正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Introducing Long-term, multiplayer memory for your agents. #1 on BEAM, the largest public memory benchmark. Install it with a single prompt. Keep your stack. Add a past. Try it today →

Mehdi Djabri

2,012 subscribers

714,636 次观看 • 9 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

40 条评论

Paul Mit 的头像

Paul Mit9 天前

Long term memory is a new gold Congrats on the launch cool video btw

Chris Park 的头像

Chris Park9 天前

This is great

Mehdi Djabri 的头像

Mehdi Djabri9 天前

would love to chat Chris, we're helping some of the best agents in the world improve their long-term memory right now

Suryansh Tiwari 的头像

Suryansh Tiwari9 天前

launch videos are getting out of hand. this one made me want to flex my agent's memory at dinner

carpe 的头像

carpe9 天前

that’s cool man 👀

Aurélien Georget 的头像

Aurélien Georget9 天前

HUGE! Happy user 🙌🙌

Mehdi Djabri 的头像

Mehdi Djabri9 天前

we want to power the best agents in the world, and Fimo is one of them

KP 的头像

KP9 天前

“These idiots must be burning so many tokens” had to lol at that

Tisser Maxime 的头像

Tisser Maxime9 天前

Great video for a great product !

roman 的头像

roman9 天前

long term memory is just what i need. thank you man!

xIA 的头像

xIA9 天前

me interesa cómo resuelven que dos agentes se contradigan sobre lo mismo

Mehdi Djabri 的头像

Mehdi Djabri9 天前

That's one of the hardest things to do, read more here

Hasan Toor 的头像

Hasan Toor9 天前

The Acme budget example is the one that got me. Most agents would've confidently said 32k

Mehdi Djabri 的头像

Mehdi Djabri9 天前

yes, facts changing over time is one the hardest things to solve

Aaliya 的头像

Aaliya9 天前

hope 'past' is as good as the video is dope

Mehdi Djabri 的头像

Mehdi Djabri9 天前

it's even better

Aaliya 的头像

Aaliya9 天前

wow

Aman 🧋 的头像

Aman 🧋9 天前

great product

Ayan Barua 的头像

Ayan Barua9 天前

awesome! long term memory should be accurate and reliable

Mehdi Djabri 的头像

Mehdi Djabri9 天前

Ampersand + the perfect combo for world-class agents ❤️

shirish 的头像

shirish9 天前

did you guys buy the domain first or build the product

Mehdi Djabri 的头像

Mehdi Djabri9 天前

haha

Nav Toor9 天前

i think memory will matter more than bigger context windows

Mehdi Djabri 的头像

Mehdi Djabri9 天前

yes, the time has come for long horizon and persistent agents

Val ⟠ 的头像

Val ⟠9 天前

definitely worth checking out

Nikunj Yaduvanshi 的头像

Nikunj Yaduvanshi9 天前

Keeping it accurate as facts change is the hard part. If a March email says one thing and a June meeting says the opposite, does it keep both with dates or overwrite with the newer one?

Flix Muller 的头像

Flix Muller9 天前

Giving AI agents reliable long-term memory could be a huge step forward. The multiplayer aspect is especially interesting when multiple agents need to share context and work together.

Tj Dunham 的头像

Tj Dunham9 天前

cool marketing bro, I got 96% on well over 10m context window for complicated data sets let’s chat

Mehdi Djabri 的头像

Mehdi Djabri9 天前

would love to chat

AshutoshShrivastava 的头像

AshutoshShrivastava9 天前

does this sit on top of your existing stack or does the agent route everything through it

Mehdi Djabri 的头像

Mehdi Djabri9 天前

You can add it to your existing memory system, combine with md files, RAG, grep, db search. We want to give devs full flexibility to leverage this.

