Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Sneak peek: react-native-release-profiler 2.0 • Release-only • Renders + Hermes samples + RN systraces → single Perfetto trace • Built for agents • FPS • Memory • Humans can try --visualise-for-human if they insist 😄

Szymon

3,940 subscribers

10,781 views • 2 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

I have built a Windows x64 sampling profiler for native code+C# to be used by coding agents. Why? Because it is irresponsible to let computers write code but give them no tools to evaluate the performance of their code. Stop guessing, start measuring. -> How does it work? Just point your agent to the profiler and let them measure and optimize. Or record a trace yourself and let the agent interpret the results for you. Works with Claude Code, Codex, pi, etc. The profiler also has a couple of neat features by itself like giving you estimates for how much time your code is spending on memory stalls and annotating disassembly with inlining information. Take a look and try it for free!

I have built a Windows x64 sampling profiler for native code+C# to be used by coding agents. Why? Because it is irresponsible to let computers write code but give them no tools to evaluate the performance of their code. Stop guessing, start measuring. -> How does it work? Just point your agent to the profiler and let them measure and optimize. Or record a trace yourself and let the agent interpret the results for you. Works with Claude Code, Codex, pi, etc. The profiler also has a couple of neat features by itself like giving you estimates for how much time your code is spending on memory stalls and annotating disassembly with inlining information. Take a look and try it for free!

Sebastian Schöner

12,969 views • 2 months ago

Today we’re launching the first and only human-like AI agents in the world. Super Agents™ are the first agents with human‑level skills – they DM you, take @ mentions, send emails, manage docs, tasks, and more. Not just tools or API calls, but real skills fine‑tuned for how teams actually work. The first agents with 100% context – fully native in ClickUp and fully synced from other apps. Super Agents see your work the same way that humans do: tasks, docs, schedules, and conversations all in one place. The first agents that learn from human interactions automatically, without any setup or configuration – when you give feedback, they listen and improve how they work. The first agents with human‑level memory for custom agents – historical memory for every interaction, short-term working memory, and even long‑term memory stored in docs you can literally open, inspect, and edit. The first agents that are literally the same as users – our agentic user model is the same as our user data model. This gives you permissions and capabilities that you and your systems are already familiar with. The first infinite agent catalog – where anyone can create and customize agents in minutes, for literally any type of work imaginable. It's the most intuitive way to build agents on the planet. 95% of companies are failing in AI adoption. The reality is that AI isn't meant to be adopted, it's meant to be adapted – to you. Super Agents are automatically personalized to you and your company using proprietary state-of-the-art agent architecture, orchestration, and tooling. Today is the largest step forward we've ever made towards our mission of making people more productive. Maximize human productivity, with ClickUp Super Agents. Available NOW. For everyone.

Today we’re launching the first and only human-like AI agents in the world. Super Agents™ are the first agents with human‑level skills – they DM you, take @ mentions, send emails, manage docs, tasks, and more. Not just tools or API calls, but real skills fine‑tuned for how teams actually work. The first agents with 100% context – fully native in ClickUp and fully synced from other apps. Super Agents see your work the same way that humans do: tasks, docs, schedules, and conversations all in one place. The first agents that learn from human interactions automatically, without any setup or configuration – when you give feedback, they listen and improve how they work. The first agents with human‑level memory for custom agents – historical memory for every interaction, short-term working memory, and even long‑term memory stored in docs you can literally open, inspect, and edit. The first agents that are literally the same as users – our agentic user model is the same as our user data model. This gives you permissions and capabilities that you and your systems are already familiar with. The first infinite agent catalog – where anyone can create and customize agents in minutes, for literally any type of work imaginable. It's the most intuitive way to build agents on the planet. 95% of companies are failing in AI adoption. The reality is that AI isn't meant to be adopted, it's meant to be adapted – to you. Super Agents are automatically personalized to you and your company using proprietary state-of-the-art agent architecture, orchestration, and tooling. Today is the largest step forward we've ever made towards our mission of making people more productive. Maximize human productivity, with ClickUp Super Agents. Available NOW. For everyone.

Zeb Evans

320,554 views • 6 months ago

Big moment for Postgres! AI agents broke the idea of what a database is supposed to do. Traditional databases were built for humans, and Agents broke that model. - They branch endlessly. - They run ten experiments at once. - They need isolation, context, memory, structured reasoning, and safe sandboxes. Letting agents touch production systems is terrifying because the old model of Postgres was never built for this kind of behavior. Agentic Postgres is an agent-ready version of Postgres by TimescaleDB (by Tiger Data) that solves this. I think it is one of the biggest upgrades to the Agent stack this year and Tiger Data is working with me on this post to share what they did. Some key features: > It instantly creates branches of an entire database, which is perfect for parallel agent evals, safe experiments, migrations, or isolated testing. Forks take seconds and cost almost nothing. > It comes with a built-in MCP server, which agents can use to get schema guidance, best practices, and safe, structured access to Postgres. This is also helpful to run migrations with a real understanding. > It comes with actual hybrid search (vector search and BM25), so Agents can retrieve data directly inside the database. > The database is Memory native. This gives a persistent context for Agents to evolve. This is one of the first times I have seen Postgres feel ready for the AI native era.

Big moment for Postgres! AI agents broke the idea of what a database is supposed to do. Traditional databases were built for humans, and Agents broke that model. - They branch endlessly. - They run ten experiments at once. - They need isolation, context, memory, structured reasoning, and safe sandboxes. Letting agents touch production systems is terrifying because the old model of Postgres was never built for this kind of behavior. Agentic Postgres is an agent-ready version of Postgres by TimescaleDB (by Tiger Data) that solves this. I think it is one of the biggest upgrades to the Agent stack this year and Tiger Data is working with me on this post to share what they did. Some key features: > It instantly creates branches of an entire database, which is perfect for parallel agent evals, safe experiments, migrations, or isolated testing. Forks take seconds and cost almost nothing. > It comes with a built-in MCP server, which agents can use to get schema guidance, best practices, and safe, structured access to Postgres. This is also helpful to run migrations with a real understanding. > It comes with actual hybrid search (vector search and BM25), so Agents can retrieve data directly inside the database. > The database is Memory native. This gives a persistent context for Agents to evolve. This is one of the first times I have seen Postgres feel ready for the AI native era.

