Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

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 →

2,894,692 Aufrufe • vor 24 Tagen •via X (Twitter)

40 Kommentare

Profilbild von Paul Mit
Paul Mitvor 24 Tagen

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

Profilbild von Chris Park
Chris Parkvor 24 Tagen

This is great

Profilbild von Mehdi Djabri
Mehdi Djabrivor 24 Tagen

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

Profilbild von Suryansh Tiwari
Suryansh Tiwarivor 24 Tagen

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

Profilbild von carpe
carpevor 24 Tagen

that’s cool man 👀

Profilbild von Aurélien Georget
Aurélien Georgetvor 24 Tagen

HUGE! Happy user 🙌🙌

Profilbild von Mehdi Djabri
Mehdi Djabrivor 24 Tagen

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

Profilbild von KP
KPvor 24 Tagen

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

Profilbild von Tisser Maxime
Tisser Maximevor 24 Tagen

Great video for a great product !

Profilbild von roman
romanvor 24 Tagen

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

Profilbild von xIA
xIAvor 24 Tagen

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

Profilbild von Mehdi Djabri
Mehdi Djabrivor 24 Tagen

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

Profilbild von Hasan Toor
Hasan Toorvor 24 Tagen

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

Profilbild von Mehdi Djabri
Mehdi Djabrivor 24 Tagen

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

Profilbild von Aaliya
Aaliyavor 24 Tagen

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

Profilbild von Mehdi Djabri
Mehdi Djabrivor 24 Tagen

it's even better

Profilbild von Aaliya
Aaliyavor 24 Tagen

wow

Profilbild von Aman 🧋
Aman 🧋vor 24 Tagen

great product

Profilbild von Ayan Barua
Ayan Baruavor 24 Tagen

awesome! long term memory should be accurate and reliable

Profilbild von Mehdi Djabri
Mehdi Djabrivor 24 Tagen

Ampersand + the perfect combo for world-class agents ❤️

Profilbild von shirish
shirishvor 24 Tagen

did you guys buy the domain first or build the product

Profilbild von Mehdi Djabri
Mehdi Djabrivor 24 Tagen

haha

Profilbild von Nav Toor
Nav Toorvor 24 Tagen

i think memory will matter more than bigger context windows

Profilbild von Mehdi Djabri
Mehdi Djabrivor 24 Tagen

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

Profilbild von Val ⟠
Val ⟠vor 24 Tagen

definitely worth checking out

Profilbild von Nikunj Yaduvanshi
Nikunj Yaduvanshivor 24 Tagen

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?

Profilbild von Flix Muller
Flix Mullervor 24 Tagen

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.

Profilbild von Tj Dunham
Tj Dunhamvor 24 Tagen

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

Profilbild von Mehdi Djabri
Mehdi Djabrivor 24 Tagen

would love to chat

Profilbild von AshutoshShrivastava
AshutoshShrivastavavor 24 Tagen

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

Profilbild von Mehdi Djabri
Mehdi Djabrivor 24 Tagen

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.

Profilbild von Jiayang Liu
Jiayang Liuvor 24 Tagen

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

Profilbild von Veyra | AI & Tech
Veyra | AI & Techvor 24 Tagen

Persistent multiplayer memory with one prompt install is huge

Profilbild von Aman 🧋
Aman 🧋vor 24 Tagen

check dm

Profilbild von Rodev
Rodevvor 24 Tagen

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

Profilbild von Aditi
Aditivor 24 Tagen

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

Profilbild von Mehdi Djabri
Mehdi Djabrivor 24 Tagen

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

Profilbild von Prajwal
Prajwalvor 24 Tagen

Great video Just sent you DM

Profilbild von M@tt
M@ttvor 24 Tagen

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?

Profilbild von Mehdi Djabri
Mehdi Djabrivor 24 Tagen

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

Ähnliche Videos

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

132,273 Aufrufe • vor 1 Jahr