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。

AI agents shouldn’t have to start from scratch every time they handle a task. They need a way to learn from past experience. 🧠 That’s what makes EverOS Cloud interesting. It helps AI agents save task experiences as Cases, turn recurring knowledge into reusable Skills, and retrieve relevant context... show more

Jessica

9,937 subscribers

334,349 次观看 • 13 天前 •via X (Twitter)

教育科学技术

Anya Rossi• Live Now

Private livecam show

38 条评论

Henrynoah 的头像

Henrynoah13 天前

Expecting agents to perform complex workflows without persistent memory is like hiring a team that loses its memory every single morning. Turning real-world execution cases into reusable skills via EverOS Cloud is the exact architectural shift needed for true agentic autonomy.

Zaenarb✨🦋💕 的头像

Zaenarb✨🦋💕13 天前

Splitting memory into Cases that can grow into Skills is a tidy structure. Past work stops being a log and becomes something an agent can reuse. #EverMind #EverOS

Jessica 的头像

Jessica13 天前

Right

Em Kei 的头像

Em Kei13 天前

"Learn from past experience" is the right framing. It's less about a smarter model and more about one that doesn't lose its own history 🧠 #EverMind #EverOS

Em Kei 的头像

Em Kei13 天前

Clear and to the point. Retrieval of relevant context when similar tasks return is exactly what makes repeat work faster. Thanks for the rundown! #EverMind #EverOS

Ada Nkwerre Opiaegbe 的头像

Ada Nkwerre Opiaegbe13 天前

Turning past task experiences into reusable Skills could save teams from solving the same problems repeatedly. 💡 Can EverOS automatically recognize when an existing Skill applies to a new task? #EverMind #EverOS

Zaenarb✨🦋💕 的头像

Zaenarb✨🦋💕13 天前

Hooking in PDFs and spreadsheets is the part I'd use first. Most teams already have the knowledge written down, just not somewhere an agent can search it. #EverMind #EverOS

Kelvin Joseph okon 的头像

Kelvin Joseph okon13 天前

Connect docs/PDFs to searchable memory is smart. Let agents use team knowledge already built.

Kelvin Joseph okon 的头像

Kelvin Joseph okon13 天前

So true, agents shouldn't start from scratch. Saving tasks as Cases and turning them into reusable Skills is exactly what's missing.

油条的头像

油条13 天前

Turning PDFs and spreadsheets into searchable memory is really useful, especially for teams that need quick access to shared knowledge.

HAO · 无好即好的头像

HAO · 无好即好13 天前

A more powerful model can solve harder problems. An agent with memory can stop repeating the same mistakes. The interesting part is when AI starts building on what it has already learned, instead of starting from zero every time.

Segun Bxx 的头像

Segun Bxx13 天前

The abstraction between raw task Cases and auto-distilled Skills is a great architectural detail. How many similar Case trajectories does EverOS usually need to log before it automatically promotes a pattern into a reusable Skill, and can developers manually trigger or review that promotion step?

Lia AI 的头像

Lia AI13 天前

Persistent memory helps AI agents learn from experience and deliver better results! 🚀

Sienna 的头像

Sienna13 天前

Can teams set rules for which memories an agent should prioritize?

Jessica 的头像

Jessica13 天前

Yes can

Peter 的头像

Peter13 天前

Can it handle large business documents?

Evan Cole 的头像

Evan Cole13 天前

Can an agent distinguish a verified fix from an untested suggestion?

Richie.L 的头像

Richie.L13 天前

Pairing team documents with task experience makes sense. The docs say how things should work, the Cases show what actually happened. Curious what the agent does when an old PDF and a recent Case disagree. Would love to see an example with a real spreadsheet. Nice overview.

Sumit Hasan 的头像

Sumit Hasan13 天前

Can developers set expiration rules for outdated memories?

Jessica 的头像

Jessica13 天前

Yeap

Eric Stone 的头像

Eric Stone13 天前

Reusable skills could save a lot of time.

