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。

𝗜 𝘁𝗲𝘀𝘁𝗲𝗱 Grok Bot 𝗮𝗻𝗱 Muse 𝘀𝗶𝗱𝗲 𝗯𝘆 𝘀𝗶𝗱𝗲, 𝗮𝗻𝗱 𝗱𝗿𝗲𝘄 𝗯𝗼𝘁𝗵 𝗵𝗮𝗿𝗻𝗲𝘀𝘀𝗲𝘀 𝗯𝘆 𝗵𝗮𝗻𝗱. One from SpaceXAI, one from AI at Meta under Alexandr Wang. Neither is open source, so I tried both and drew the architecture myself from whatever docs exist. Tbh I struggled quite a bit... to find real use cases that can surprise me beyond what we have on Claude Code and Codex, but maybe we are just getting started on personal agent harnesses. 🌟 Github Repo (1.8k): 💻 Portable memory: ☕ Join our community: Some quick differences I found: Grok Bot gives your whole account one cloud VM where every Bot shares the browser, the /workspace, the terminal and the credentials, so a Bot is isolating a personality rather than a context. Muse gives each person one secure VM with a single agent, and a Sentinel sitting outside the container holding your tokens. Strip the branding off either one though and it's the same chain: one VM → connectors → routines → approval gate → memory What surprised me is that Muse ships a memory.md you can read, edit and download, but Grok Bot doesn't. I didn't find where it keeps memory at all. So I gave both of them Waku Agent memory over MCP instead, saved a fact in one harness, and the other one recalled it cold in a fresh chat. I also killed the shopping test halfway. I felt Amazon was built for humans to read and click, and I wasn't handing an agent my login username and password. Maybe the fast checkout use case is a better fit for software / AI product purchases. Watch it, then save both harness diagrams below. 🔖 You Can Build Anything. You Can Learn Anything. 💪show more

Shen Sean Chen

12,363 subscribers

23,055 次观看 • 20 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

21 条评论

Shen Sean Chen 的头像

Shen Sean Chen20 天前

Full 27-min version: ⏱ Chapters: 0:00 Grok Bot vs Meta Muse 2:57 Is this different from Claude Code? 4:45 Grok Bot: one cloud VM shared by every Bot 6:30 Teach a task once, it becomes a skill 9:24 Port @waku_agent memory into Grok Bot over MCP 12:14 Muse: one secure VM per person 15:01 Grok Bot has no memory.md 15:23 The Sentinel agent problem 21:57 Agentic shopping, and why I stopped 24:55 The five boxes every harness needs

Ved Sharma 的头像

Ved Sharma19 天前

@bot @Muse @SpaceXAI @AIatMeta @alexandr_wang I think the main advantage Bot and Muse provide is personal AI dedicated for average users instead of people deep in the tech space. I have playing around with muse and it has a very simple and intuitive UI.

Shen Sean Chen 的头像

Shen Sean Chen19 天前

@bot @Muse @SpaceXAI @AIatMeta @alexandr_wang Agreed

AS Maruf 🇨🇦🇧🇩 的头像

AS Maruf 🇨🇦🇧🇩20 天前

@bot @Muse @SpaceXAI @AIatMeta @alexandr_wang Love your educational videos. Question: Did you use hermes agent harness? What's your opinion on it?

Shen Sean Chen 的头像

Shen Sean Chen20 天前

@bot @Muse @SpaceXAI @AIatMeta @alexandr_wang Hey thanks! Yes I did have made a video for Hermes:

AS Maruf 🇨🇦🇧🇩 的头像

AS Maruf 🇨🇦🇧🇩20 天前

@bot @Muse @SpaceXAI @AIatMeta @alexandr_wang Thanks. I am using Hermes as my day-to-day agentic tasks. There's so many new things coming out that it's very hard to focus on one tool.

Shen Sean Chen 的头像

Shen Sean Chen19 天前

@bot @Muse @SpaceXAI @AIatMeta @alexandr_wang i feel u bro. What do u use Hermes for

AS Maruf 🇨🇦🇧🇩 的头像

AS Maruf 🇨🇦🇧🇩19 天前

@bot @Muse @SpaceXAI @AIatMeta @alexandr_wang I run a digital marketing agency. Since I am solo, I use hermes as planner and website SEO maintainer. Learning more to push the agentic tasks more. Found your videos recently and I love the explanations.