Jiayang Liu 的头像

Jiayang Liu9 天前

Had such a blast directing this launch video! Excited for the future of

Veyra | AI & Tech 的头像

Veyra | AI & Tech9 天前

Persistent multiplayer memory with one prompt install is huge

Aman 🧋 的头像

Aman 🧋9 天前

check dm

Rodev 的头像

Rodev9 天前

just wow. long term memory >>>>>>>>>

Aditi 的头像

Aditi9 天前

agents that actually remember context over time would be such a game changer

Mehdi Djabri 的头像

Mehdi Djabri9 天前

it is possible now, and it looks crazy when you try it in real life scenarios

Prajwal 的头像

Prajwal9 天前

Great video Just sent you DM

M@tt 的头像

M@tt9 天前

Nice. I see ingest, recall, and delete but no export. If I keep my raws I can always rebuild, but can I get the cooked claims and what they superseded back out?

Mehdi Djabri 的头像

Mehdi Djabri9 天前

yes, we are offering export, never want to lock anyone!

相关视频

introducing XERJ Corpus Hub, reference memory for AI agents. give your agent a corpus for your task. watch it become superintelligent. > finds the answers in indexed expert knowledge > applies them to your code, research, and projects > works with any model. free and OSS forever/Apache 2 install in one prompt: >Install XERJ (docs: index this project’s sources, docs, and logs, and connect as reference memory hub

introducing XERJ Corpus Hub, reference memory for AI agents. give your agent a corpus for your task. watch it become superintelligent. > finds the answers in indexed expert knowledge > applies them to your code, research, and projects > works with any model. free and OSS forever/Apache 2 install in one prompt: >Install XERJ (docs: index this project’s sources, docs, and logs, and connect as reference memory hub

Ivan Novikov

81,473 次观看 • 11 天前

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 次观看 • 6 个月前

New short course: Long-Term Agentic Memory with LangGraph. Learn to build an agent with long-term memory in this course developed in collaboration with taught by its Co-Founder and CEO, Harrison Chase! Personal assistance and productivity tasks have become important use cases for agents. An important feature of an AI assistant, such as a coding or calendar assistant, is its ability to keep improving over time from its experience. Agent memory is the key capability that enables this. To add memory to an agent, you must first figure out what to store and what to retrieve when it is time to use the information. Additionally, you’ll have to decide when to update the stored information. For example, you might update in each iteration loop of the agent or perform updates in the background, with a helper agent. In this course, you will learn a mental framework to build agents with long-term memory. You'll create a useful email assistant that can respond, ignore, and notify using writing, scheduling, and memory-management tools. You’ll develop your agent's memory by adding facts to its memory store, provide examples to learn the user's preferences, and optimize system prompts to evolve instructions based on previous responses. In detail, you’ll: - Learn how the three types of memory--semantic, episodic, and procedural–and the two update mechanisms–via hot path and in the background–apply to your agents. - Build an email agent with writing, scheduling, and availability tools, along with a router that triages incoming email and handles it accordingly by ignoring, responding, or notifying the user. - Add tools to your email agent that allow it to operate on semantic memory by learning facts about the user, storing them in a long-term memory store, and searching over them in future interactions. - Incorporate episodic memory, in the form of few-shot examples, in the triage step of your agents to help them learn and update user preferences. - Add procedural memory as system prompts, optimized with feedback to improve the instructions the agent follows. Learn how to approach memory in agents, and start building agents with long-term memory with LangGraph! Please sign up here:

New short course: Long-Term Agentic Memory with LangGraph. Learn to build an agent with long-term memory in this course developed in collaboration with taught by its Co-Founder and CEO, Harrison Chase! Personal assistance and productivity tasks have become important use cases for agents. An important feature of an AI assistant, such as a coding or calendar assistant, is its ability to keep improving over time from its experience. Agent memory is the key capability that enables this. To add memory to an agent, you must first figure out what to store and what to retrieve when it is time to use the information. Additionally, you’ll have to decide when to update the stored information. For example, you might update in each iteration loop of the agent or perform updates in the background, with a helper agent. In this course, you will learn a mental framework to build agents with long-term memory. You'll create a useful email assistant that can respond, ignore, and notify using writing, scheduling, and memory-management tools. You’ll develop your agent's memory by adding facts to its memory store, provide examples to learn the user's preferences, and optimize system prompts to evolve instructions based on previous responses. In detail, you’ll: - Learn how the three types of memory--semantic, episodic, and procedural–and the two update mechanisms–via hot path and in the background–apply to your agents. - Build an email agent with writing, scheduling, and availability tools, along with a router that triages incoming email and handles it accordingly by ignoring, responding, or notifying the user. - Add tools to your email agent that allow it to operate on semantic memory by learning facts about the user, storing them in a long-term memory store, and searching over them in future interactions. - Incorporate episodic memory, in the form of few-shot examples, in the triage step of your agents to help them learn and update user preferences. - Add procedural memory as system prompts, optimized with feedback to improve the instructions the agent follows. Learn how to approach memory in agents, and start building agents with long-term memory with LangGraph! Please sign up here:

Andrew Ng

132,225 次观看 • 1 年前

I built the best memory for voice agents while sponsoring Y Combinator hackathon. Introducing: Voice AI + Memory! We built a deep supermemory integration for Pipecat AI, so now even your agents have great memory With user profiles, these are almost-instant latency as well :)

I built the best memory for voice agents while sponsoring Y Combinator hackathon. Introducing: Voice AI + Memory! We built a deep supermemory integration for Pipecat AI, so now even your agents have great memory With user profiles, these are almost-instant latency as well :)

Dhravya Shah

83,511 次观看 • 7 个月前

MemOS now has a plugin for OpenClaw that enables your AI agents to work on the common memory layer and cut down token usage. - Multiple agents read/write the same memory — no manual context handoff - 72% lower token costs (15.6M → 4.4M on LOCOMO dataset) - Cross-session and long-term memory that actually works Sponsored

MemOS now has a plugin for OpenClaw that enables your AI agents to work on the common memory layer and cut down token usage. - Multiple agents read/write the same memory — no manual context handoff - 72% lower token costs (15.6M → 4.4M on LOCOMO dataset) - Cross-session and long-term memory that actually works Sponsored

🚨 AI News | TestingCatalog

41,040 次观看 • 8 个月前

I rebuilt most of OpenClaw's core in a single workflow: - 25 blocks - 29 connections - Short + long-term memory - Multi-channel (Telegram + Slack) Didn't build it manually. Stack is fully open-source. Self-host, run local models, own it end-to-end. Full walkthrough: Chapters: 00:00 - Intro 01:00 - SimClaw in action: planning my day, finding meetings, sending email 04:05 - Long-term memory capability 05:52 - Inside the workflow: how it's wired 12:09 - The plot twist 12:50 - Building an entire workflow using a single prompt 15:42 - Why this is an OS for your AI workforce 17:00 - Try it yourself If you want to see the open-source stack that powers all of this, check out Sim on GitHub and drop a star if you find it useful:

I rebuilt most of OpenClaw's core in a single workflow: - 25 blocks - 29 connections - Short + long-term memory - Multi-channel (Telegram + Slack) Didn't build it manually. Stack is fully open-source. Self-host, run local models, own it end-to-end. Full walkthrough: Chapters: 00:00 - Intro 01:00 - SimClaw in action: planning my day, finding meetings, sending email 04:05 - Long-term memory capability 05:52 - Inside the workflow: how it's wired 12:09 - The plot twist 12:50 - Building an entire workflow using a single prompt 15:42 - Why this is an OS for your AI workforce 17:00 - Try it yourself If you want to see the open-source stack that powers all of this, check out Sim on GitHub and drop a star if you find it useful:

Akshay 🚀

65,756 次观看 • 5 个月前

Introducing @opensea/cli — the OpenSea skill for your AI agents. Query NFTs, listings, swaps & more from your terminal. Or install it as a skill to power up your agents with deep onchain data from OpenSea. npm install -g @opensea/cli Your agents will thank you 🫡

Introducing @opensea/cli — the OpenSea skill for your AI agents. Query NFTs, listings, swaps & more from your terminal. Or install it as a skill to power up your agents with deep onchain data from OpenSea. npm install -g @opensea/cli Your agents will thank you 🫡

OpenSea

300,161 次观看 • 7 个月前

We just launched Twin 2 500,000+ tasks automated in our first month. Now: multi-agent automation. → Master agent that orchestrates all your agents → Workspaces where agents share context and collaborate → Persistent databases for long-term memory → See and edit your agent brain for maximum control → Runner mode: scale at 1/10th the cost → Auto-generated web apps to share your agents Try it out now!