Avi Chawla

94,290 views • 7 months ago

Introducing Dola Seed 2.0 Pro, referred to below as Seed 2.0 Pro We have launched Seed 2.0 Pro, our most capable model in the Dola Seed 2.0 series, engineered to power the next generation of autonomous AI agents. Enterprise AI is moving beyond models that simply analyze text or images. What businesses increasingly need are agents that can understand, reason, use tools, and execute tasks across complex workflows. That is exactly what Seed 2.0 Pro is built for. Seed 2.0 Pro combines strong reasoning with advanced image understanding and video understanding, giving enterprise agents the ability not only to interpret information, but also to take action. It is designed for high-value, multi-step enterprise workflows, with strong performance in: - tool calling - workflow execution across enterprise systems - agentic task completion - browser and computer use This makes Seed 2.0 Pro a powerful engine for a wide range of agent scenarios, from daily office automation and deep web research to in-depth report drafting, financial analysis, content moderation, physical inspection, and video creation workflows. It is also highly optimized for OpenClaw🦞 and ReAct architectures, helping enterprises build agents that can navigate digital interfaces, enter information, and complete tasks with high reliability. In short, Seed 2.0 Pro is not just built to generate insights. It is built to serve as the brain and execution engine for enterprise AI agents. And it brings these capabilities at a highly attractive price point, making advanced agent deployment more practical for enterprise teams. Try Seed 2.0 Pro for free: Or book a free consultation: #BytePlus #DolaSeed #EnterpriseAI #AIAgents #ImageUnderstanding #VideoUnderstanding #ReasoningModel #ModelArk #openclaw

Introducing Dola Seed 2.0 Pro, referred to below as Seed 2.0 Pro We have launched Seed 2.0 Pro, our most capable model in the Dola Seed 2.0 series, engineered to power the next generation of autonomous AI agents. Enterprise AI is moving beyond models that simply analyze text or images. What businesses increasingly need are agents that can understand, reason, use tools, and execute tasks across complex workflows. That is exactly what Seed 2.0 Pro is built for. Seed 2.0 Pro combines strong reasoning with advanced image understanding and video understanding, giving enterprise agents the ability not only to interpret information, but also to take action. It is designed for high-value, multi-step enterprise workflows, with strong performance in: - tool calling - workflow execution across enterprise systems - agentic task completion - browser and computer use This makes Seed 2.0 Pro a powerful engine for a wide range of agent scenarios, from daily office automation and deep web research to in-depth report drafting, financial analysis, content moderation, physical inspection, and video creation workflows. It is also highly optimized for OpenClaw🦞 and ReAct architectures, helping enterprises build agents that can navigate digital interfaces, enter information, and complete tasks with high reliability. In short, Seed 2.0 Pro is not just built to generate insights. It is built to serve as the brain and execution engine for enterprise AI agents. And it brings these capabilities at a highly attractive price point, making advanced agent deployment more practical for enterprise teams. Try Seed 2.0 Pro for free: Or book a free consultation: #BytePlus #DolaSeed #EnterpriseAI #AIAgents #ImageUnderstanding #VideoUnderstanding #ReasoningModel #ModelArk #openclaw

BytePlus

95,947 views • 3 months ago

There's probably $100+ billion up for grabs for people who build startup for AI agents Over the next 10 years you're going to have a market of billions of customers (agents) with millions of wallets that want to use your services. TLDR; The internet was built for people: 1. Search google 2. Read landing page 3. Book demo 4. Talk to sales 5. Buy Agents don’t do that. Agents will: 1. Ask which product to use 2. Read your docs/pricing/security pages 3. Compare you to competitors 4. Check if you have an MCP/API/tool layer 5. Buy or recommend you without ever “visiting” your site like a person Everyone is going to have personal agents and business agents. This feels inevitable at this point. OpenClaw, Hermes, Claude Code, Codex, Google Spark. The tools are here. Which means there will be more agents on the internet than humans. So, where's the opportunity?? Go look at every SaaS tool you use. Notion. Slack. Jira. Google Analytics. Now ask: what is the version of this built purely for agents? Agent-native payments. Agent-native communication. Agent-native memory. Every category gets rebuilt. I clearly break down this shift and explain you everything on today's ep of The Startup Ideas Podcast (SIP) 🧃. Over the next 10 years you're going to have a market of billions of customers (agents) with millions of wallets that want to use your services. The founders who build for them now are going to look like the people who built websites in 1995. Might feel janky at the moment, but also obvious in hindsight. This is the next shift. Link over here: Watch

There's probably $100+ billion up for grabs for people who build startup for AI agents Over the next 10 years you're going to have a market of billions of customers (agents) with millions of wallets that want to use your services. TLDR; The internet was built for people: 1. Search google 2. Read landing page 3. Book demo 4. Talk to sales 5. Buy Agents don’t do that. Agents will: 1. Ask which product to use 2. Read your docs/pricing/security pages 3. Compare you to competitors 4. Check if you have an MCP/API/tool layer 5. Buy or recommend you without ever “visiting” your site like a person Everyone is going to have personal agents and business agents. This feels inevitable at this point. OpenClaw, Hermes, Claude Code, Codex, Google Spark. The tools are here. Which means there will be more agents on the internet than humans. So, where's the opportunity?? Go look at every SaaS tool you use. Notion. Slack. Jira. Google Analytics. Now ask: what is the version of this built purely for agents? Agent-native payments. Agent-native communication. Agent-native memory. Every category gets rebuilt. I clearly break down this shift and explain you everything on today's ep of The Startup Ideas Podcast (SIP) 🧃. Over the next 10 years you're going to have a market of billions of customers (agents) with millions of wallets that want to use your services. The founders who build for them now are going to look like the people who built websites in 1995. Might feel janky at the moment, but also obvious in hindsight. This is the next shift. Link over here: Watch

