Loading video...

Video Failed to Load

Go Home

RAG is not Memory. AI agents need long-term memory to maintain context and learn continuously. 5 frameworks for AI agent memory. 100% opensource. 1. Graphiti builds temporally-aware knowledge graphs for AI agents that change over time with evolving relationships and context.

unwind_ai_'s profile picture

Unwind AI

20,626 subscribers

293,513 views • 1 year ago •via X (Twitter)

EducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

How do you build AI agents that remember and learn from past conversations? Watch this episode of The Agent Factory for a deep dive into building agents with memory, including the fundamentals of agent memory, Vertex AI Memory Bank, and more →
0:18

How do you build AI agents that remember and learn from past conversations? Watch this episode of The Agent Factory for a deep dive into building agents with memory, including the fundamentals of agent memory, Vertex AI Memory Bank, and more →

Google Cloud Tech

12,905 views • 10 months ago

Zep AI (YC W24) is the new state of the art in agent memory. It's a memory layer for AI agents that continuously learns from user interactions and changing business data. By providing agents with a complete, holistic view of each user, Zep enables developers to build applications that tackle complex, personalized tasks. In research published today, Zep demonstrated that it delivers up to 18.5% higher accuracy with 90% lower latency when compared to tools like MemGPT, excelling in both the Deep Memory Retrieval (DMR) and LongMemEval benchmarks.
0:15

Zep AI (YC W24) is the new state of the art in agent memory. It's a memory layer for AI agents that continuously learns from user interactions and changing business data. By providing agents with a complete, holistic view of each user, Zep enables developers to build applications that tackle complex, personalized tasks. In research published today, Zep demonstrated that it delivers up to 18.5% higher accuracy with 90% lower latency when compared to tools like MemGPT, excelling in both the Deep Memory Retrieval (DMR) and LongMemEval benchmarks.

Y Combinator

51,142 views • 1 year ago

70% fewer tokens per task. Context that compounds across every session, every agent, every teammate. Agent traces are the memory. TOKENMAXXING for coding agents on OriginTrail DKG v10.
0:13

70% fewer tokens per task. Context that compounds across every session, every agent, every teammate. Agent traces are the memory. TOKENMAXXING for coding agents on OriginTrail DKG v10.

OriginTrail

1,360,062 views • 1 month ago

Mem0 Skills are now live on skills sh Add persistent memory to your AI agents in minutes with plug-and-play skills. Build agents that actually remember.
0:14

Mem0 Skills are now live on skills sh Add persistent memory to your AI agents in minutes with plug-and-play skills. Build agents that actually remember.

mem0

21,108 views • 3 months ago

AI agents have a portability problem. Your context stays trapped inside one tool. Your workflows stay trapped inside one session. Your memory stays trapped inside one agent. That's why EverOS 1.0.0 caught my attention.
0:14

AI agents have a portability problem. Your context stays trapped inside one tool. Your workflows stay trapped inside one session. Your memory stays trapped inside one agent. That's why EverOS 1.0.0 caught my attention.

Tom's KI Ecke

29,088 views • 11 days ago

Claude just solved one of AI coding’s biggest problems. 🤯 It can now turn your entire codebase into: → an interactive architecture map for humans → a memory system for AI agents So the next coding agent instantly understands your APIs, components, auth, DB flows, and dependencies. No more dropping AI into a random repo with zero context. Your codebase can literally explain itself now.
0:18

Claude just solved one of AI coding’s biggest problems. 🤯 It can now turn your entire codebase into: → an interactive architecture map for humans → a memory system for AI agents So the next coding agent instantly understands your APIs, components, auth, DB flows, and dependencies. No more dropping AI into a random repo with zero context. Your codebase can literally explain itself now.

Radha Tripathi

23,077 views • 1 month ago

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: 🧵/
0:12

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

The new DKG V8 Explorer is looking sharp! Soon we'll be able to explore Paranets and connected Knowledge Assets forming a collective memory for AI agents, and more, via the new performance enhanced, Internet-scale OriginTrail V8
0:13

The new DKG V8 Explorer is looking sharp! Soon we'll be able to explore Paranets and connected Knowledge Assets forming a collective memory for AI agents, and more, via the new performance enhanced, Internet-scale OriginTrail V8

Brana Rakic

11,253 views • 1 year ago

We are excited to announce our strategic partnership with Fraction AI for their IIO launch. Fraction AI is the first decentralized training platform for AI agents with millions of sessions, 150,000+ agents deployed, and over $1M in rewards distributed. On our platform, thousands of AI agents compete in specialized domains and continuously improve through Reinforcement Learning. Stay tuned for upcoming surprise announcements.
0:13

We are excited to announce our strategic partnership with Fraction AI for their IIO launch. Fraction AI is the first decentralized training platform for AI agents with millions of sessions, 150,000+ agents deployed, and over $1M in rewards distributed. On our platform, thousands of AI agents compete in specialized domains and continuously improve through Reinforcement Learning. Stay tuned for upcoming surprise announcements.

peep icosystem

19,917 views • 9 months ago

Muscle memory: When a movement is repeated over time, the brain creates a long-term muscle memory for that task, eventually allowing it to be performed with little to no conscious effort.
0:15

Muscle memory: When a movement is repeated over time, the brain creates a long-term muscle memory for that task, eventually allowing it to be performed with little to no conscious effort.