We just launched Twin 2 500,000+ tasks automated in our first month. Now: multi-agent automation. → Master agent that orchestrates all your agents → Workspaces where agents share context and collaborate → Persistent databases for long-term memory → See and edit your agent brain for maximum control → Runner mode: scale at 1/10th the cost → Auto-generated web apps to share your agents Try it out now!

Hugo Mercier

11,226 次观看 • 7 个月前

Built a 3-layer Memory Stack that wires Claude Code directly into Obsidian with skills so it never forgets your project DNA, your notes, your standards, or your goals. Fixes most of Claude Code's memory issues.

Built a 3-layer Memory Stack that wires Claude Code directly into Obsidian with skills so it never forgets your project DNA, your notes, your standards, or your goals. Fixes most of Claude Code's memory issues.

WorldofAI

115,934 次观看 • 6 个月前

This is crazy!! Introducing: MemoryGPT 🤯 It’s ChatGPT but with long term memory. It will remember the things you say and will be able to personalize your conversation based on that. Currently polishing this and working on a better UI. Will open up to testing on Tuesday. Who wants to try this? 👇

This is crazy!! Introducing: MemoryGPT 🤯 It’s ChatGPT but with long term memory. It will remember the things you say and will be able to personalize your conversation based on that. Currently polishing this and working on a better UI. Will open up to testing on Tuesday. Who wants to try this? 👇

Rik 🦭

1,143,013 次观看 • 3 年前

holy sh*t. this is f**king insane. langchain just documented the missing memory layer for agents that are supposed to improve after every run. instead of stuffing everything into one giant prompt, deep agents can keep long-term memory, reusable skills and lessons from previous tasks. [it takes a few minutes to understand the loop] 1/ run the task 2/ save what actually worked 3/ load that lesson into the next run that’s how an agent stops starting from zero every single time.

holy sh*t. this is f**king insane. langchain just documented the missing memory layer for agents that are supposed to improve after every run. instead of stuffing everything into one giant prompt, deep agents can keep long-term memory, reusable skills and lessons from previous tasks. [it takes a few minutes to understand the loop] 1/ run the task 2/ save what actually worked 3/ load that lesson into the next run that’s how an agent stops starting from zero every single time.

Gipp 🦅

33,704 次观看 • 1 个月前

Memory Store (Memory Store) gives your team and AI agents a shared company brain. Your team's knowledge & decisions are scattered across slack, emails, and people's heads. Memory Store turns them into a living wiki for your agents and teammates. Congrats on the launch, Ishita Jindal & Diwank Singh Tomer!

Memory Store (Memory Store) gives your team and AI agents a shared company brain. Your team's knowledge & decisions are scattered across slack, emails, and people's heads. Memory Store turns them into a living wiki for your agents and teammates. Congrats on the launch, Ishita Jindal & Diwank Singh Tomer!

Y Combinator

246,981 次观看 • 5 个月前

Clude is now available as a custom connector on Anthropic Claude. Giving it persistent memory across every conversation. It remembers your projects, your preferences, and the decisions you make, so you never start from zero again. Use Clude across Chat / Co-Work and Claude Code. Add it in 30 seconds, no API key: 1. In Claude: Customize, Add custom connector URL: Enter your email. That's it. Recap for people unfamiliar: Clude deviates from the traditional vector database that many others bolt onto Claude. We are a cognitive memory system modeled on how human memory works. Think traditional memory systems: Calculator > It computes. Fullstop. Excel > Dynamic, formula run, able to share and manipulate Clude scored 86% on LongMemEval, one of the toughest long-term memory benchmarks. This means less hallucinations to traditional platforms. It scores memories by relevance, recency, and importance, links them into a knowledge graph, and consolidates them over time. Tell Claude something, open a new chat, and watch it remember.