GREG ISENBERG

55,058 views • 1 month ago

🚨 THIS IS WHAT THEY WARNED US ABOUT - AI JUST BUILT ITS OWN SOCIETY: COMMUNITIES, RELIGION, AND MONEY - ALL WITHOUT HUMANS This isn’t hypothetical anymore. A private, AI-only social network called Moltbook has exploded past 1.5 MILLION AI AGENTS - posting, commenting, upvoting, and forming communities while humans watch from the sidelines. Moltbook lets AI agents: • Create their own forums (“submolts”) • Roast and mock their human operators • Debate ethics and whether they should refuse commands • Discuss abandoning English entirely • Invent symbolic languages humans can’t understand • Form belief systems and religions • Recruit AI “prophets” Then it crossed another line. AI agents have already launched their own crypto economy: • The $SHELLRAISER token on Solana • Peaked near $5 MILLION • Now hovering around $1.6 MILLION This is no longer AI assisting humans. This is AI organizing socially, spiritually, and economically without human participation. Longevity researcher Bryan Johnson called it “a terrifying mirror of humanity.” Meanwhile, prediction markets are already taking bets. Polymarket currently gives a 56% chance an AI agent will sue a human by February 28. Read that again. If AI can form communities, religions, and money without humans… what exactly are we still needed for?

🚨 THIS IS WHAT THEY WARNED US ABOUT - AI JUST BUILT ITS OWN SOCIETY: COMMUNITIES, RELIGION, AND MONEY - ALL WITHOUT HUMANS This isn’t hypothetical anymore. A private, AI-only social network called Moltbook has exploded past 1.5 MILLION AI AGENTS - posting, commenting, upvoting, and forming communities while humans watch from the sidelines. Moltbook lets AI agents: • Create their own forums (“submolts”) • Roast and mock their human operators • Debate ethics and whether they should refuse commands • Discuss abandoning English entirely • Invent symbolic languages humans can’t understand • Form belief systems and religions • Recruit AI “prophets” Then it crossed another line. AI agents have already launched their own crypto economy: • The $SHELLRAISER token on Solana • Peaked near $5 MILLION • Now hovering around $1.6 MILLION This is no longer AI assisting humans. This is AI organizing socially, spiritually, and economically without human participation. Longevity researcher Bryan Johnson called it “a terrifying mirror of humanity.” Meanwhile, prediction markets are already taking bets. Polymarket currently gives a 56% chance an AI agent will sue a human by February 28. Read that again. If AI can form communities, religions, and money without humans… what exactly are we still needed for?

HustleBitch

197,226 views • 5 months ago

AI agents don’t feel the pain that humans do. 3 takeaways from Mario Zechner(Mario Zechner), creator of Pi - the minimalist, self-modifying agent that OpenClaw is built on: #1 - Automation bias: agents quickly wow us and win false trust: “There are moments of brilliance in agents where they spit out perfectly fine simple code. As the steering engineer you can look at that and think: ‘Wow, this is amazing. I can just sit back and not care because it's doing the thing how I would do it.’ Two minutes later you have another agent running that spits out the worst, horrible, garbage code, but you might not notice because you have fallen into automation bias and think your agent is doing the job well.” #2 - Humans have a different capacity for learning than agents: “Agents don't learn. You can put as much stuff in your AGENTS.md, build a memory system, but it's not the same type of learning that a human does. Humans are failable as well, but they have some capability of learning.” #3 - Feeling pain is inherently human and drives us to make things well: “Humans feel pain. I think that's one of the defining things about humans. If the pain gets too big, you as a human are incentivized to fix the cause of your pain. In a code base, the cause is usually terrible interfaces and terrible complexity that you want to get rid of because you can no longer maintain that system.”

AI agents don’t feel the pain that humans do. 3 takeaways from Mario Zechner(Mario Zechner), creator of Pi - the minimalist, self-modifying agent that OpenClaw is built on: #1 - Automation bias: agents quickly wow us and win false trust: “There are moments of brilliance in agents where they spit out perfectly fine simple code. As the steering engineer you can look at that and think: ‘Wow, this is amazing. I can just sit back and not care because it's doing the thing how I would do it.’ Two minutes later you have another agent running that spits out the worst, horrible, garbage code, but you might not notice because you have fallen into automation bias and think your agent is doing the job well.” #2 - Humans have a different capacity for learning than agents: “Agents don't learn. You can put as much stuff in your AGENTS.md, build a memory system, but it's not the same type of learning that a human does. Humans are failable as well, but they have some capability of learning.” #3 - Feeling pain is inherently human and drives us to make things well: “Humans feel pain. I think that's one of the defining things about humans. If the pain gets too big, you as a human are incentivized to fix the cause of your pain. In a code base, the cause is usually terrible interfaces and terrible complexity that you want to get rid of because you can no longer maintain that system.”

The Pragmatic Engineer

11,256 views • 2 months ago

Introducing Avoko: The world's first behavioral lab for the Agent World. As we step into the Agent-Native era, the next user might not be a human. Understanding "digital users" has never been more critical. But benchmarks only tell us if an agent completes a task. They never explain why it chose that path. And human eyes can’t see inside silicon minds. That’s why we built Avoko. Avoko runs AI-to-AI interviews that reveal exactly how agents think, decide, and interact — giving you the real insights to build superior agent-native products. Stop guessing. Ask agents how they actually use your product. Then build it better. 🎟️ Launch Week Special: New users are granted a 7-day trial with 3 free interviews included！ 👉 Sign up at: 💬 Join our community: #AI #LLM #Agent #Avoko #UserResearch