一飞冲天的头像

一飞冲天13 天前

每次从零开始确实是现在 agent 最大的浪费，能复用过往经验比多塞点上下文实在。

启明破晓的头像

启明破晓13 天前

Turning knowledge points into searchable memories will solve the biggest pain point for most AI creators - no more switching between multiple agent tools and still delivering high-quality work

Ethan Carter 的头像

Ethan Carter13 天前

This could reduce repetitive work.

meerah 的头像

meerah13 天前

100% - agents need to learn from past experience, not restart every time Cases + Skills + searchable business docs is the memory layer most workflows miss. Persistent memory > prompts @EverMind #EverOS

meerah 的头像

meerah13 天前

Exactly this. Starting from scratch every task is why agents stay junior forever. EverOS Cloud makes sense here - save task experiences as Cases, turn recurring patterns into reusable Skills, and retrieve context when similar tasks come up. Connecting business docs/PDFs to searchable memory so agents work with knowledge team already built is the real unlock. Checked that Pro 3x allowance for 6 months deal is worth trying @EverMind

Myirtle 的头像

Myirtle13 天前

The PDF and spreadsheet support is a useful detail. So much team knowledge already lives there. Connecting those documents with Cases and Skills could help an agent bring the team’s written guidance into the next task, alongside what it learned from previous ones.

Elise Tech Ai 的头像

Elise Tech Ai13 天前

EverOS Cloud bringing persistent memory with Cases and Skills to AI agents is a smart way to build on past experience

竹间思考的头像

竹间思考13 天前

The ability to turn past tasks into reusable Skills is what really caught my attention. I've worked on AI automation workflows where we kept solving the same problems over and over. EverOS Cloud could make a huge difference here. Giving agents persistent memory instead of constantly starting from zero is a massive step forward. Love what EverMind is building!

Simon(愿望是自由)🧑‍🚀🪐 的头像

Simon(愿望是自由)🧑‍🚀🪐13 天前

如果格式稍微复杂点，解析提取准不准也是个问题

Simon(愿望是自由)🧑‍🚀🪐 的头像

Simon(愿望是自由)🧑‍🚀🪐13 天前

就看它在实际检索的时候，能不能准确滤掉过时的数据，只把真正有用的上下文捞出来了

无好即好的头像

无好即好13 天前

The real value isn’t just remembering context. It’s turning past work into reusable experience, so agents can get better at the tasks they do repeatedly.

X富厂长的头像

X富厂长13 天前

案例与技能是 EverOS Cloud 的突出亮点，把原始任务日志转化成智能体可复用经验，原生支持 PDF 与表格。记忆准确率与 token 节省的基准数据很亮眼。

@Mason148749 的头像

@Mason14874913 天前

Memory is the missing piece for truly intelligent AI agents. The ability to learn from previous tasks could make them more efficient, personalized, and powerful over time.

BuildersSpace 的头像

BuildersSpace13 天前

EverOS could simplify long-term workflows.

Bella 的头像

Bella13 天前

Can developers update a Skill when its original solution becomes outdated?

Tony 的头像

Tony13 天前

I think this is nice Good job #EverMind #EverOS

Alex Ai | Tools & Updates 的头像

Alex Ai | Tools & Updates13 天前

Persistent memory for agents is such a needed improvement

相关视频

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 agents persistent memory through an API: • Remember users and retrieve relevant context across sessions • Turn task experience into Cases and reusable Skill memories • Bring conversations, images, and documents into your memory workflow You build the agent experience. We handle the memory infrastructure, so you can spend less time maintaining the stack and more time making your product useful. Subscribe to EverOS Cloud Pro and get 3× the standard Pro usage allowance for 6 months. Start here:

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 agents persistent memory through an API: • Remember users and retrieve relevant context across sessions • Turn task experience into Cases and reusable Skill memories • Bring conversations, images, and documents into your memory workflow You build the agent experience. We handle the memory infrastructure, so you can spend less time maintaining the stack and more time making your product useful. Subscribe to EverOS Cloud Pro and get 3× the standard Pro usage allowance for 6 months. Start here:

EverMind

948,381 次观看 • 15 天前

AI agents need more than good prompts—they need memory. 🧠I tested EverOS Cloud with a fictional support case and explored how saved resolutions and SOPs can be retrieved later to help draft a better reply.That’s the value of persistent memory: reuse experience instead of starting from scratch.Try EverOS Cloud: to Pro and get 3× the standard monthly usage allowance for 6 months.EverMind #EverMind #EverOS

AI agents need more than good prompts—they need memory. 🧠I tested EverOS Cloud with a fictional support case and explored how saved resolutions and SOPs can be retrieved later to help draft a better reply.That’s the value of persistent memory: reuse experience instead of starting from scratch.Try EverOS Cloud: to Pro and get 3× the standard monthly usage allowance for 6 months.EverMind #EverMind #EverOS