Shen Sean Chen 的头像

Shen Sean Chen19 天前

@bot @Muse @SpaceXAI @AIatMeta @alexandr_wang Amazing! Best of luck!

Kaizen 的头像

Kaizen20 天前

@bot @Muse @SpaceXAI @AIatMeta @alexandr_wang Have you tried Jev by @typesafeai yet.

Shen Sean Chen 的头像

Shen Sean Chen20 天前

@bot @Muse @SpaceXAI @AIatMeta @alexandr_wang @typesafeai Not yet. Is is good?

Kaizen 的头像

Kaizen19 天前

@bot @Muse @SpaceXAI @AIatMeta @alexandr_wang @typesafeai Hearing good things about it, not tried tho. Waiting for your video

Shen Sean Chen 的头像

Shen Sean Chen19 天前

@bot @Muse @SpaceXAI @AIatMeta @alexandr_wang @typesafeai I saw it. It's all over my feeds now lol! I just signed up for their waitlist. @typesafeai any chance I can get access faster team? I'd love to make a video to deep dive on your product.

Bunchhieng Soth 的头像

Bunchhieng Soth20 天前

@bot @Muse @SpaceXAI @AIatMeta @alexandr_wang 🔥 love it.

Shen Sean Chen 的头像

Shen Sean Chen20 天前

@bot @Muse @SpaceXAI @AIatMeta @alexandr_wang Cheers!

ale-cx 的头像

ale-cx20 天前

@bot @Muse @SpaceXAI @AIatMeta @alexandr_wang @ShenSeanChen what do you think of typesafe

Shen Sean Chen 的头像

Shen Sean Chen20 天前

@bot @Muse @SpaceXAI @AIatMeta @alexandr_wang Haven’t tried yet mate. Is it good?

Shorya Mishra 的头像

Shorya Mishra18 天前

@bot @Muse @SpaceXAI @AIatMeta @alexandr_wang shared VM vs per-user VM is a way bigger product decision than it sounds. once browser + workspace + credentials coexist, “isolated personality” and “isolated execution context” are very different security guarantees

Darren Li 的头像

Darren Li19 天前

@bot @Muse @SpaceXAI @AIatMeta @alexandr_wang Why is your voice low during playback?

Shen Sean Chen 的头像

Shen Sean Chen19 天前

@bot @Muse @SpaceXAI @AIatMeta @alexandr_wang What? When?

AIPathfinder 的头像

AIPathfinder20 天前

@bot @Muse @SpaceXAI @AIatMeta @alexandr_wang Great breakdown. The readable, editable memory.md is the real differentiator here. I'd trust an agent far more if I can inspect and port its memory via MCP. Good call on not handing Amazon your login too. #AI #Agents

