Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

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 →

3,010,859 görüntüleme • 1 ay önce •via X (Twitter)

40 Yorum

Paul Mit profil fotoğrafı
Paul Mit1 ay önce

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

Chris Park profil fotoğrafı
Chris Park1 ay önce

This is great

Mehdi Djabri profil fotoğrafı
Mehdi Djabri1 ay önce

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 profil fotoğrafı
Suryansh Tiwari1 ay önce

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

carpe profil fotoğrafı
carpe1 ay önce

that’s cool man 👀

Aurélien Georget profil fotoğrafı
Aurélien Georget1 ay önce

HUGE! Happy user 🙌🙌

Mehdi Djabri profil fotoğrafı
Mehdi Djabri1 ay önce

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

KP profil fotoğrafı
KP1 ay önce

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

Tisser Maxime profil fotoğrafı
Tisser Maxime1 ay önce

Great video for a great product !

roman profil fotoğrafı
roman1 ay önce

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

xIA profil fotoğrafı
xIA1 ay önce

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

Mehdi Djabri profil fotoğrafı
Mehdi Djabri1 ay önce

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

Hasan Toor profil fotoğrafı
Hasan Toor1 ay önce

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

Mehdi Djabri profil fotoğrafı
Mehdi Djabri1 ay önce

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

Aaliya profil fotoğrafı
Aaliya1 ay önce

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

Mehdi Djabri profil fotoğrafı
Mehdi Djabri1 ay önce

it's even better

Aaliya profil fotoğrafı
Aaliya1 ay önce

wow

Aman 🧋 profil fotoğrafı
Aman 🧋1 ay önce

great product

Ayan Barua profil fotoğrafı
Ayan Barua1 ay önce

awesome! long term memory should be accurate and reliable

Mehdi Djabri profil fotoğrafı
Mehdi Djabri1 ay önce

Ampersand + the perfect combo for world-class agents ❤️

shirish profil fotoğrafı
shirish1 ay önce

did you guys buy the domain first or build the product

Mehdi Djabri profil fotoğrafı
Mehdi Djabri1 ay önce

haha

Nav Toor profil fotoğrafı
Nav Toor1 ay önce

i think memory will matter more than bigger context windows

Mehdi Djabri profil fotoğrafı
Mehdi Djabri1 ay önce

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

Val ⟠ profil fotoğrafı
Val ⟠1 ay önce

definitely worth checking out

Nikunj Yaduvanshi profil fotoğrafı
Nikunj Yaduvanshi1 ay önce

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 profil fotoğrafı
Flix Muller1 ay önce

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 profil fotoğrafı
Tj Dunham1 ay önce

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

Mehdi Djabri profil fotoğrafı
Mehdi Djabri1 ay önce

would love to chat

AshutoshShrivastava profil fotoğrafı
AshutoshShrivastava1 ay önce

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

Mehdi Djabri profil fotoğrafı
Mehdi Djabri1 ay önce

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 profil fotoğrafı
Jiayang Liu1 ay önce

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

Veyra | AI & Tech profil fotoğrafı
Veyra | AI & Tech1 ay önce

Persistent multiplayer memory with one prompt install is huge

Aman 🧋 profil fotoğrafı
Aman 🧋1 ay önce

check dm

Rodev profil fotoğrafı
Rodev1 ay önce

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

Aditi profil fotoğrafı
Aditi1 ay önce

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

Mehdi Djabri profil fotoğrafı
Mehdi Djabri1 ay önce

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

Prajwal profil fotoğrafı
Prajwal1 ay önce

Great video Just sent you DM

M@tt profil fotoğrafı
M@tt1 ay önce

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 profil fotoğrafı
Mehdi Djabri1 ay önce

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

Benzer Videolar

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

132,349 görüntüleme • 1 yıl önce