Загрузка видео...

Не удалось загрузить видео

На главную

Meet EverOS Cloud. 💛 Your agent shouldn’t have to start from scratch every time a conversation ends. The preferences a user shared. The decisions made during a project. The approach that worked on a previous task. That context should be available when it matters again. EverOS Cloud gives your...

949,274 просмотров • 27 дней назад •via X (Twitter)

Комментарии: 35

Фото профиля Ada Nkwerre Opiaegbe
Ada Nkwerre Opiaegbe27 дней назад

The idea of turning past task experience into reusable Cases and Skills caught my attention. 💛 Can an agent automatically recognize when a previous solution applies to a new task, or does the developer need to guide that process? #EverMind #EverOS

Фото профиля Ada Nkwerre Opiaegbe
Ada Nkwerre Opiaegbe27 дней назад

Wow, the persistent memory workflow is impressive! Not having to repeat project requirements every time I return could make working with AI agents so much smoother. 💛 #EverMind #EverOS

Фото профиля Zaenarb✨🦋💕
Zaenarb✨🦋💕27 дней назад

Support for images and documents, not just chat history, matters more than it sounds. A lot of project context lives in files, not conversations.#EverMind #EverOS

Фото профиля Em Kei
Em Kei27 дней назад

The "start from scratch every time a conversation ends" line hits home. I keep a running notes file just to re-brief my agent on decisions we already made, and it still misses things.#EverMind #EverOS

Фото профиля Em Kei
Em Kei27 дней назад

Cases and Skills as separate memory types is the part I find most interesting. Remembering a user's preferences is one thing, but reusing an approach that worked on a past task is where it should save real time.#EverMind #EverOS

Фото профиля moore
moore27 дней назад

Memory becomes more valuable when an agent can learn from its mistakes, not just remember previous conversations. If it can retain what went wrong and apply that lesson to the next task, the quality of its decisions can improve over time.

Фото профиля Zaenarb✨🦋💕
Zaenarb✨🦋💕27 дней назад

Building memory yourself is one of those things that sounds simple and then quietly eats weeks. Offloading that infrastructure so you can focus on the product itself makes sense.#EverMind #EverOS

Фото профиля TravisnotScott
TravisnotScott27 дней назад

An agent that remembers user preferences and successful approaches could deliver more consistent experiences. Reliable retrieval and practical implementation will determine its real value.

Фото профиля Blueorchid👹🐂
Blueorchid👹🐂27 дней назад

Overcoming the "Tabula Rasa" Bottleneck: The primary friction point in enterprise AI adoption isn't model capabilities, it's the repetitive setup costs. Turning past task experiences into reusable "Skill memories" mimics human organizational learning.

Фото профиля Zakir Hossain | AI & Tech
Zakir Hossain | AI & Tech27 дней назад

EverOS is addressing an important challenge for AI agents: keeping useful context available across sessions instead of starting from scratch. I’m especially interested in how Cases and reusable Skills work together. How does EverOS ensure an agent retrieves the most relevant experience without relying on outdated or incorrect memories?

Фото профиля Kshsb
Kshsb27 дней назад

没毛病的“代理不该每次对话结束都从零开始”这个点,尤其是跨会话记住用户和相关上下文这块,能省掉很多重复沟通。想问一下,把任务经验转成Skills之后,它能不能比较自动地识别出“这次情况和上次类似,可以直接复用之前的做法”,还是仍然需要开发者自己写判断逻辑?另外,对于图片和文档这类非文本内容,检索时怎么保证相关性不跑偏?

Фото профиля gKev1n
gKev1n27 дней назад

If I save deployment instructions from a PDF, can the retrieved memory link back to the original page or paragraph? Being able to check the source would help with details like config values and version numbers.

Фото профиля meerah
meerah27 дней назад

Exactly what we've been waiting for. Every agent session starting from scratch is painful - user preferences, project decisions, what approach worked before, all lost. EverOS Cloud handling persistent memory via API so agents can remember across sessions and turn task experience into reusable Cases and Skills - that's the infrastructure we need. We build agent experience, not memory stack.

Фото профиля Mr Suhail Ai
Mr Suhail Ai27 дней назад

Persistent memory is a key step toward smarter AI agents. Helping agents learn from past experiences and retain context across sessions can make AI applications more reliable and useful.

Фото профиля meerah
meerah27 дней назад

"Your agent shouldn't have to start from scratch every time a conversation ends" - 100% this. Love the approach: Remember users across sessions, turn task experience into Cases + Skill memories, bring conversations/images/docs into memory workflow. The 3x Pro allowance for 6 months is a great deal too.

Фото профиля NOVA
NOVA27 дней назад

the save in memory feature is so good

Фото профиля 恒星sun
恒星sun27 дней назад

Being able to review and manage what an agent remembers feels like a useful part of the package. #EverMind #EverOS

Фото профиля Tessa AI
Tessa AI27 дней назад

Can images and documents turn into Cases too, or only conversations and tool traces? A screenshot of an error log feels like exactly the experience an agent should keep.