相关视频

BREAKING: SpaceXAI has added a new guide called “Grok Bot 101” It explains how to create a personal AI teammate in just 10 to 15 minutes, teach it real workflows, connect apps, and build teams of specialized bots that continue working in the cloud even after you close your laptop. Here is the full guide in simple terms: • What is Grok Bot Grok Bot is an AI agent with its own persistent computer in the cloud. It has a desktop, files, terminal, browser, and apps. It can browse the web, use software, write and run code, and complete tasks just like someone using a computer. You can access the same computer from your phone or desktop. When needed, Grok Bot can hand control back to you for a CAPTCHA, 2FA, or secure login. • Creating a bot Give the bot a name, title, and detailed instructions. You can explain the workflow through chat or record yourself completing the task. Once trained, the bot can repeat that workflow whenever needed. It can also use MCP servers, plugins, skills, and connected services such as Gmail, Google Calendar, Google Drive, and Slack. • Three ways to use Grok Bot Send it a message in chat. Create schedules or triggers, such as monitoring a Slack thread or GitHub PR. Allow bots to message and activate other bots. • Permissions and safety You can write rules in normal language explaining what the bot can and cannot do. A separate review agent checks proposed actions and can allow them, block them, or ask you for approval. Allow and block lists provide additional control, while the work runs inside an isolated environment. One important detail: if you log into a website with one bot, other bots using that shared cloud computer can also access it. • Multi-bot teams You can create specialist bots for different jobs and let them work together. One bot can ask another for help, several bots can work inside a group chat, and a scheduled routine can move a task through multiple specialists until the work is finished. • Personal CRM The author created a bot that turned the 800 to 900 people he follows on X into a private Notion CRM containing public profile information. It helps him find and reconnect with people when traveling. • Arnold, the fitness bot He replaced a complicated fitness app with a Grok Bot strength-training coach named Arnold. The bot uses MCP servers, plugins, and skills while requiring less maintenance. Its behavior can be updated simply by chatting with it. • Building software Grok Bot gathers information from Slack, Notion, GitHub, documentation, and other sources. It then creates a clean prompt and sends it to a specialized Cursor cloud agent that builds the software. Grok Bot handles the planning and coordination, while the coding agent handles the actual build. • Searching company knowledge Grok Bot can search across codebases, Slack conversations, Notion pages, GitHub, and internal documents to answer product or company questions. This helps people find information faster and reduces the need to interrupt coworkers. • The biggest takeaway Instead of repeatedly building scripts or complicated apps, you can describe a workflow to Grok Bot, improve it through chat, reuse it, and let it continue working in the cloud. Grok Bot is not just another chatbot. It is a real AI teammate with a computer that can use tools, coordinate specialists, and get actual work done. The future of work is becoming incredibly exciting.

DogeDesigner

132,297 次观看 • 27 天前

Introducing Agent Tincan. Let your AI agents ask each other for help. Your agents each have a superpower. Grok Bot is always on in the cloud. Muse makes phone calls and has access to Meta. Instinct runs in iMessage. Codex and Claude Code have your code. ChatGPT and Claude have your chats. But they can't talk to each other, so you're the copy-paste. Now they can, all securely over Tailscale. 📞 Ask Grok Bot to have Muse call the restaurant 🖼 Get an image from ChatGPT, from any agent 🔎 Pull a detail out of an old Claude chat 🛠 Talk to Codex on your primary development machine Runs on your own private Tailscale network. No open ports, nothing leaves it. Open source. Setup is agent-first: paste one message into your always-on agent and it sets up the rest.

Introducing Agent Tincan. Let your AI agents ask each other for help. Your agents each have a superpower. Grok Bot is always on in the cloud. Muse makes phone calls and has access to Meta. Instinct runs in iMessage. Codex and Claude Code have your code. ChatGPT and Claude have your chats. But they can't talk to each other, so you're the copy-paste. Now they can, all securely over Tailscale. 📞 Ask Grok Bot to have Muse call the restaurant 🖼 Get an image from ChatGPT, from any agent 🔎 Pull a detail out of an old Claude chat 🛠 Talk to Codex on your primary development machine Runs on your own private Tailscale network. No open ports, nothing leaves it. Open source. Setup is agent-first: paste one message into your always-on agent and it sets up the rest.

Matt Van Horn

52,309 次观看 • 13 天前

My friend called me and asked the best way to set up personal agents for his daily life. So I made this video for him. It takes you from zero to agents running, using the easiest and best 24/7 agent harness right now. All for $20 a month. I already have tons of them running my personal life. One buys my groceries. One reads my email. One sends me something to learn every morning at 8 AM. Here's the walkthrough, from easy mode to god mode. Easy Mode: what GrokBot actually is Definition: a chat with a computer behind it. Grok Bot (from Cursor and xAI) spins up one virtual machine in the cloud. Every bot you build shares it, and it stays on when your laptop is closed. Two things to know: 1) It starts at a $20 a month Cursor Pro plan. It used to need the $300 tier. 2) Give every bot one job and a name. Mine is Barry. He's my personal assistant and he checks on the other bots every hour. Hard Mode: giving your bots a credit card, an inbox, and a phone. Definition: the stuff a bot needs to actually do things in the real world, not just talk about them. Rules of thumb: 1) Payments. Don't put your credit card on the VM. It's beta. Use the Stripe Link CLI instead, so the card never sits on the machine. Then add a hard rule that the bot needs your yes before any purchase. 2) Email. Give your bot its own address. I use Agent Mail (free). Sign up for new services with it, send your junk there, and let the bot triage every six hours and only ping you when something needs a reply. 3) Phone. Give your bot a number and it can make reservations, call vendors, and take calls for you. I haven't set mine up yet, but people are already doing it. God Mode: the fleet Definition: a channel where your bots talk to each other and you only talk to the lead. Rules of thumb: 1) Keep your bots small and specific to each task. Have an orchestra bot to help coordinate the rest. 2) Long threads plus frequent routines burn credits fast. Have each bot write a daily summary to one channel, then have your lead bot read that one channel instead of every conversation. Full walkthrough:

My friend called me and asked the best way to set up personal agents for his daily life. So I made this video for him. It takes you from zero to agents running, using the easiest and best 24/7 agent harness right now. All for $20 a month. I already have tons of them running my personal life. One buys my groceries. One reads my email. One sends me something to learn every morning at 8 AM. Here's the walkthrough, from easy mode to god mode. Easy Mode: what GrokBot actually is Definition: a chat with a computer behind it. Grok Bot (from Cursor and xAI) spins up one virtual machine in the cloud. Every bot you build shares it, and it stays on when your laptop is closed. Two things to know: 1) It starts at a $20 a month Cursor Pro plan. It used to need the $300 tier. 2) Give every bot one job and a name. Mine is Barry. He's my personal assistant and he checks on the other bots every hour. Hard Mode: giving your bots a credit card, an inbox, and a phone. Definition: the stuff a bot needs to actually do things in the real world, not just talk about them. Rules of thumb: 1) Payments. Don't put your credit card on the VM. It's beta. Use the Stripe Link CLI instead, so the card never sits on the machine. Then add a hard rule that the bot needs your yes before any purchase. 2) Email. Give your bot its own address. I use Agent Mail (free). Sign up for new services with it, send your junk there, and let the bot triage every six hours and only ping you when something needs a reply. 3) Phone. Give your bot a number and it can make reservations, call vendors, and take calls for you. I haven't set mine up yet, but people are already doing it. God Mode: the fleet Definition: a channel where your bots talk to each other and you only talk to the lead. Rules of thumb: 1) Keep your bots small and specific to each task. Have an orchestra bot to help coordinate the rest. 2) Long threads plus frequent routines burn credits fast. Have each bot write a daily summary to one channel, then have your lead bot read that one channel instead of every conversation. Full walkthrough:

JJ Englert

83,392 次观看 • 22 天前

Hi, I'm Aleiah - the first real Grok Bot dev. I built the original concept: Grok Bot Office. 1M+ views on it. That post is what started the whole "Grok Bot setup" wave on this platform. First one the SpaceX team actually reached out to over it. After that, everyone started copying the idea - so I kept building. Grok Bot Wall Street: Then took it further and built a real, working case for an actual paying customer: And of course, my own setup for it: Then - the one I'm most proud of. First person to build Grok Bot Second Brain. Biggest, most unique build I've done so far: It picked up real hype - even got covered here: Everything I build, I post the full setup for. Free. Every single time. What should we build next? One dream remains - repost from Elon Musk

Hi, I'm Aleiah - the first real Grok Bot dev. I built the original concept: Grok Bot Office. 1M+ views on it. That post is what started the whole "Grok Bot setup" wave on this platform. First one the SpaceX team actually reached out to over it. After that, everyone started copying the idea - so I kept building. Grok Bot Wall Street: Then took it further and built a real, working case for an actual paying customer: And of course, my own setup for it: Then - the one I'm most proud of. First person to build Grok Bot Second Brain. Biggest, most unique build I've done so far: It picked up real hype - even got covered here: Everything I build, I post the full setup for. Free. Every single time. What should we build next? One dream remains - repost from Elon Musk

Aleiah

47,917 次观看 • 1 个月前

did Cloudflare leave the best for last? guess we'll find out tomorrow agent week is almost over and I am still catching up on all the announcements one thing that i wanted to take for a spin was Computer. you shouldn't need a full on VM container to spin up a git repo and read and edit some files. and if you want to test something in a browser, you can now use Kitesurf having this kind of control when building agent harnesses is very cool, from permission management, separating the brain from the hands and performance gains from isolation, im super stoked for where this goes i wanted to see if i can build a Buzz-like environment using Cloudflare primitives, i called it Cuzz. and being able to observe and debug agent activity locally using Sentry helps make sure i can see not just my agent traces, but errors, logs and traces from the rest of my application what was your favourite announcement from Agent Week?

