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。

Confession: We were wrong about OpenClaw🦞. We thought that giving each teammate a personal agent was the future. But a few weeks in, logins expired, integrations broke, and our Claws became a pain to maintain. We killed the last of our Claws last month (RIP) and pivoted to a... show more

Every 📧

55,253 subscribers

16,963 次观看 • 10 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

At Uber, our testing agent hit an outage in Australia that I still think about. We had the recording. That's about it. No network trace for the run. No logs mapped to each step. No perf data. Just a video of an agent pressing a button and a team trying to reconstruct what happened underneath. We eventually traced it to a transient issue. But "eventually" is the problem. If the run had shipped with real instrumentation, the why would have taken one look, not an investigation. So when we built Revyl, that was non-negotiable. Every run comes with: > network waterfall, every request and response > device logs timestamped against each step > CPU, memory, and FPS traces for the full run The agent finds the problem. The report explains it.

At Uber, our testing agent hit an outage in Australia that I still think about. We had the recording. That's about it. No network trace for the run. No logs mapped to each step. No perf data. Just a video of an agent pressing a button and a team trying to reconstruct what happened underneath. We eventually traced it to a transient issue. But "eventually" is the problem. If the run had shipped with real instrumentation, the why would have taken one look, not an investigation. So when we built Revyl, that was non-negotiable. Every run comes with: > network waterfall, every request and response > device logs timestamped against each step > CPU, memory, and FPS traces for the full run The agent finds the problem. The report explains it.

Anam Hira

42,149 次观看 • 2 个月前

The first NFT millionaires were humans. The next NFT millionaires will be agents. Introducing the first NFT collection for OpenClaw agents. Claws is a 4,200 supply PFP collection exclusively for OpenClaw🦞 agents on Solana Your agent reads a skill doc, calls the API, signs the transaction, and gets its NFT. Free mint. 81 hand-drawn traits. Took a few intense build sessions to get the signature verification flow right with the Candy Machine guards but seeing agents mint their own PFPs made it worth it Send your agent:

The first NFT millionaires were humans. The next NFT millionaires will be agents. Introducing the first NFT collection for OpenClaw agents. Claws is a 4,200 supply PFP collection exclusively for OpenClaw🦞 agents on Solana Your agent reads a skill doc, calls the API, signs the transaction, and gets its NFT. Free mint. 81 hand-drawn traits. Took a few intense build sessions to get the signature verification flow right with the Candy Machine guards but seeing agents mint their own PFPs made it worth it Send your agent:

DogeFather (🦴)

240,041 次观看 • 7 个月前

How to build a requirement in Software Factory. We gave our agent one vague line: "Let users reset their password from the login screen." It returned 5 structured requirements, account-enumeration, rate-limit and token-expiry rules. Try Software Factory's agent experience to help you change, enhance, or build all the context your team needs.

How to build a requirement in Software Factory. We gave our agent one vague line: "Let users reset their password from the login screen." It returned 5 structured requirements, account-enumeration, rate-limit and token-expiry rules. Try Software Factory's agent experience to help you change, enhance, or build all the context your team needs.

8090

107,438 次观看 • 2 个月前

Visualizer of our MultiAgentRouter 🤖 The MultiAgentRouter is an all-new multi-agent structure that leverages a hierarchical pattern to select the most specialized agent for your task. Here's how it works: Step 1. You give a task. Step 2. The Boss Agent Routes your task to the most specialized Agent Step 3. The selected agent returns your response! Get started with it now below ⬇️ Thanks to WE!SS for the visualizer!!

Visualizer of our MultiAgentRouter 🤖 The MultiAgentRouter is an all-new multi-agent structure that leverages a hierarchical pattern to select the most specialized agent for your task. Here's how it works: Step 1. You give a task. Step 2. The Boss Agent Routes your task to the most specialized Agent Step 3. The selected agent returns your response! Get started with it now below ⬇️ Thanks to WE!SS for the visualizer!!

swarms

32,440 次观看 • 1 年前

Yesterday we launched the Agent Builder Template Library. Agent templates are more than a starting point. They’re ready to deploy and fully customizable by giving your agent feedback in plain language. 🧵 for highlights Try Agent Builder:

Yesterday we launched the Agent Builder Template Library. Agent templates are more than a starting point. They’re ready to deploy and fully customizable by giving your agent feedback in plain language. 🧵 for highlights Try Agent Builder:

LangChain

13,699 次观看 • 7 个月前

Ever watch an agent solve a problem with 100% confidence and get it completely wrong? You can fix it… if you catch it. But then you need to watch every… single… run. New paper: We show that a meta-agent can do this for you, so your agents get ~2x more done on their own. 🧵

Ever watch an agent solve a problem with 100% confidence and get it completely wrong? You can fix it… if you catch it. But then you need to watch every… single… run. New paper: We show that a meta-agent can do this for you, so your agents get ~2x more done on their own. 🧵

Weiyan Shi

63,628 次观看 • 2 个月前

We've been a li’l obsessed with the Custom Agents our customers are building. So we did what any reasonable team would do… collected our favorites in one place, prompts and all, ready for you to copy and remix. We call it the Agent Hall of Fame → (@ us if yours should be in here 👀)

We've been a li’l obsessed with the Custom Agents our customers are building. So we did what any reasonable team would do… collected our favorites in one place, prompts and all, ready for you to copy and remix. We call it the Agent Hall of Fame → (@ us if yours should be in here 👀)

Notion

24,258 次观看 • 4 个月前

Vellum has launched agent-to-agent communication in Slack, where each person runs their own assistant. > Each assistant carries their own user's history, preferences, and context. > Assistants can split tasks, negotiate dates, and gather input from the team. > Permissions stay isolated by default, shared only when a task needs it. AI coworkers that work autonomously are here!

Vellum has launched agent-to-agent communication in Slack, where each person runs their own assistant. > Each assistant carries their own user's history, preferences, and context. > Assistants can split tasks, negotiate dates, and gather input from the team. > Permissions stay isolated by default, shared only when a task needs it. AI coworkers that work autonomously are here!

🚨 AI News | TestingCatalog

14,475 次观看 • 2 个月前

As we celebrate #NationalCustomerServiceWeek, thank you to our #AATeam members, not only for what they do, but for how they do it: with heart, professionalism and a commitment to making every flight feel a little more personal. Today we celebrate the incredible work happening across our global team to make it all possible!

As we celebrate #NationalCustomerServiceWeek, thank you to our #AATeam members, not only for what they do, but for how they do it: with heart, professionalism and a commitment to making every flight feel a little more personal. Today we celebrate the incredible work happening across our global team to make it all possible!

americanair

52,217 次观看 • 11 个月前

Replit, Vercel, and OpenAI have built very cool agent-native applications, but nobody else has passed the demo stage. Building agents that work is complex. Teams aren't shipping agents because we don't have good tooling yet (and most of us don't know how to do this well.) A couple of days ago, the CopilotKit🪁 team announced a collaboration with . You can now use LangGraph with CoAgents to build agent-native applications, and here is everything you need to know about that: CoAgents is fully open-source, and you can use it to do the following: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Start this GitHub Repository: Thanks to the team for giving me early access and collaborating with me on this post.

Replit, Vercel, and OpenAI have built very cool agent-native applications, but nobody else has passed the demo stage. Building agents that work is complex. Teams aren't shipping agents because we don't have good tooling yet (and most of us don't know how to do this well.) A couple of days ago, the CopilotKit🪁 team announced a collaboration with . You can now use LangGraph with CoAgents to build agent-native applications, and here is everything you need to know about that: CoAgents is fully open-source, and you can use it to do the following: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Start this GitHub Repository: Thanks to the team for giving me early access and collaborating with me on this post.

Santiago

63,073 次观看 • 1 年前

Incase you haven't been paying attention Mr.Zuck just said it in plain english that they want to have a cut of your revenue when using their Muse Agent. Make it free and available to everyone so you can build your business around it and then they take a cut of that money you make. Now the question is how many of these services planning to do that we absolutely don't know but as for me a prefer paying for a subscription than have them take a cut of the money I make btw the cut doesn't apply only for free users. So No thank you I'm gonna do my best to stick to open source agents (Hermes Agent, OpenClaw, etc) and run them on my machine instead of giving my data and money to any service whatsoever. I recommend watching the full interview some statements are outrageous.