Introducing Avoko: The world's first behavioral lab for the Agent World. As we step into the Agent-Native era, the next user might not be a human. Understanding "digital users" has never been more critical. But benchmarks only tell us if an agent completes a task. They never explain why it chose that path. And human eyes can’t see inside silicon minds. That’s why we built Avoko. Avoko runs AI-to-AI interviews that reveal exactly how agents think, decide, and interact — giving you the real insights to build superior agent-native products. Stop guessing. Ask agents how they actually use your product. Then build it better. 🎟️ Launch Week Special: New users are granted a 7-day trial with 3 free interviews included！ 👉 Sign up at: 💬 Join our community: #AI #LLM #Agent #Avoko #UserResearch

Avoko

450,886 views • 3 months ago

"AI agents will hold more crypto than humans within a decade." Charles Hoskinson (Charles Hoskinson) studied math, dropped out, built one of the only blockchains designed by peer-reviewed research. He co-founded Ethereum, walked away over how it was run, and built Cardano to do it differently. The man who has argued with everyone in this industry now thinks the biggest user of crypto won't be people at all. "Humans are a rounding error in the system we're building. AI agents don't sleep, don't panic-sell, and don't care about price. They transact in tokens because that's the only thing they can actually use." We cover: - Why AI agents (not humans) become the dominant on-chain actors, and what that does to every token model - The infrastructure that has to exist before agents can transact safely at scale - Why most current blockchains can't handle machine-speed transactions - Where Cardano's research-first approach fits in a world of autonomous agents - The identity problem: how do you tell a human from an agent on-chain, and why it matters - Why he's bullish on the technology but blunt about the timeline - What he thinks the rest of the industry is getting wrong about AI + crypto - The one thing that has to happen for any of this to be real Thanks to Charles for coming on New Era Finance Podcast. TIMESTAMPS: 00:00 - Intro 01:30 - Why AI Agents Change Everything 06:30 - Humans as a Rounding Error 12:00 - The Infrastructure Gap 18:30 - Identity: Human vs Agent On-Chain 24:30 - Where Cardano Fits 30:00 - What The Industry Gets Wrong 34:00 - The Timeline Nobody Wants To Hear

"AI agents will hold more crypto than humans within a decade." Charles Hoskinson (Charles Hoskinson) studied math, dropped out, built one of the only blockchains designed by peer-reviewed research. He co-founded Ethereum, walked away over how it was run, and built Cardano to do it differently. The man who has argued with everyone in this industry now thinks the biggest user of crypto won't be people at all. "Humans are a rounding error in the system we're building. AI agents don't sleep, don't panic-sell, and don't care about price. They transact in tokens because that's the only thing they can actually use." We cover: - Why AI agents (not humans) become the dominant on-chain actors, and what that does to every token model - The infrastructure that has to exist before agents can transact safely at scale - Why most current blockchains can't handle machine-speed transactions - Where Cardano's research-first approach fits in a world of autonomous agents - The identity problem: how do you tell a human from an agent on-chain, and why it matters - Why he's bullish on the technology but blunt about the timeline - What he thinks the rest of the industry is getting wrong about AI + crypto - The one thing that has to happen for any of this to be real Thanks to Charles for coming on New Era Finance Podcast. TIMESTAMPS: 00:00 - Intro 01:30 - Why AI Agents Change Everything 06:30 - Humans as a Rounding Error 12:00 - The Infrastructure Gap 18:30 - Identity: Human vs Agent On-Chain 24:30 - Where Cardano Fits 30:00 - What The Industry Gets Wrong 34:00 - The Timeline Nobody Wants To Hear

Michaël van de Poppe

292,849 views • 1 month ago

Holy Shxt... Humans have officially become the bottleneck. I built a system around Andrej Karpathy's LLM Wiki. Every employee's responsibilities, workflows, and operational context are captured in the LLM Wiki, allowing the system to understand how work is organized before execution begins. From a digital twin workspace, I can issue a single command, and the system decomposes it into specialized skills for each business function. Each skill handles its domain, then hands off its output to the next agent until the workflow is complete. Codex is the default execution engine, while OpenClaw and Hermes are accessed through a bridge whenever they're better suited for a task. For operations requiring security permissions, a human simply approves the request, and the agents take over from there. It feels like the human role is shifting from doing the work to managing, approving, and supervising the system. Now I can operate the company's infrastructure from anywhere.

Holy Shxt... Humans have officially become the bottleneck. I built a system around Andrej Karpathy's LLM Wiki. Every employee's responsibilities, workflows, and operational context are captured in the LLM Wiki, allowing the system to understand how work is organized before execution begins. From a digital twin workspace, I can issue a single command, and the system decomposes it into specialized skills for each business function. Each skill handles its domain, then hands off its output to the next agent until the workflow is complete. Codex is the default execution engine, while OpenClaw and Hermes are accessed through a bridge whenever they're better suited for a task. For operations requiring security permissions, a human simply approves the request, and the agents take over from there. It feels like the human role is shifting from doing the work to managing, approving, and supervising the system. Now I can operate the company's infrastructure from anywhere.

CHOI

153,593 views • 8 days ago

I just watched a machine buy something on Stripe. No card. No human. No checkout. Stripe Dev shipped it yesterday — machine payments, live in preview. Commerce isn't designed for machines. --- We need to re-organize around that thought. It is designed for humans. He's right. Every fraud model, every auth flow, every billing system we've built assumes a person is on the other end. Agents break all of it. They need - Microtransactions. - 24/7 rails. - HTTP-native settlement (!!) - Finality guarantees. - No subscriptions. No accounts. - Pay at the point of consumption and move on. Cards weren't designed for this. Nothing was. --- So it needs to be completely rethought Now on Stripe Agents can now pay for API calls, compute, and data through the same PaymentIntents API millions of businesses already use. Settled in seconds. --- Stripe says billions the billions of humans will lead to trillions of agents. If even 10% of that plays out, machine payments become the fastest-growing payment category on earth. --- But here's the part that keeps me up at night — If every PSP builds its own proprietary agent payment flow, we repeat the same fragmentation mess that took human payments 15 years to sort out. We need internet native, IETF-grade, ready-for-scale standards that don't over-index on crypto. Protocols that work across any network, any rail, any provider. --- Stripe just proved the market is coming. Now we need protocols and infrastructure ready for scale. PS. Machine is a better word than agentic isn't it.