did Cloudflare leave the best for last? guess we'll find out tomorrow agent week is almost over and I am still catching up on all the announcements one thing that i wanted to take for a spin was Computer. you shouldn't need a full on VM container to spin up a git repo and read and edit some files. and if you want to test something in a browser, you can now use Kitesurf having this kind of control when building agent harnesses is very cool, from permission management, separating the brain from the hands and performance gains from isolation, im super stoked for where this goes i wanted to see if i can build a Buzz-like environment using Cloudflare primitives, i called it Cuzz. and being able to observe and debug agent activity locally using Sentry helps make sure i can see not just my agent traces, but errors, logs and traces from the rest of my application what was your favourite announcement from Agent Week?

Serge

14,865 次观看 • 2 个月前

OH F*CK, I RAN AN ENTIRE OPERATION OFF ONE $40 SEAT! grok bot, xai's agents each with own always-on computer in the cloud, a browser and a terminal, signed into my real tools i gave six of them job titles instead of prompts research > drafting > outreach > ops > finance > support, one narrow charter each nothing overlapping i showed one of them a task once while it watched it's own screen it saved the whole flow as a named skill and now fires it the moment a matching email lands / no plugin for a tool? the bot drives it's own browser until it hits a login wall, hands me the screen, then resumes in that session, so it holds a session and never a password / xai, aug 21: grok bot now ships with all supergrok plus, cursor pro + and cursor teams plans / cursor's own pricing page lists team at $40 / user / mo, with "access to grok bot" on both team tiers / cursor pro at $20 still doen't get it pro+ is where the individual floor moved to

OH F*CK, I RAN AN ENTIRE OPERATION OFF ONE $40 SEAT! grok bot, xai's agents each with own always-on computer in the cloud, a browser and a terminal, signed into my real tools i gave six of them job titles instead of prompts research > drafting > outreach > ops > finance > support, one narrow charter each nothing overlapping i showed one of them a task once while it watched it's own screen it saved the whole flow as a named skill and now fires it the moment a matching email lands / no plugin for a tool? the bot drives it's own browser until it hits a login wall, hands me the screen, then resumes in that session, so it holds a session and never a password / xai, aug 21: grok bot now ships with all supergrok plus, cursor pro + and cursor teams plans / cursor's own pricing page lists team at $40 / user / mo, with "access to grok bot" on both team tiers / cursor pro at $20 still doen't get it pro+ is where the individual floor moved to

dunik

11,528 次观看 • 1 个月前

I dug into Pi because the greatest projects are usually built on top of one very simple building block. 𝗣𝗶 𝗵𝗮𝘀 𝟳𝟳,𝟬𝟬𝟬 𝗚𝗶𝘁𝗛𝘂𝗯 𝘀𝘁𝗮𝗿𝘀 𝗮𝗻𝗱 𝗲𝘅𝗮𝗰𝘁𝗹𝘆 𝗳𝗼𝘂𝗿 𝘁𝗼𝗼𝗹𝘀: 𝗿𝗲𝗮𝗱, 𝘄𝗿𝗶𝘁𝗲, 𝗲𝗱𝗶𝘁, 𝗯𝗮𝘀𝗵. 𝗦𝘂𝗽𝗲𝗿 𝘀𝗶𝗺𝗽𝗹𝗲. No MCP, no sub agents, no plan mode, no to-dos, no permission popups. Their site has a whole section called "what we did not build." So here's the whole logic by Mario Zechner: prompt in → agents.md + system prompt become one forkable JSON → loop starts → read / write / edit / bash → session saved as a tree → loop ends agent-loop.ts has only 792 lines. I think it's beautiful. Initially I was wondering if it's gonna be a little bit too basic. And yes out of the box it's weaker than Claude Code. But skipping MCP isn't purity, it's a context budget. One MCP can sit tens of thousands of tokens in your window every single turn, for a tool you use maybe 10% of the time. Pi moves that weight from always on to on demand. A skill is just markdown. An extension is one .ts file. A package ships both. I ran it in the terminal, then again as a coding sub agent inside my own harness Waku-Agent ( through a delegate_task tool. Same binary both times. You're paying setup time for a harness that stays yours. Full 22 min breakdown in the comments. Save the diagram 🔖 You Can Build Anything. You Can Learn Anything. 💪