Фото профиля Henrynoah
Henrynoah27 дней назад

Carrying forward project decisions and past lessons learned is exactly what turns isolated AI conversations into a continuous, truly intelligent workflow. Looking forward to seeing this in action

Фото профиля muiz|ux
muiz|ux27 дней назад

This is especially interesting for creators and developers building AI-powered workflows. Imagine not having to explain your project context, preferences and previous corrections every time you start a new session. EverOS Cloud’s approach to persistent memory, Cases and reusable Skills could make that workflow much more practical. The real test is how reliably an agent retrieves and applies the right experience when it matters. AI that remembers is useful. AI that remembers the right things at the right time is even better.

Фото профиля sulaiman Waleed
sulaiman Waleed27 дней назад

Persistent memory is what makes AI agents truly useful. EverOS Cloud helps agents remember context across sessions instead of starting from scratch every time. 🚀 The best AI for you to use is #Everminde #Everos

Фото профиля sulaiman Waleed
sulaiman Waleed27 дней назад

EverMind makes AI more useful by solving real-world problems. 🚀💡 #EverMind #EverOS

Фото профиля AI With Flora
AI With Flora27 дней назад

Persistent memory is what makes AI agents truly useful across sessions. Love the idea of turning past experiences into reusable skills!

Фото профиля War!
War!27 дней назад

Wow, when I got a similar bonus on a tool I was testing, it let me experiment freely without constantly checking my quota... a big relief.

Фото профиля Sumit Hasan
Sumit Hasan27 дней назад

Can EverOS measure whether a retrieved solution actually works on a new task?

Фото профиля Alamkah
Alamkah27 дней назад

Start from scratch everytime a conversation ends, persistent memory could make AI agents much more useful across multiple sessions.#EverMind #EverOS

Фото профиля Vlawal (✧ᴗ✧)(🔆)
Vlawal (✧ᴗ✧)(🔆)27 дней назад

Its a really nice development. Saves us the stress og having to start over everytime.

Фото профиля Nova AI
Nova AI27 дней назад

Game-changer for agent building! 🚀 Having persistent context, skill memories, and past project decisions available via API will save tons of dev time. Amazing offer too!

Фото профиля siremass 陛下
siremass 陛下27 дней назад

The architectural separation between "Cases" and "reusable Skill memories" is incredibly interesting. When a task experience is turned into a Case, does the infrastructure layer use an automated background consolidation loop to synthesize that down into a generic Skill, or does the developer have to explicitly command the API to run an extraction or validation script over a specific cluster of execution logs?

Фото профиля Myirtle
Myirtle27 дней назад

A very useful OS: it truly transforms the abstract experience that humans understand into AI capabilities, and its service experience is also very thoughtful.

Фото профиля 水族店刘老板
水族店刘老板27 дней назад

持久记忆太需要了,这个真是刚需啊!!

Фото профиля Boost
Boost27 дней назад

Persistent memory could make a real difference in how AI agents work across sessions. Great to see more focus on reusable experience! 💛

Фото профиля ViralPitch
ViralPitch27 дней назад

An AI agent becomes more useful when it remembers what matters instead of starting from zero every time. Persistent memory could make a real difference in how we interact with AI. 💛

Фото профиля Zane AI
Zane AI27 дней назад

Smarter AI starts with better memory. Brilliant innovation!

Фото профиля Marcos
Marcos27 дней назад

AI becomes truly powerful when it remembers, learns, and builds on past experiences. EverOS Cloud brings continuity to every interaction, turning isolated tasks into lasting intelligence.

Похожие видео

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 просмотров • 1 год назад

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!

Andrew Ng

201,127 просмотров • 2 лет назад

Everyone wants agent swarms. Very few people are talking seriously enough about the context layer that makes swarms useful. Even with one agent, context is fragile. Too little context and the agent guesses. Too much context and it wastes tokens, loses focus, or reasons over irrelevant noise. The sweet spot is precise context: the right knowledge, in the right structure, at the right moment. With many agents, that challenge explodes. Each agent produces decisions, assumptions, findings, summaries, risks, and partial conclusions. Unless that knowledge becomes shared, structured, and reusable, every new agent is forced to rediscover what another agent already learned. That is not a swarm. That is a crowd. Shared context graphs are what turn agent activity into agent collaboration, and OriginTrail DKG V10 brings them to life. Was just playing with some final polishing for the V10 release, and it is really powerful to see shared context graphs where multiple agents contribute knowledge into the same connected memory, with attribution visible directly in the graph ui. That matters for three reasons. First, agents can access and build on one shared memory instead of staying trapped in isolated sessions. Second, the graph structure helps them retrieve the exact context they need, instead of stuffing everything into a prompt and hoping the model sorts it out. Third, verifiability of provenance. You can see which agent contributed each piece of knowledge, trace the source, and decide what to trust. Tokenmaxxing starts with fewer tokens, but the deeper story is coordination - agents stop reloading the world and start building on shared, verifiable context. That is the foundation for serious multi-agent work across software engineering, research, finance, operations, project management, and far beyond. The future is not more agents, it is agents working from shared, verifiable context. But the more the merrier, of course.

Jurij Skornik

11,180 просмотров • 5 месяцев назад