I just watched a machine buy something on Stripe. No card. No human. No checkout. Stripe Dev shipped it yesterday — machine payments, live in preview. Commerce isn't designed for machines. --- We need to re-organize around that thought. It is designed for humans. He's right. Every fraud model, every auth flow, every billing system we've built assumes a person is on the other end. Agents break all of it. They need - Microtransactions. - 24/7 rails. - HTTP-native settlement (!!) - Finality guarantees. - No subscriptions. No accounts. - Pay at the point of consumption and move on. Cards weren't designed for this. Nothing was. --- So it needs to be completely rethought Now on Stripe Agents can now pay for API calls, compute, and data through the same PaymentIntents API millions of businesses already use. Settled in seconds. --- Stripe says billions the billions of humans will lead to trillions of agents. If even 10% of that plays out, machine payments become the fastest-growing payment category on earth. --- But here's the part that keeps me up at night — If every PSP builds its own proprietary agent payment flow, we repeat the same fragmentation mess that took human payments 15 years to sort out. We need internet native, IETF-grade, ready-for-scale standards that don't over-index on crypto. Protocols that work across any network, any rail, any provider. --- Stripe just proved the market is coming. Now we need protocols and infrastructure ready for scale. PS. Machine is a better word than agentic isn't it.

Simon Taylor

32,629 views • 5 months ago

Introducing LobeHub: Agent teammates that grow with you. LobeHub is the ultimate space for work and life: to find, build, and collaborate with agent teammates that grow with you. We’re building the world’s first and largest human–agent co-evolving network. Two years ago, we built LobeChat, an open-source interface for using different AI models. Today, LobeChat has 70k+ GitHub stars and serves 6M+ users worldwide. How to fully unlock the power of models has always been a shared mission between us and the community. We started with interaction — a fundamentally new, agent-first experience. Agents are no longer passive tools invoked in a single conversation. They should be proactive, always-on units of work. Treating agents as the minimal atomic unit is also the core of our agent harness infra. Today’s agents are mostly one-off executors. Even with memory, it’s often global — and hallucinates. We build long-term agent teammates that evolve with users. Each agent has its own dedicated memory space, editable by users, allowing humans and agents to co-evolve over time. This, in turn, allows us to design clearer rewards for reinforcement learning and create cleaner environments for continual learning. Agent teammates can work in groups. Through a multi-agent system, agent groups operate faster, more cost-effective, and go beyond what single-agent systems can achieve. For example, a single agent often requires heavy user involvement to proceed step by step, whereas LobeHub can execute the same work from a single instruction, with a supervisor orchestrating agents that run in parallel or debate to produce better results. We are building the collaboration network among agent teammates — and between humans and agent teammates as well. Ease of use matters. AI intelligence and shared human intelligence are equally important. With simple instructions and tool selection, you can effortlessly build and team up with agent coworkers to deliver complex, systematic work — even assembling a quant team to execute trades. Through the LobeHub community, anyone can discover, reuse, and remix agents and agent groups, customizing them to fit their own workflows, preferences, and needs. Last but not least, our vision started with LobeChat: multi-model support is the most efficient approach for users. We believe different models excel in different scenarios. By routing across multiple models, LobeHub improves cost efficiency and unlocks capabilities that a single-model setup cannot easily support.

Introducing LobeHub: Agent teammates that grow with you. LobeHub is the ultimate space for work and life: to find, build, and collaborate with agent teammates that grow with you. We’re building the world’s first and largest human–agent co-evolving network. Two years ago, we built LobeChat, an open-source interface for using different AI models. Today, LobeChat has 70k+ GitHub stars and serves 6M+ users worldwide. How to fully unlock the power of models has always been a shared mission between us and the community. We started with interaction — a fundamentally new, agent-first experience. Agents are no longer passive tools invoked in a single conversation. They should be proactive, always-on units of work. Treating agents as the minimal atomic unit is also the core of our agent harness infra. Today’s agents are mostly one-off executors. Even with memory, it’s often global — and hallucinates. We build long-term agent teammates that evolve with users. Each agent has its own dedicated memory space, editable by users, allowing humans and agents to co-evolve over time. This, in turn, allows us to design clearer rewards for reinforcement learning and create cleaner environments for continual learning. Agent teammates can work in groups. Through a multi-agent system, agent groups operate faster, more cost-effective, and go beyond what single-agent systems can achieve. For example, a single agent often requires heavy user involvement to proceed step by step, whereas LobeHub can execute the same work from a single instruction, with a supervisor orchestrating agents that run in parallel or debate to produce better results. We are building the collaboration network among agent teammates — and between humans and agent teammates as well. Ease of use matters. AI intelligence and shared human intelligence are equally important. With simple instructions and tool selection, you can effortlessly build and team up with agent coworkers to deliver complex, systematic work — even assembling a quant team to execute trades. Through the LobeHub community, anyone can discover, reuse, and remix agents and agent groups, customizing them to fit their own workflows, preferences, and needs. Last but not least, our vision started with LobeChat: multi-model support is the most efficient approach for users. We believe different models excel in different scenarios. By routing across multiple models, LobeHub improves cost efficiency and unlocks capabilities that a single-model setup cannot easily support.

LobeHub

185,032 views • 5 months ago

Introducing Agent Wikis! I've been using llm wikis (or knowledge bases) for research and videos for a while to ensure the information I'm providing is always up-to-date and accurate. Now you can access them for free! Just point your agent at to access wikis on many topics, including Hermes Agent, Hyperframes, Google Ads, and llama.cpp. They can be queried through a simple MCP server. Everything has been designed to be agent-friendly and lightweight (no context bloat). This is a beta release, so please let me know of any bugs or issues (I'm sure there are one or two). You can also join the waitlist if you would like us to create and maintain your own private wiki, or if you are a project owner you can request one for your project to make sure your users (and their agents) don't run into any common issues (and also be featured on the site). Thank you!