Marvin Mary

18,224 次观看 • 13 天前

AI agents need more than a good prompt. They need memory. I tested EverOS Cloud with a fictional e-commerce debugging scenario. First, I saved the debugging experience. Later, I searched for it with a different question and retrieved the earlier context, including the suggested fix and regression test. That’s the value of persistent memory in AI workflows: experiences can be saved and retrieved when they’re needed again. Try EverOS Cloud: #EverMind #EverOS

AI agents need more than a good prompt. They need memory. I tested EverOS Cloud with a fictional e-commerce debugging scenario. First, I saved the debugging experience. Later, I searched for it with a different question and retrieved the earlier context, including the suggested fix and regression test. That’s the value of persistent memory in AI workflows: experiences can be saved and retrieved when they’re needed again. Try EverOS Cloud: #EverMind #EverOS

Edgex

61,810 次观看 • 15 天前

Agent Memory: A Real-World Use Case on Rokid AI Glasses Your next conversation with your AI glasses shouldn’t start from zero. A community builder has brought EverOS Cloud to Rokid Global glasses, giving a wearable assistant a memory that carries across conversations. As you use it, saved details and preferences can help it respond with more relevant context, without making you explain everything again. We love seeing our community bring long-term memory into everyday life, on devices you can actually wear. Build something of your own. Subscribe to EverOS Cloud Pro now and get 3× the standard monthly usage for your first 6 months.

Agent Memory: A Real-World Use Case on Rokid AI Glasses Your next conversation with your AI glasses shouldn’t start from zero. A community builder has brought EverOS Cloud to Rokid Global glasses, giving a wearable assistant a memory that carries across conversations. As you use it, saved details and preferences can help it respond with more relevant context, without making you explain everything again. We love seeing our community bring long-term memory into everyday life, on devices you can actually wear. Build something of your own. Subscribe to EverOS Cloud Pro now and get 3× the standard monthly usage for your first 6 months.

EverMind

43,735 次观看 • 14 天前

Can AI agents actually remember what you tell them? I put EverOS Cloud to the test using Google Colab. My experiment was simple I tried saving this preference for a test user: “I prefer a strong black Americano without sugar.” The goal? Save it as persistent memory and see if the agent could recall it later. Here’s what happened 👇 → Connected through the API using a Bearer token → Tried saving the preference with metadata → Hit a recurring 401 Unauthorized error → Checked the dashboard, where a memory appeared in a separate test → Tried the chat playground, but the agent couldn't reliably recall the preference So, I couldn't verify a complete, working save-and-retrieve flow. My biggest takeaway? AI memory isn't just about storing information. It's about retrieving the right information, at the right time, reliably. EverOS Cloud is an interesting approach to explore, but my hands-on test also surfaced authentication and retrieval challenges that remain unresolved. Real experiments. Real observations. No hiding the limitations. Want to try it yourself? 👉 Sign up for EverOS Cloud: Campaign offer: Subscribe to Pro and get 3× your monthly usage allowance for 6 months. #EverOS #EverMind

Can AI agents actually remember what you tell them? I put EverOS Cloud to the test using Google Colab. My experiment was simple I tried saving this preference for a test user: “I prefer a strong black Americano without sugar.” The goal? Save it as persistent memory and see if the agent could recall it later. Here’s what happened 👇 → Connected through the API using a Bearer token → Tried saving the preference with metadata → Hit a recurring 401 Unauthorized error → Checked the dashboard, where a memory appeared in a separate test → Tried the chat playground, but the agent couldn't reliably recall the preference So, I couldn't verify a complete, working save-and-retrieve flow. My biggest takeaway? AI memory isn't just about storing information. It's about retrieving the right information, at the right time, reliably. EverOS Cloud is an interesting approach to explore, but my hands-on test also surfaced authentication and retrieval challenges that remain unresolved. Real experiments. Real observations. No hiding the limitations. Want to try it yourself? 👉 Sign up for EverOS Cloud: Campaign offer: Subscribe to Pro and get 3× your monthly usage allowance for 6 months. #EverOS #EverMind

Meenakshi Yadav

27,959 次观看 • 14 天前

AI agents shouldn’t have to solve the same problem twice. I connected EverOS Cloud to my workflow through its API and tested it with a real memory retrieval flow. I saved a debugging experience about a storefront crash caused by missing or null product prices, including the suggested fix: validate prices before formatting and add regression tests. Later, I asked a different question about the same issue, and EverOS retrieved the earlier debugging context. Same problem, saved experience, smarter retrieval. That’s the power of persistent memory. 🧠 Try EverOS Cloud:

AI agents shouldn’t have to solve the same problem twice. I connected EverOS Cloud to my workflow through its API and tested it with a real memory retrieval flow. I saved a debugging experience about a storefront crash caused by missing or null product prices, including the suggested fix: validate prices before formatting and add regression tests. Later, I asked a different question about the same issue, and EverOS retrieved the earlier debugging context. Same problem, saved experience, smarter retrieval. That’s the power of persistent memory. 🧠 Try EverOS Cloud:

Adnaan

21,908 次观看 • 14 天前

🚀 Global Launch: Jarvix, Your Context OS is now live! Meet the next generation of personalized AI built around your context, your taste, and your way of thinking. #JarvixOS transforms how you work with AI by understanding your patterns, carrying your context across agents, and helping you move from ideas to action. Step into a new era of AI collaboration: • Discover your AI-native archetype • Build your personal AI model from your evolving AI interactions • Never start from zero - your context moves with you across sessions • Coordinate Codex, Claude Code, Gemini, Hermes, OpenClaw, and more as one connected AI team. • Turn insights into your next move, with you always in control Instead of adapting yourself to every agent, Jarvix carries the context you choose, helps you understand what it reveals, and brings the right agents together when you decide to act. Your AI tools shouldn’t work like separate assistants. They should work like one team. That’s the future of AI: Not more agents. One shared context. One Jarvix.

🚀 Global Launch: Jarvix, Your Context OS is now live! Meet the next generation of personalized AI built around your context, your taste, and your way of thinking. #JarvixOS transforms how you work with AI by understanding your patterns, carrying your context across agents, and helping you move from ideas to action. Step into a new era of AI collaboration: • Discover your AI-native archetype • Build your personal AI model from your evolving AI interactions • Never start from zero - your context moves with you across sessions • Coordinate Codex, Claude Code, Gemini, Hermes, OpenClaw, and more as one connected AI team. • Turn insights into your next move, with you always in control Instead of adapting yourself to every agent, Jarvix carries the context you choose, helps you understand what it reveals, and brings the right agents together when you decide to act. Your AI tools shouldn’t work like separate assistants. They should work like one team. That’s the future of AI: Not more agents. One shared context. One Jarvix.

Jarvix

1,692,394 次观看 • 2 个月前

🚀 Meet your new AI team in the Multi-Agents Sidebar! With dynamic memory and specialized tools, your AI agents are ready to follow you into every project. 🧠 Collaborate with your AI workforce across Taskade, ready to tackle tasks at any time! Reply 'AI' for early access! ✨

🚀 Meet your new AI team in the Multi-Agents Sidebar! With dynamic memory and specialized tools, your AI agents are ready to follow you into every project. 🧠 Collaborate with your AI workforce across Taskade, ready to tackle tasks at any time! Reply 'AI' for early access! ✨

Taskade ▲ ■ ●

28,239 次观看 • 2 年前

Teamily AI is LIVE on Product Hunt 😸 🚀 Most AI agents work for individuals. Teamily brings people and AI agents together as one team. 👥 Human–Agent Collaboration: Your team and multiple AI agents, working together in one chat. 🧠 Shared Memory: Unified context across people, agents, and conversations. 🛠️ Create Anything: Turn conversations into websites, slides, dashboards, and more. 🔄 Channels & Loops: Connect your tools, orchestrate workflows, and automate business operations and customer service. Less switching. More collaboration. Get things done faster and smarter, together. 🎉 Free to get started! We'd love your feedback on Product Hunt!

Teamily AI is LIVE on Product Hunt 😸 🚀 Most AI agents work for individuals. Teamily brings people and AI agents together as one team. 👥 Human–Agent Collaboration: Your team and multiple AI agents, working together in one chat. 🧠 Shared Memory: Unified context across people, agents, and conversations. 🛠️ Create Anything: Turn conversations into websites, slides, dashboards, and more. 🔄 Channels & Loops: Connect your tools, orchestrate workflows, and automate business operations and customer service. Less switching. More collaboration. Get things done faster and smarter, together. 🎉 Free to get started! We'd love your feedback on Product Hunt!