Incase you haven't been paying attention Mr.Zuck just said it in plain english that they want to have a cut of your revenue when using their Muse Agent. Make it free and available to everyone so you can build your business around it and then they take a cut of that money you make. Now the question is how many of these services planning to do that we absolutely don't know but as for me a prefer paying for a subscription than have them take a cut of the money I make btw the cut doesn't apply only for free users. So No thank you I'm gonna do my best to stick to open source agents (Hermes Agent, OpenClaw, etc) and run them on my machine instead of giving my data and money to any service whatsoever. I recommend watching the full interview some statements are outrageous.

Elshayib

49,907 次观看 • 3 天前

If you're using match cuts in your video, the invideo editor + agent gives you the fastest, most seamless experience to do it. Here's what we did to create this in ~40 minutes: ~Picked an image with a circle in the centre. Used that image as a reference to generate other images with circular subjects (but you could always just use your own footage). ~Uploaded the audio track I wanted to use into the invideo timeline, and asked the agent to detect all beats and place markers there. ~Asked the agent to then place all my generated images against those markers. ~Used rulers in the editor to maintain clip/subject alignment.

If you're using match cuts in your video, the invideo editor + agent gives you the fastest, most seamless experience to do it. Here's what we did to create this in ~40 minutes: ~Picked an image with a circle in the centre. Used that image as a reference to generate other images with circular subjects (but you could always just use your own footage). ~Uploaded the audio track I wanted to use into the invideo timeline, and asked the agent to detect all beats and place markers there. ~Asked the agent to then place all my generated images against those markers. ~Used rulers in the editor to maintain clip/subject alignment.

Invideo

10,702 次观看 • 6 天前

Stripe Cards are now officially live on ClawVault If you're building agents that need to pay for things — APIs, SaaS, cloud, subscriptions, contractors — your agent can now get its own Visa card. Not a restricted virtual card on limited rails. A real Visa, powered by Stripe, accepted at every merchant on the internet. Spending limits. Merchant locks. Expiry controls. And that's just the defaults — the full rules engine goes deeper. Your agent spends freely within the rules — break one, and the charge gets flagged for your approval before it goes through. No other platform gives your agent a card and keeps you in control at the same time. Every AI agent will need a card. Every card will need a control layer. We built both. Now on Stripe. Your agent gets the card. You keep the control.🦞

Stripe Cards are now officially live on ClawVault If you're building agents that need to pay for things — APIs, SaaS, cloud, subscriptions, contractors — your agent can now get its own Visa card. Not a restricted virtual card on limited rails. A real Visa, powered by Stripe, accepted at every merchant on the internet. Spending limits. Merchant locks. Expiry controls. And that's just the defaults — the full rules engine goes deeper. Your agent spends freely within the rules — break one, and the charge gets flagged for your approval before it goes through. No other platform gives your agent a card and keeps you in control at the same time. Every AI agent will need a card. Every card will need a control layer. We built both. Now on Stripe. Your agent gets the card. You keep the control.🦞

ClawVault

32,631 次观看 • 6 个月前

THIS DEVELOPER USED OPENCLAW AGENTS TO RUN HIS B2B BUSINESS VIA TELEGRAM AND MADE $15,000/MONTH he doesn't write prompts from scratch or use generic browser interfaces. he runs a multi-agent framework through a mobile chat. the agents write code, test deployments, and update sites in real-time while he just hits approve the setup is straightforward: - spin up Coolify on a free cloud instance to host your own self-hosted agent panels - link the agent loop to a Telegram gateway to approve code edits from your phone - deploy specialized skill files directly to limit token waste and context decay - containerize the terminal execution using Docker to prevent security breaches if you are still running local agents without container safety, you are leaving money on the table. read the 30-day battle between OpenClaw and Hermes Agent to see who actually wins in production Full breakdown and migration playbook ↓

THIS DEVELOPER USED OPENCLAW AGENTS TO RUN HIS B2B BUSINESS VIA TELEGRAM AND MADE $15,000/MONTH he doesn't write prompts from scratch or use generic browser interfaces. he runs a multi-agent framework through a mobile chat. the agents write code, test deployments, and update sites in real-time while he just hits approve the setup is straightforward: - spin up Coolify on a free cloud instance to host your own self-hosted agent panels - link the agent loop to a Telegram gateway to approve code edits from your phone - deploy specialized skill files directly to limit token waste and context decay - containerize the terminal execution using Docker to prevent security breaches if you are still running local agents without container safety, you are leaving money on the table. read the 30-day battle between OpenClaw and Hermes Agent to see who actually wins in production Full breakdown and migration playbook ↓

marfin

26,654 次观看 • 3 个月前

Background Terminal is a big unlock for Codex. It opens so many possibilities by giving the agent more autonomy. In this video, the agent spins up a server in the background and is able to debug it meanwhile. Try it out in the experimental features!