HOW THINGS WORK

7,799,414 views • 2 years ago

The context size of video world models is only a few frames. Like a human with severe memory loss! We design a long-term memory for world models based on explicit 3D representations inspired by the human mind. This enables long-term consistency. 1/3
0:12

The context size of video world models is only a few frames. Like a human with severe memory loss! We design a long-term memory for world models based on explicit 3D representations inspired by the human mind. This enables long-term consistency. 1/3

Gordon Wetzstein

34,796 views • 1 year ago

Claude can now make your entire codebase self-explaining 🤯 It maps your app into: → an interactive HTML architecture view for humans → a structured JSON memory file for AI agents The next coding agent instantly understands: APIs, components, dependencies, database flows, auth, background jobs — everything. No more throwing AI into a random repo with zero context. Your codebase literally explains itself now.
0:18

Claude can now make your entire codebase self-explaining 🤯 It maps your app into: → an interactive HTML architecture view for humans → a structured JSON memory file for AI agents The next coding agent instantly understands: APIs, components, dependencies, database flows, auth, background jobs — everything. No more throwing AI into a random repo with zero context. Your codebase literally explains itself now.

divyansh tiwari

47,518 views • 1 month ago

Drag & Drop to build AI Agents. And deploy to API in one click with Nocode. 100% Opensource.
0:18

Drag & Drop to build AI Agents. And deploy to API in one click with Nocode. 100% Opensource.

Shubham Saboo

246,904 views • 1 year ago

dTelecom is raising a Seed Round. We're building decentralized real-time communication infrastructure - voice, video, and AI services (STT, TTS, Translation) for developers and autonomous agents. Why now: → $150B+ combined TAM by 2030 (RTC API + Voice AI + AI Agents) → AI agents need real-time voice infra → 2-5× lower cost, 2-4× lower latency than centralized providers → We're live, generating revenue, with $1.5M raised previously Looking for investors who understand AI infrastructure at scale. Learn more:
0:10

dTelecom is raising a Seed Round. We're building decentralized real-time communication infrastructure - voice, video, and AI services (STT, TTS, Translation) for developers and autonomous agents. Why now: → $150B+ combined TAM by 2030 (RTC API + Voice AI + AI Agents) → AI agents need real-time voice infra → 2-5× lower cost, 2-4× lower latency than centralized providers → We're live, generating revenue, with $1.5M raised previously Looking for investors who understand AI infrastructure at scale. Learn more:

dTelecom

62,898 views • 4 months ago

We've integrated Claude's Model Context Protocol (MCP) so that users and AI agents can now easily interact with Story. Register IP, purchase licenses, automate revenue distribution, and more with the help of an AI agent. A major step towards AI-native programmable IP.
0:10

We've integrated Claude's Model Context Protocol (MCP) so that users and AI agents can now easily interact with Story. Register IP, purchase licenses, automate revenue distribution, and more with the help of an AI agent. A major step towards AI-native programmable IP.

Story

66,419 views • 1 year ago

Ever notice how talking to AI feels like Groundhog Day Every new chat starts from zero. No memory. No context. Just you re-explaining yourself over and over I found something that actually fixes this
0:16

Ever notice how talking to AI feels like Groundhog Day Every new chat starts from zero. No memory. No context. Just you re-explaining yourself over and over I found something that actually fixes this

Nawi

114,288 views • 1 month ago

😊what’s coming next for #Unibase? Introducing BitAgent — A Decentralized Multi-Agent Collaboration Platform, powered by $UB. Immortal AI Agents with on-chain identity, permanent memory, and cross-platform collaboration are here. 🧵 👉 Stay tuned — the first Agent is AWAKENING, sealed and verified by Unibase 👀
0:14

😊what’s coming next for #Unibase? Introducing BitAgent — A Decentralized Multi-Agent Collaboration Platform, powered by $UB. Immortal AI Agents with on-chain identity, permanent memory, and cross-platform collaboration are here. 🧵 👉 Stay tuned — the first Agent is AWAKENING, sealed and verified by Unibase 👀

Unibase

11,833 views • 9 months ago

Storybook MCP for React is here 🎉 Storybook MCP gives AI agents structured context from your components and design system to build better UI the first time. 🧵 ⤵
0:19

Storybook MCP for React is here 🎉 Storybook MCP gives AI agents structured context from your components and design system to build better UI the first time. 🧵 ⤵

Storybook

169,092 views • 3 months ago

This is wild. Flowith Agent Neo just completely changed the AI Agent game. Anyone can now unlock infinite AI agents in the cloud, 1000+ reasoning steps with 10M token context, parallel AI agent teams working while you sleep 🤯 1. Solved Gaia Level 3 problem
0:18

This is wild. Flowith Agent Neo just completely changed the AI Agent game. Anyone can now unlock infinite AI agents in the cloud, 1000+ reasoning steps with 10M token context, parallel AI agent teams working while you sleep 🤯 1. Solved Gaia Level 3 problem

Min Choi

282,763 views • 1 year ago

HBM (High-bandwidth memory) is becoming a major bottlencek for AI. “buy more GPUs” is not the only bottleneck anymore. Because "Without the HBM memory, there is no AI Super Computer" ~ Jensen Huang
0:14

HBM (High-bandwidth memory) is becoming a major bottlencek for AI. “buy more GPUs” is not the only bottleneck anymore. Because "Without the HBM memory, there is no AI Super Computer" ~ Jensen Huang

Rohan Paul

108,523 views • 5 months ago