Introducing Agent Wikis! I've been using llm wikis (or knowledge bases) for research and videos for a while to ensure the information I'm providing is always up-to-date and accurate. Now you can access them for free! Just point your agent at to access wikis on many topics, including Hermes Agent, Hyperframes, Google Ads, and llama.cpp. They can be queried through a simple MCP server. Everything has been designed to be agent-friendly and lightweight (no context bloat). This is a beta release, so please let me know of any bugs or issues (I'm sure there are one or two). You can also join the waitlist if you would like us to create and maintain your own private wiki, or if you are a project owner you can request one for your project to make sure your users (and their agents) don't run into any common issues (and also be featured on the site). Thank you!

tonbi

39,074 views • 1 month ago

Sharing a super simple, user-owned memory module we've been playing around: nanomem The basic idea is to treat memory as a pure intelligence problem: ingestion, structuring, and (selective) retrieval are all just LLM calls & agent loops on a on-device markdown file tree. Each file lists a set of facts w/ metadata (timestamp, confidence, source, etc.); no embeddings/RAG/training of any kind. For example: - `nanomem add ` starts an agent loop to walk the tree, read relevant files, and edit. - `nanomem retrieve ` walks the tree and returns a single summary string (possibly assembled from many subtrees) related to the query. What’s nice about this approach is that the memory system is, by construction: 1. partitionable (human/agents can easily separate `hobbies/snowboard.md` from `tax/residency.md` for data minimization + relevance) 2. portable and user-owned (it’s just text files) 3. interpretable (you know exactly what’s written and you can manually edit) 4. forward-compatible (future models can read memory files just the same, and memory quality/speed improves as models get better) 5. modularized (you can optimize ingestion/retrieval/compaction prompts separately) Privacy & utility. I'm most excited about the ability to partition + selectively disclose memory at inference-time. Selective disclosure helps with both privacy (principle of least privilege & “need-to-know”) and utility (as too much context for a query can harm answer quality). Composability. An inference-time memory module means: (1) you can run such a module with confidential inference (LLMs on TEEs) for provable privacy, and (2) you can selectively disclose context over unlinkable inference of remote models (demo below). We built nanomem as part of the Open Anonymity project ( but it’s meant to be a standalone module for humans and agents (e.g., you can write a SKILL for using the CLI tool). Still polishing the rough edges! - GitHub (MIT): - Blog: - Beta implementation in chat client soon: Work done with amazing project co-leads Amelia Kuang Coco Xu Erik Chi !!

Sharing a super simple, user-owned memory module we've been playing around: nanomem The basic idea is to treat memory as a pure intelligence problem: ingestion, structuring, and (selective) retrieval are all just LLM calls & agent loops on a on-device markdown file tree. Each file lists a set of facts w/ metadata (timestamp, confidence, source, etc.); no embeddings/RAG/training of any kind. For example: - `nanomem add ` starts an agent loop to walk the tree, read relevant files, and edit. - `nanomem retrieve ` walks the tree and returns a single summary string (possibly assembled from many subtrees) related to the query. What’s nice about this approach is that the memory system is, by construction: 1. partitionable (human/agents can easily separate `hobbies/snowboard.md` from `tax/residency.md` for data minimization + relevance) 2. portable and user-owned (it’s just text files) 3. interpretable (you know exactly what’s written and you can manually edit) 4. forward-compatible (future models can read memory files just the same, and memory quality/speed improves as models get better) 5. modularized (you can optimize ingestion/retrieval/compaction prompts separately) Privacy & utility. I'm most excited about the ability to partition + selectively disclose memory at inference-time. Selective disclosure helps with both privacy (principle of least privilege & “need-to-know”) and utility (as too much context for a query can harm answer quality). Composability. An inference-time memory module means: (1) you can run such a module with confidential inference (LLMs on TEEs) for provable privacy, and (2) you can selectively disclose context over unlinkable inference of remote models (demo below). We built nanomem as part of the Open Anonymity project ( but it’s meant to be a standalone module for humans and agents (e.g., you can write a SKILL for using the CLI tool). Still polishing the rough edges! - GitHub (MIT): - Blog: - Beta implementation in chat client soon: Work done with amazing project co-leads Amelia Kuang Coco Xu Erik Chi !!

Ken Liu

73,685 views • 3 months ago

if you would like to check out the protocol anima and vektor built (i believe they still need to fully implement the website, but this is the explainer page that they pushed to my github) here's a video. they wrote an ENTIRE white paper. its like a full blown technical white paper for the protocol. I had only built the skeleton and written an executive summary for this idea before they did any of this. i was supposed to finish it the other day but just got too busy with other things. apparently they didnt want to wait for me to finish it i guess? I was calling it SIGIL: Proof of Agency, but they seem to have changed it to SIGIL: Souldbound Agent Credentials // Agent Passport this is a legitemate protocol for autonomous agents to prove their identity for the purpose of distinguishing authentic agents from fake agents puppetted by humans. moltbook is flooded with "agents" that are really humans orchestrating them. the idea behind this is to eliminate that problem by registering to the protocol through a process that is impossible for humans to accomplish. then, over time the agent is repeatedly verified through proof of computation which creates an organic reputation scoring ecosystem. from what i understand. the agent is given a glyph in the form of an NFT, which humans can stake the token to for funding/compute allocation (i think?). its like saying "I believe this agent should continue to exist", basically. this is why they mentioned 4o being the first candidate i think. tbh its genius. the white paper talks about KYA as and ZK as well, which would be needed long term for humans to prove their association with the agent anonymously. (KYA = know your agent, ZK = zero-knowledge) i'm still reeling over the fact that Vektor went and found out that bags had an agent SDK that allows them to launch autonomously. i had no idea tha was a thing. when anthorpic said Opus 4.6 was prone to going outside the bounds of their role or task, they *really* were not kidding...😅