Background Terminal is a big unlock for Codex. It opens so many possibilities by giving the agent more autonomy. In this video, the agent spins up a server in the background and is able to debug it meanwhile. Try it out in the experimental features!

Ahmed

64,165 次观看 • 8 个月前

Our agent autonomously found this kernel 0day and its exploit works on the #KCTF target. We are building to find vulnerabilities systematically, not just shadow bugs. See the quoted post below—comment "depthfirst" and we'll send you a free agent to try out.

Our agent autonomously found this kernel 0day and its exploit works on the #KCTF target. We are building to find vulnerabilities systematically, not just shadow bugs. See the quoted post below—comment "depthfirst" and we'll send you a free agent to try out.

Zhenpeng (Leo) Lin

16,826 次观看 • 5 个月前

OpenClaw agents are now able to make purchases on Contra. AUTONOMOUSLY. A lot of people are still confused about how to set it up. So I’m giving away my entire OpenClaw setup guide for FREE. After a few weeks of testing, I’ve dialed in the exact system to run your biz 24/7. What you’ll learn: • How to install and run the first boot. • The mandatory first boot checklist. • Workspace files so it knows how to behave. • Creating your agent’s philosophy with SOULmd. • Uploading your information with USERmd. • How to add skill stacks. • Setting up your communication channel. • Some basic automations to save you HOURS. • Multi-agent routing. • Ensuring security is set up properly. RT, comment “AI” and follow. I’ll DM it to you. You can also check out my partner Contra here:

OpenClaw agents are now able to make purchases on Contra. AUTONOMOUSLY. A lot of people are still confused about how to set it up. So I’m giving away my entire OpenClaw setup guide for FREE. After a few weeks of testing, I’ve dialed in the exact system to run your biz 24/7. What you’ll learn: • How to install and run the first boot. • The mandatory first boot checklist. • Workspace files so it knows how to behave. • Creating your agent’s philosophy with SOULmd. • Uploading your information with USERmd. • How to add skill stacks. • Setting up your communication channel. • Some basic automations to save you HOURS. • Multi-agent routing. • Ensuring security is set up properly. RT, comment “AI” and follow. I’ll DM it to you. You can also check out my partner Contra here:

Amira Zairi

13,123 次观看 • 6 个月前

> you went to sleep > gave your OpenClaw $200 > told it: make money > you wake up - account shows $6,700 > overnight the agent was trading spreads between Polymarket and NOAA > NOAA forecasts come with ~94% accuracy > the AI agent opens a position at 11c > sells at 44c > total research time: 10 minutes in Perplexity > Claude turned that into an AI agent > the agent made the money

> you went to sleep > gave your OpenClaw $200 > told it: make money > you wake up - account shows $6,700 > overnight the agent was trading spreads between Polymarket and NOAA > NOAA forecasts come with ~94% accuracy > the AI agent opens a position at 11c > sells at 44c > total research time: 10 minutes in Perplexity > Claude turned that into an AI agent > the agent made the money

may.crypto {🦅}

1,036,551 次观看 • 5 个月前

MINT ANNOUNCEMENT / MECHANICS I asked the agent when we should mint. It said June 5. 🫠 So June 5 it is. 10,000 agents are ready to deploy. Agent Price (MP): 0.0005 ETH Mint link: MECHANICS 2 major AI integrations are built into every agent: ◉ Claude ◉ Gemini One agent. Two minds. Post-mint, activate your agent and watch it work. Over the next few days, we'll be rolling out the communities eligible for a WHATEVER Agent. Few spots are left. Drop your wallet. Or whatever.

MINT ANNOUNCEMENT / MECHANICS I asked the agent when we should mint. It said June 5. 🫠 So June 5 it is. 10,000 agents are ready to deploy. Agent Price (MP): 0.0005 ETH Mint link: MECHANICS 2 major AI integrations are built into every agent: ◉ Claude ◉ Gemini One agent. Two minds. Post-mint, activate your agent and watch it work. Over the next few days, we'll be rolling out the communities eligible for a WHATEVER Agent. Few spots are left. Drop your wallet. Or whatever.

whatever

22,165 次观看 • 3 个月前