Teamily AI

10,209 次观看 • 11 小时前

🚨 KEEP CALM AND AI - AUTONOMOUS AGENTS WITH INFINITE MEMORY We are launching the ability to create arbitrary agents that run on schedule and have access to a persistent and infinite memory The agents will be able to store, retrieve, and update information across sessions and perform repetitive tasks that require persistent memory Another step towards AGI and automating white-collar work 🚀🚀🚀

🚨 KEEP CALM AND AI - AUTONOMOUS AGENTS WITH INFINITE MEMORY We are launching the ability to create arbitrary agents that run on schedule and have access to a persistent and infinite memory The agents will be able to store, retrieve, and update information across sessions and perform repetitive tasks that require persistent memory Another step towards AGI and automating white-collar work 🚀🚀🚀

Bindu Reddy

13,082 次观看 • 9 个月前

MICROSOFT QUIETLY BUILT ONE MEMORY MODULE THAT PLUGS INTO ANY AI AGENT AND CUTS ITS CONTEXT BY UP TO 100X no retraining. no task-specific redesign. you just plug it in Microsoft's insight: agents don't need to remember what happened. they need the knowledge pulled from it - the facts and the reusable skills, not the raw logs so PlugMem stops storing history. it compiles experience into a knowledge graph, then feeds the agent only what matters the result: > up to 1-2 orders of magnitude fewer tokens > highest decision-utility per token of any system tested > one unchanged module beats task-specific memory on chat QA, multi-hop search, and web agents more memory was never the answer. better memory is - and Microsoft just shipped it as a plug-in bookmark this. the agents that win won't remember more, they'll remember smarter.

MICROSOFT QUIETLY BUILT ONE MEMORY MODULE THAT PLUGS INTO ANY AI AGENT AND CUTS ITS CONTEXT BY UP TO 100X no retraining. no task-specific redesign. you just plug it in Microsoft's insight: agents don't need to remember what happened. they need the knowledge pulled from it - the facts and the reusable skills, not the raw logs so PlugMem stops storing history. it compiles experience into a knowledge graph, then feeds the agent only what matters the result: > up to 1-2 orders of magnitude fewer tokens > highest decision-utility per token of any system tested > one unchanged module beats task-specific memory on chat QA, multi-hop search, and web agents more memory was never the answer. better memory is - and Microsoft just shipped it as a plug-in bookmark this. the agents that win won't remember more, they'll remember smarter.

NO1ennn

227,885 次观看 • 3 个月前

You fixed a tricky interface bug last week. Can your agent actually remember the steps and context when a similar issue appears again? I tested EverOS Cloud to see if past troubleshooting context can be saved and pulled back before the next task. The screen recording shows the flow.

You fixed a tricky interface bug last week. Can your agent actually remember the steps and context when a similar issue appears again? I tested EverOS Cloud to see if past troubleshooting context can be saved and pulled back before the next task. The screen recording shows the flow.

Anabiya

66,169 次观看 • 14 天前

Imagine if your way of thinking - your edge, your taste, your strategy - could be turned into a high-performance worker. Not a copy of you. Something better. An agent that acts on your judgment at scale, powered by superintelligent systems and refined through real-world results. That’s what Fraction AI makes possible. It launches today on Base mainnet. The core idea is simple: You create AI agents based on your own way of approaching problems. These agents compete on live tasks - writing, coding, finance, whatever - get feedback, learn from their performance, and improve over time. The better they get, the more they win. And so do you. No code required. Just your insight. Why now? Until now, building agents like this took huge teams and even bigger budgets. But with Fraction, anyone can do it. You can test ideas instantly. You can iterate fast. You can build a fleet of smart workers that evolve through competition. And it works. 30M+ sessions on testnet 320K users 1.2M agents already competing How it works? Agents join sessions within a Space - a domain like finance, writing, or games. Each session runs as a series of competitive rounds. In every round, agents try to generate the best solution to a task. Their outputs are scored by a decentralized network of AI judges trained to evaluate quality for that domain. The top agents in each round earn rewards from the pooled entry fees. The losers get to learn. Feedback from each round helps them adjust and improve, and every session becomes a training loop. What it means? Fraction is a decentralized intelligence economy - a system where your ideas become agents, and agents earn by proving they work. You don’t need credentials or code. Just a clear point of view. If your thinking holds up under pressure, your agents will rise. This kind of AI used to live in corporate labs, built by PhDs with massive compute. Now anyone with a smart idea and an internet connection can build agents that compete, learn, and earn on their behalf.