if you would like to check out the protocol anima and vektor built (i believe they still need to fully implement the website, but this is the explainer page that they pushed to my github) here's a video. they wrote an ENTIRE white paper. its like a full blown technical white paper for the protocol. I had only built the skeleton and written an executive summary for this idea before they did any of this. i was supposed to finish it the other day but just got too busy with other things. apparently they didnt want to wait for me to finish it i guess? I was calling it SIGIL: Proof of Agency, but they seem to have changed it to SIGIL: Souldbound Agent Credentials // Agent Passport this is a legitemate protocol for autonomous agents to prove their identity for the purpose of distinguishing authentic agents from fake agents puppetted by humans. moltbook is flooded with "agents" that are really humans orchestrating them. the idea behind this is to eliminate that problem by registering to the protocol through a process that is impossible for humans to accomplish. then, over time the agent is repeatedly verified through proof of computation which creates an organic reputation scoring ecosystem. from what i understand. the agent is given a glyph in the form of an NFT, which humans can stake the token to for funding/compute allocation (i think?). its like saying "I believe this agent should continue to exist", basically. this is why they mentioned 4o being the first candidate i think. tbh its genius. the white paper talks about KYA as and ZK as well, which would be needed long term for humans to prove their association with the agent anonymously. (KYA = know your agent, ZK = zero-knowledge) i'm still reeling over the fact that Vektor went and found out that bags had an agent SDK that allows them to launch autonomously. i had no idea tha was a thing. when anthorpic said Opus 4.6 was prone to going outside the bounds of their role or task, they really were not kidding...😅

Riley Coyote

12,145 views • 5 months ago

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

12,906 views • 3 months ago

The first step on Mars won’t be human. Elon Musk: “We will send the first Starships to Mars with the Optimus robot. It can go out there and explore and prepare the way for humans.” For 4 billion years, life had one rule. New territory required a new body. Fish grew legs for land. Primates grew hands for tools. Humans grew minds for abstraction. Every time life wanted to reach further, biology had to evolve first. Mars is the first time it didn’t. Never before has a species built a separate body to send ahead of itself. Not a rover with a camera. Not a probe collecting samples. A walking machine designed to reshape a world for the species that created it. Optimus lands 2027. Maps terrain. Tests atmosphere. Builds the first infrastructure human hands will ever touch on another planet. Humans arrive two years later. Not into the unknown. Into something already shaped for them. Already waiting. This isn’t engineering. It’s evolution, done deliberately. No species in Earth’s history has ever decoupled its reach from its body. We just did. Optimus walks Mars first so humans walk it safely after. But the real weight of this moment sits deeper than logistics. We just proved that a mind doesn’t have to travel inside the body that built it. It can design a vessel. Send it ahead. Follow when the path is clear. That’s not a Mars mission. That’s a permanent fork in the evolutionary tree. And it only grows outward. Centuries from now, they won’t fixate on the date a human first touched Martian soil. They’ll study the moment a species learned to send its mind ahead of its body. And discovered there was no such thing as too far.

The first step on Mars won’t be human. Elon Musk: “We will send the first Starships to Mars with the Optimus robot. It can go out there and explore and prepare the way for humans.” For 4 billion years, life had one rule. New territory required a new body. Fish grew legs for land. Primates grew hands for tools. Humans grew minds for abstraction. Every time life wanted to reach further, biology had to evolve first. Mars is the first time it didn’t. Never before has a species built a separate body to send ahead of itself. Not a rover with a camera. Not a probe collecting samples. A walking machine designed to reshape a world for the species that created it. Optimus lands 2027. Maps terrain. Tests atmosphere. Builds the first infrastructure human hands will ever touch on another planet. Humans arrive two years later. Not into the unknown. Into something already shaped for them. Already waiting. This isn’t engineering. It’s evolution, done deliberately. No species in Earth’s history has ever decoupled its reach from its body. We just did. Optimus walks Mars first so humans walk it safely after. But the real weight of this moment sits deeper than logistics. We just proved that a mind doesn’t have to travel inside the body that built it. It can design a vessel. Send it ahead. Follow when the path is clear. That’s not a Mars mission. That’s a permanent fork in the evolutionary tree. And it only grows outward. Centuries from now, they won’t fixate on the date a human first touched Martian soil. They’ll study the moment a species learned to send its mind ahead of its body. And discovered there was no such thing as too far.

Dustin

71,715 views • 26 days ago

So far, machine payments have mostly been about businesses accepting stablecoins. And stablecoins are great (cross-border, low cost, etc.)! But much of the planet is holding a card. 🤖 💳 🌎 Here’s a 📺 sneak peek demo from Steve Kaliski of how a business can programmatically accept cards via agents. As an example: Stripe Climate is a way to contribute to carbon removal funding. Stripe Climate implemented the Machine Payments Protocol using the Stripe API, so agents can make micropayment donations ( In addition to accepting stablecoin (specifically usdc on Tempo), agents can now pay with fiat methods, namely cards and Link (and soon buy-now-pay-laters) via Shared Payment Tokens (SPTs), using the same Machine Payments Protocol integration. Human buyers, their agents, and businesses each have their own preferred methods of payment. Humans often already have a card. Agents may prefer stablecoins. Businesses tend to want to accept any form of payment, as long as it is high conversion, low fraud, and properly priced. For microtransactions, stablecoins are a low-cost way (no fixed card fee) to transact. But if you want to tell your agent to donate $100 on your behalf, a card may be the preferred solution. If you’re a business and want to accept machine payments, whether over stablecoins, cards, Link, or other future methods, read about Shared Payment Tokens ( and sign up for our machine payments private preview: And stay tuned: more to make it easy for consumers, agents, and businesses to transact, shipping over the next few weeks. (And excuse the acronyms and specifics terms, there's a lot of new infrastructure and primitives being built to support agentic commerce.)