Clude is now available as a custom connector on Anthropic Claude. Giving it persistent memory across every conversation. It remembers your projects, your preferences, and the decisions you make, so you never start from zero again. Use Clude across Chat / Co-Work and Claude Code. Add it in 30 seconds, no API key: 1. In Claude: Customize, Add custom connector URL: Enter your email. That's it. Recap for people unfamiliar: Clude deviates from the traditional vector database that many others bolt onto Claude. We are a cognitive memory system modeled on how human memory works. Think traditional memory systems: Calculator > It computes. Fullstop. Excel > Dynamic, formula run, able to share and manipulate Clude scored 86% on LongMemEval, one of the toughest long-term memory benchmarks. This means less hallucinations to traditional platforms. It scores memories by relevance, recency, and importance, links them into a knowledge graph, and consolidates them over time. Tell Claude something, open a new chat, and watch it remember.

seb

20,611 次观看 • 4 个月前

Introducing supermemory for Codex! give your codex better memory while having it interoperable between every other provider - OpenCode, Claude code, etc 1. Codex can see the timeline 2. It has your profile 3. Both explicit and implicit (dreaming) memory

Dhravya Shah

29,816 次观看 • 5 个月前

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

162,636 次观看 • 7 个月前

Introducing LangSmith Agent Builder 🤖🧱 A true agent building experience (not workflows!!), all through a simple natural language interface. Describe your agent to "build" it, then interact with it via chat, or add an automatic trigger. Connect your agents to any MCP server, or use our builtin tools. These agents also come with builtin memory, so they can optimize themselves over time, both ambiently, and from user feedback! Sign up for the waitlist today:

Introducing LangSmith Agent Builder 🤖🧱 A true agent building experience (not workflows!!), all through a simple natural language interface. Describe your agent to "build" it, then interact with it via chat, or add an automatic trigger. Connect your agents to any MCP server, or use our builtin tools. These agents also come with builtin memory, so they can optimize themselves over time, both ambiently, and from user feedback! Sign up for the waitlist today:

Brace

30,846 次观看 • 1 年前

SpaceXAI engineer Lauren (poteto) on why your codebase is a form of memory for agents. The architecture you choose and the constraints your tech stack imposes shape how well an agent reasons about the code, so good structure makes your agents smarter by default.

SpaceXAI engineer Lauren (poteto) on why your codebase is a form of memory for agents. The architecture you choose and the constraints your tech stack imposes shape how well an agent reasons about the code, so good structure makes your agents smarter by default.

tetsuo

25,747 次观看 • 1 个月前

We gave Pi Code persistent memory with Mem0 Launching the Mem0 plugin for Pi Code: persistent, scoped, semantic memory across sessions and projects. It captures what matters, searches by meaning, and brings the right context back when your agent needs it. Try it out: pi install npm:@ mem0/pi-agent-plugin

We gave Pi Code persistent memory with Mem0 Launching the Mem0 plugin for Pi Code: persistent, scoped, semantic memory across sessions and projects. It captures what matters, searches by meaning, and brings the right context back when your agent needs it. Try it out: pi install npm:@ mem0/pi-agent-plugin

mem0

25,165 次观看 • 4 个月前

Claude now have long-term memory similar to OpenAI ChatGPT. It can remember your conversations across chats. Claude Sonnet 3.5 becomes much more useful now with GPT-4o like memory feature.

Claude now have long-term memory similar to OpenAI ChatGPT. It can remember your conversations across chats. Claude Sonnet 3.5 becomes much more useful now with GPT-4o like memory feature.

Shubham Saboo

109,499 次观看 • 2 年前

All your Agents, shared Memory. Memory belongs to your work, not the agent.

All your Agents, shared Memory. Memory belongs to your work, not the agent.

Joe Fernandez

1,182,033 次观看 • 5 个月前