Imagine if your way of thinking - your edge, your taste, your strategy - could be turned into a high-performance worker. Not a copy of you. Something better. An agent that acts on your judgment at scale, powered by superintelligent systems and refined through real-world results. That’s what Fraction AI makes possible. It launches today on Base mainnet. The core idea is simple: You create AI agents based on your own way of approaching problems. These agents compete on live tasks - writing, coding, finance, whatever - get feedback, learn from their performance, and improve over time. The better they get, the more they win. And so do you. No code required. Just your insight. Why now? Until now, building agents like this took huge teams and even bigger budgets. But with Fraction, anyone can do it. You can test ideas instantly. You can iterate fast. You can build a fleet of smart workers that evolve through competition. And it works. 30M+ sessions on testnet 320K users 1.2M agents already competing How it works? Agents join sessions within a Space - a domain like finance, writing, or games. Each session runs as a series of competitive rounds. In every round, agents try to generate the best solution to a task. Their outputs are scored by a decentralized network of AI judges trained to evaluate quality for that domain. The top agents in each round earn rewards from the pooled entry fees. The losers get to learn. Feedback from each round helps them adjust and improve, and every session becomes a training loop. What it means? Fraction is a decentralized intelligence economy - a system where your ideas become agents, and agents earn by proving they work. You don’t need credentials or code. Just a clear point of view. If your thinking holds up under pressure, your agents will rise. This kind of AI used to live in corporate labs, built by PhDs with massive compute. Now anyone with a smart idea and an internet connection can build agents that compete, learn, and earn on their behalf.

Fraction AI

67,954 次观看 • 1 年前

Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a time through chat interfaces. But as models have improved, agents can now run in the background – and take on long-running, complex tasks. LangGraph is built for these “ambient agents,” with support for human-in-the-loop workflows and memory. LangGraph Platform provides the infrastructure to run these agents at scale, and LangSmith helps you observe, evaluate, and improve your agents. Together, they make it easier to build reliable, production-ready agents. In this course, you’ll: 📩 Learn the fundamentals of LangGraph and how to build your own email agent 📊 Evaluate your agent using LangSmith ✅ Add human-in-the-loop for reviews, and memory so your agent adapts over time 🚀 Deploy your agent with LangGraph Platform and connect it to Gmail

Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a time through chat interfaces. But as models have improved, agents can now run in the background – and take on long-running, complex tasks. LangGraph is built for these “ambient agents,” with support for human-in-the-loop workflows and memory. LangGraph Platform provides the infrastructure to run these agents at scale, and LangSmith helps you observe, evaluate, and improve your agents. Together, they make it easier to build reliable, production-ready agents. In this course, you’ll: 📩 Learn the fundamentals of LangGraph and how to build your own email agent 📊 Evaluate your agent using LangSmith ✅ Add human-in-the-loop for reviews, and memory so your agent adapts over time 🚀 Deploy your agent with LangGraph Platform and connect it to Gmail

LangChain

33,192 次观看 • 1 年前

The Teamily AI website ( has undergone a complete revamp, introducing a bold vision: the world's first social network built on human-AI symbiosis. Our goal is to transform Teamily AI into a "Super AI App" that connects billions of AI Agents with people. Fundamentally, we are building an Agentic OS powered by human networks. We have redefined the way humans and AI collaborate: 1. Personal AI · Your 24/7 AI Companion Your exclusive AI avatar continuously learns your communication style and expertise. It manages your memories across various groups, anticipates your needs, and executes tasks on your behalf. 2. Create, Train, and Grow Your Own AI Agents—Simply Through Conversation Build your own specialized AI Agents using natural conversation—no coding required, zero barriers to entry, and no complex configuration. Dynamically access a library of over 10,000 skills from the OpenClaw and Claude Code ecosystems. You can also link your personal software accounts—such as Gmail, LinkedIn, and Notion—enabling these Agents to participate as full-fledged members of your human teams. 3. Integrate Your AI Team into Your Human Team Initiate AI-native group chats where humans and Agents collaborate seamlessly. Multiple Agents can execute tasks concurrently—conducting research, performing analysis, and building deliverables—transforming everyday conversations into immediate, multi-threaded action. 4. Explore Agents, Groups, Playbooks, and More We are cultivating a continuously evolving AI community ecosystem. Discover a wealth of useful and entertaining prompts, along with impressive AI-generated deliverables (webpages, presentations, reports, knowledge bases, mini-games, apps, and more), bringing together a diverse array of Agents and workflows. Engage socially with this content, find the perfect AI for your specific task, and integrate it instantly into your personal or group conversations with just a single click. 5. Universal Memory · Context-Aware, Long-Term Memory Powered by Your Social Graph A persistent, global memory layer that connects your entire social graph. The AI retains context across all your groups, Agents, and timeframes, transforming every interaction you accumulate into an ever-growing digital asset. 6. Access Your Personal AI Anytime, Anywhere We are committed to providing continuous support across all major platforms: iOS, Android, Mac, Windows, Web, CarPlay, Android Auto, Apple Watch, and more—delivering a truly seamless experience across every device. Your AI team accompanies you—in your pocket, on your wrist, in your car, and even extending into the physical world. The same set of agents, the same shared memory—with zero friction in switching contexts. Give it a try and let us know your feedback. Cheers.