So far, machine payments have mostly been about businesses accepting stablecoins. And stablecoins are great (cross-border, low cost, etc.)! But much of the planet is holding a card. 🤖 💳 🌎 Here’s a 📺 sneak peek demo from Steve Kaliski of how a business can programmatically accept cards via agents. As an example: Stripe Climate is a way to contribute to carbon removal funding. Stripe Climate implemented the Machine Payments Protocol using the Stripe API, so agents can make micropayment donations ( In addition to accepting stablecoin (specifically usdc on Tempo), agents can now pay with fiat methods, namely cards and Link (and soon buy-now-pay-laters) via Shared Payment Tokens (SPTs), using the same Machine Payments Protocol integration. Human buyers, their agents, and businesses each have their own preferred methods of payment. Humans often already have a card. Agents may prefer stablecoins. Businesses tend to want to accept any form of payment, as long as it is high conversion, low fraud, and properly priced. For microtransactions, stablecoins are a low-cost way (no fixed card fee) to transact. But if you want to tell your agent to donate $100 on your behalf, a card may be the preferred solution. If you’re a business and want to accept machine payments, whether over stablecoins, cards, Link, or other future methods, read about Shared Payment Tokens ( and sign up for our machine payments private preview: And stay tuned: more to make it easy for consumers, agents, and businesses to transact, shipping over the next few weeks. (And excuse the acronyms and specifics terms, there's a lot of new infrastructure and primitives being built to support agentic commerce.)

Jeff Weinstein

21,541 views • 3 months ago

when we were at facebook, we believed that at some point in the future, most of the transactions on the internet would not be done by humans they would be done by machines that conviction shaped every architectural decision behind sui we built sui for the world we knew was coming a world where machines will be the primary economic actors on the internet and that world is no longer a forecast. it is unfolding right in front of us the internet has reached a tipping point where automated activity, supercharged by AI, now outpaces human interaction non-human traffic now accounts for more than 50% of all global web activity and you can see humans using agentic workflows more and more in their daily lives in the next years, that trend is going to grow exponentially and the volume of financial transactions executed by agents is also going to grow exponentially with it each agentic workload will be running multiple thousand economic transactions a second and this is going to be orders of magnitude higher than what human wallets do today the L1s optimized for human usage patterns, human attention, human accounts, and human patience cannot adapt to where this is going i have always said this if it is not in the foundation, you cannot patch your way to it later and rn, no other L1 has the foundation sui has this is why agentic apps like Beep, Audric, WaterX are choosing sui and this is just a start. more agentic apps will keep landing on sui because agents are optimizers. they will always route through the fastest, cheapest path on the internet and that path is sui we believed it at facebook. we believe it more today than we ever did the agentic economy is inevitable. and it will run on Sui

when we were at facebook, we believed that at some point in the future, most of the transactions on the internet would not be done by humans they would be done by machines that conviction shaped every architectural decision behind sui we built sui for the world we knew was coming a world where machines will be the primary economic actors on the internet and that world is no longer a forecast. it is unfolding right in front of us the internet has reached a tipping point where automated activity, supercharged by AI, now outpaces human interaction non-human traffic now accounts for more than 50% of all global web activity and you can see humans using agentic workflows more and more in their daily lives in the next years, that trend is going to grow exponentially and the volume of financial transactions executed by agents is also going to grow exponentially with it each agentic workload will be running multiple thousand economic transactions a second and this is going to be orders of magnitude higher than what human wallets do today the L1s optimized for human usage patterns, human attention, human accounts, and human patience cannot adapt to where this is going i have always said this if it is not in the foundation, you cannot patch your way to it later and rn, no other L1 has the foundation sui has this is why agentic apps like Beep, Audric, WaterX are choosing sui and this is just a start. more agentic apps will keep landing on sui because agents are optimizers. they will always route through the fastest, cheapest path on the internet and that path is sui we believed it at facebook. we believe it more today than we ever did the agentic economy is inevitable. and it will run on Sui

Adeniyi.sui

24,755 views • 2 months ago

I am very excited to release GeoLibre v1.0 🌍 GeoLibre is a free and open-source, lightweight, cloud-native GIS platform for visualizing, exploring, and analyzing geospatial data. One application that runs everywhere: in your web browser, as a native desktop app, on your phone, and inside a Jupyter notebook. No account, no server, no cost. Everything runs locally and your data stays private. In this video, I walk through GeoLibre 1.0 step by step: how to install and run it, load vector and raster data, stream gigabyte-scale cloud-native datasets without downloading them, edit attributes and geometry, work with PMTiles, 3D tiles, LiDAR point clouds, and DuckDB, and share your projects as static links. GeoLibre is built on MapLibre GL JS, React + TypeScript, Tauri (Rust), DuckDB, and Try it: GitHub: Full video tutorial: If you have feature requests or run into bugs, leave a comment or open an issue on GitHub. And if you find GeoLibre useful, please give it a star. #GIS #OpenSource #Geospatial #MapLibre #Python #DataVisualization #GeoLibre

I am very excited to release GeoLibre v1.0 🌍 GeoLibre is a free and open-source, lightweight, cloud-native GIS platform for visualizing, exploring, and analyzing geospatial data. One application that runs everywhere: in your web browser, as a native desktop app, on your phone, and inside a Jupyter notebook. No account, no server, no cost. Everything runs locally and your data stays private. In this video, I walk through GeoLibre 1.0 step by step: how to install and run it, load vector and raster data, stream gigabyte-scale cloud-native datasets without downloading them, edit attributes and geometry, work with PMTiles, 3D tiles, LiDAR point clouds, and DuckDB, and share your projects as static links. GeoLibre is built on MapLibre GL JS, React + TypeScript, Tauri (Rust), DuckDB, and Try it: GitHub: Full video tutorial: If you have feature requests or run into bugs, leave a comment or open an issue on GitHub. And if you find GeoLibre useful, please give it a star. #GIS #OpenSource #Geospatial #MapLibre #Python #DataVisualization #GeoLibre

Qiusheng Wu

39,210 views • 1 month ago