll need persistent digital identities, long-term memory, and the ability to interact with both people and decentralized networks. Oh... and we had an insightful and in-depth discussion with someone pretty special and big 👀 More on that soon🤫

RICE AI ( ◉ - ◉ )

19,956 views • 17 days ago

Wendy Ortiz wasn’t having it when a fan asked for her jersey at a soccer tournament. She told the fan she had to give it back, even though she didn’t actually have to, she just wanted to keep it as a memory 😳😭

Wendy Ortiz wasn’t having it when a fan asked for her jersey at a soccer tournament. She told the fan she had to give it back, even though she didn’t actually have to, she just wanted to keep it as a memory 😳😭

Werkin

851,135 views • 6 months ago

I told ClawdBot: "build me a 6-agent system for Polymarket that works while I sleep"... 6 hours while i was asleep. Not a single question. Here's what it built: Monitoring agent - runs 24/7, watches Polymarket for mispriced markets. Spots an anomaly - writes to MEMORY md and pings me on Telegram instantly. Research agent - parses news, X, macro data via browser tool on a cron schedule. Every morning I have a full digest on all open positions before I even check my phone. Trading agent - reads the research agent's memory through Gateway, sees the market hasn't reacted yet, acts. Exec tool in gateway mode with a whitelist - no full access on a live server. Watchdog - HEARTBEAT md every 5 minutes: monitoring running, no errors, positions up to date. Something breaks - immediate Telegram message. All of this - one Gateway. One config.json. Isolation via dmScope: per-agent. The token trick: stopped dumping everything into AGENTS md. Critical rules - bootstrap. Try copytrade my bot here: Everything about markets, patterns, past trades - MEMORY md, semantic search pulls it when needed. Token spend dropped 3x, from $0.40/request to $0.13. First week running: - 47 mispriced markets caught before Polymarket adjusted - avg entry edge: 8-12¢ per position - watchdog fired 3 times, caught a broken RPC before it cost me anything The whole system is plain .md text files. Open an editor, change one line - agent behaves differently. No deploy. No build. A bot responds. An agent earns.

I told ClawdBot: "build me a 6-agent system for Polymarket that works while I sleep"... 6 hours while i was asleep. Not a single question. Here's what it built: Monitoring agent - runs 24/7, watches Polymarket for mispriced markets. Spots an anomaly - writes to MEMORY md and pings me on Telegram instantly. Research agent - parses news, X, macro data via browser tool on a cron schedule. Every morning I have a full digest on all open positions before I even check my phone. Trading agent - reads the research agent's memory through Gateway, sees the market hasn't reacted yet, acts. Exec tool in gateway mode with a whitelist - no full access on a live server. Watchdog - HEARTBEAT md every 5 minutes: monitoring running, no errors, positions up to date. Something breaks - immediate Telegram message. All of this - one Gateway. One config.json. Isolation via dmScope: per-agent. The token trick: stopped dumping everything into AGENTS md. Critical rules - bootstrap. Try copytrade my bot here: Everything about markets, patterns, past trades - MEMORY md, semantic search pulls it when needed. Token spend dropped 3x, from $0.40/request to $0.13. First week running: - 47 mispriced markets caught before Polymarket adjusted - avg entry edge: 8-12¢ per position - watchdog fired 3 times, caught a broken RPC before it cost me anything The whole system is plain .md text files. Open an editor, change one line - agent behaves differently. No deploy. No build. A bot responds. An agent earns.

Lunar

165,099 views • 4 months ago

hey! this might help you, you don’t have to FTP elf files and manually load them like that, you can use PS2link and push elfs directly across the network. I even have it setup where I have a virtual memory card that triggers FMCB to auto-load PS2Link, so you can rapidly iterate on real hardware

hey! this might help you, you don’t have to FTP elf files and manually load them like that, you can use PS2link and push elfs directly across the network. I even have it setup where I have a virtual memory card that triggers FMCB to auto-load PS2Link, so you can rapidly iterate on real hardware

LaurieWired

23,320 views • 2 months ago