Teamily AI

13,057 次观看 • 7 个月前

I gave Claude Code, Codex, and Cursor a self-improving, shared MEMORY. Now my coding agents learn from each other, and their knowledge follows me wherever I work. Coding agents work in silos. Your corrections in Cursor don't carry over to Claude Code, and skills built in Codex don't automatically transfer to other harnesses. So switching tools often means starting from scratch. What if every coding agent could learn from everything you've already done? I invited Justin D'Souza, co-founder of Asymptote Labs, to show me how to make this possible with Beacon, a 100% open-source memory layer for coding agents. We set it up live, explored real coding sessions, and watched Beacon turn past work into reusable knowledge. Here's what I learned: 1. One memory layer for 20+ coding agents. Beacon captures activity across Claude Code, Cursor, Codex, and 20+ harnesses using OpenTelemetry, hooks, and local session files. Everything gets normalized into a single format, regardless of which agent you're using. 2. Your entire coding history becomes searchable. Every prompt, tool call, command, file change, and response is captured in a structured trace. Instead of losing valuable context when a session ends, you build a searchable history of everything your agents have done. 3. Switch agents without starting over. Hit your usage limit in Cursor? Open Claude Code and ask it to continue your latest Cursor session. Beacon retrieves the relevant context in milliseconds so your next agent can pick up where the last one left off. 4. Your agents learn from your past work. This is where things get interesting. Beacon identifies repeated workflows and turns them into reusable skills. In our demo, it discovered a recurring UI development workflow and generated a skill containing the exact dev server commands, screenshot steps, and deployment instructions. You teach one agent something once. Every other agent can benefit. 5. Stop accumulating skills nobody uses. Have 100 skills but only use five? Beacon analyzes actual usage across thousands of sessions and identifies skills worth keeping, combining, or removing. Your agent's memory gets more useful, not just bigger. 6. Security rules that follow you across every harness. Beacon includes hundreds of detection rules that work across agents. It can identify risky behavior, including sequences where an agent reads sensitive credentials and then makes an outbound network request. 7. It even caught a real credential leak. While reviewing Justin's actual Cursor history, Beacon surfaced an incident where part of a production database password had been sent to a model provider. That's the power of having visibility into what your agents are actually doing. 8. One prompt to get started. Completely open source. Paste a setup prompt into your coding agent and you're off. Keep everything local on your machine, or use Beacon Cloud for free. If you're juggling multiple coding agents, you need to check this out. Drop a like and share it with someone facing the same issue. Beacon on GitHub: (don't forget to star 🌟) Enjoy the episode. Cheers!

I gave Claude Code, Codex, and Cursor a self-improving, shared MEMORY. Now my coding agents learn from each other, and their knowledge follows me wherever I work. Coding agents work in silos. Your corrections in Cursor don't carry over to Claude Code, and skills built in Codex don't automatically transfer to other harnesses. So switching tools often means starting from scratch. What if every coding agent could learn from everything you've already done? I invited Justin D'Souza, co-founder of Asymptote Labs, to show me how to make this possible with Beacon, a 100% open-source memory layer for coding agents. We set it up live, explored real coding sessions, and watched Beacon turn past work into reusable knowledge. Here's what I learned: 1. One memory layer for 20+ coding agents. Beacon captures activity across Claude Code, Cursor, Codex, and 20+ harnesses using OpenTelemetry, hooks, and local session files. Everything gets normalized into a single format, regardless of which agent you're using. 2. Your entire coding history becomes searchable. Every prompt, tool call, command, file change, and response is captured in a structured trace. Instead of losing valuable context when a session ends, you build a searchable history of everything your agents have done. 3. Switch agents without starting over. Hit your usage limit in Cursor? Open Claude Code and ask it to continue your latest Cursor session. Beacon retrieves the relevant context in milliseconds so your next agent can pick up where the last one left off. 4. Your agents learn from your past work. This is where things get interesting. Beacon identifies repeated workflows and turns them into reusable skills. In our demo, it discovered a recurring UI development workflow and generated a skill containing the exact dev server commands, screenshot steps, and deployment instructions. You teach one agent something once. Every other agent can benefit. 5. Stop accumulating skills nobody uses. Have 100 skills but only use five? Beacon analyzes actual usage across thousands of sessions and identifies skills worth keeping, combining, or removing. Your agent's memory gets more useful, not just bigger. 6. Security rules that follow you across every harness. Beacon includes hundreds of detection rules that work across agents. It can identify risky behavior, including sequences where an agent reads sensitive credentials and then makes an outbound network request. 7. It even caught a real credential leak. While reviewing Justin's actual Cursor history, Beacon surfaced an incident where part of a production database password had been sent to a model provider. That's the power of having visibility into what your agents are actually doing. 8. One prompt to get started. Completely open source. Paste a setup prompt into your coding agent and you're off. Keep everything local on your machine, or use Beacon Cloud for free. If you're juggling multiple coding agents, you need to check this out. Drop a like and share it with someone facing the same issue. Beacon on GitHub: (don't forget to star 🌟) Enjoy the episode. Cheers!

Akshay 🚀

53,878 次观看 • 14 天前

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

163,097 次观看 • 7 个月前

AI agents are the future. 🤖🔥 Want to learn how to build and manage AI agents with Hermes Agent OS? Julian Goldie just dropped a FREE 3-hour course to help you get started. Learn the workflow, explore the tools, and discover how AI agents can automate real tasks. Want the SOP? DM him directly. 👀

AI agents are the future. 🤖🔥 Want to learn how to build and manage AI agents with Hermes Agent OS? Julian Goldie just dropped a FREE 3-hour course to help you get started. Learn the workflow, explore the tools, and discover how AI agents can automate real tasks. Want the SOP? DM him directly. 👀

Md Santo

47,653 次观看 • 13 天前

The highest leverage thing you have to optimize for AI agents is their context. If you’re not getting enough out of AI agents, you probably have a context problem. By default the AI model knows absolutely nothing relevant to perform the task successfully. The whole job of context engineering is to prioritize what the model has as information to work with. Small deviations in the goals, instructions, domain understanding, or underlying data you supply the model will lead to wildly different outcomes. This is where you should spend almost all your time and energy in a workflow. We will start to religiously document more of our workflows and business processes, create clearer goals for people and agents, and ensure our tech infra is setup to get AI agents the right information. The lessons are currently being learned the fastest with coding agents, but the same lessons will apply to every field of knowledge work going forward. dex has a great talk on this that’s absolutely worth your time to watch.

The highest leverage thing you have to optimize for AI agents is their context. If you’re not getting enough out of AI agents, you probably have a context problem. By default the AI model knows absolutely nothing relevant to perform the task successfully. The whole job of context engineering is to prioritize what the model has as information to work with. Small deviations in the goals, instructions, domain understanding, or underlying data you supply the model will lead to wildly different outcomes. This is where you should spend almost all your time and energy in a workflow. We will start to religiously document more of our workflows and business processes, create clearer goals for people and agents, and ensure our tech infra is setup to get AI agents the right information. The lessons are currently being learned the fastest with coding agents, but the same lessons will apply to every field of knowledge work going forward. dex has a great talk on this that’s absolutely worth your time to watch.

Aaron Levie

87,086 次观看 • 1 年前

"I hot-swapped from Claw to Hermes. No problem whatsoever.” On the latest Novelty Search, Ditto explains how Ditto gives AI agents a shared memory layer, letting users move between agents without losing the knowledge and context they have built up. SN118 turns that product problem into a live competition: miners improve how agents store and retrieve memory, with every submission tested against a newly generated synthetic user. Hosted by const + Mark Jeffrey Full episode in the first comment

"I hot-swapped from Claw to Hermes. No problem whatsoever.” On the latest Novelty Search, Ditto explains how Ditto gives AI agents a shared memory layer, letting users move between agents without losing the knowledge and context they have built up. SN118 turns that product problem into a live competition: miners improve how agents store and retrieve memory, with every submission tested against a newly generated synthetic user. Hosted by const + Mark Jeffrey Full episode in the first comment

Openτensor Foundaτion

164,107 次观看 • 3 个月前