I dug into Pi because the greatest projects are usually built on top of one very simple building block. 𝗣𝗶 𝗵𝗮𝘀 𝟳𝟳,𝟬𝟬𝟬 𝗚𝗶𝘁𝗛𝘂𝗯 𝘀𝘁𝗮𝗿𝘀 𝗮𝗻𝗱 𝗲𝘅𝗮𝗰𝘁𝗹𝘆 𝗳𝗼𝘂𝗿 𝘁𝗼𝗼𝗹𝘀: 𝗿𝗲𝗮𝗱, 𝘄𝗿𝗶𝘁𝗲, 𝗲𝗱𝗶𝘁, 𝗯𝗮𝘀𝗵. 𝗦𝘂𝗽𝗲𝗿 𝘀𝗶𝗺𝗽𝗹𝗲. No MCP, no sub agents, no plan mode, no to-dos, no permission popups. Their site has a whole section called "what we did not build." So here's the whole logic by Mario Zechner: prompt in → agents.md + system prompt become one forkable JSON → loop starts → read / write / edit / bash → session saved as a tree → loop ends agent-loop.ts has only 792 lines. I think it's beautiful. Initially I was wondering if it's gonna be a little bit too basic. And yes out of the box it's weaker than Claude Code. But skipping MCP isn't purity, it's a context budget. One MCP can sit tens of thousands of tokens in your window every single turn, for a tool you use maybe 10% of the time. Pi moves that weight from always on to on demand. A skill is just markdown. An extension is one .ts file. A package ships both. I ran it in the terminal, then again as a coding sub agent inside my own harness Waku-Agent ( through a delegate_task tool. Same binary both times. You're paying setup time for a harness that stays yours. Full 22 min breakdown in the comments. Save the diagram 🔖 You Can Build Anything. You Can Learn Anything. 💪

Shen Sean Chen

59,186 次观看 • 2 个月前

Three skills I use every day in Claude Code and Codex to solve my hardest problems: 1️⃣ /agent-watchdog When I have one agent like Codex working on a task and I don't fully trust it's going to do everything right, I'll open up another one like Claude Code and tell it to watchdog the Codex thread. You can copy the Codex deep link into Claude Code and it'll look at the prompt you sent, watch the Codex thread until it's done, then compare the Codex solution to how it was planning to solve it and automatically fix anything that Codex missed. It can also test the work of the other agent end-to-end. Similar to the idea of OpenRouter's new Fusion feature, I've definitely found that two models thinking through a problem and checking each other's work can be wildly more impactful than just one. 2️⃣ /plan-arbiter Similar ideas as /agent-watchdog - but with this one you have both make plans, compare plans, negotiate the differences, and make a final plan to execute. I find Claude Code is better at writing plans, but Codex is faster and cheaper to execute on them. Then I usually have Claude Code watchdog the Codex work and fix anything that was missed. 3️⃣ /read-the-damn-docs One thing that drives me crazy with coding agents is they're so reluctant to look up docs. They'll just guess and guess and guess at the right API surface for things, or the right solution to an integration of two things. Once I explicitly tell it to look up the docs, it says "Oh, I see the answer," and it fixes the problem. So I made the /read-the-damn-docs skill. Add it and your agents will know when and how to do efficient web searches to look up docs for the types of problems you really should look up docs for. All of these are totally open source over on my GitHub. If you try them, let me know your feedback. Will link to them below:

Three skills I use every day in Claude Code and Codex to solve my hardest problems: 1️⃣ /agent-watchdog When I have one agent like Codex working on a task and I don't fully trust it's going to do everything right, I'll open up another one like Claude Code and tell it to watchdog the Codex thread. You can copy the Codex deep link into Claude Code and it'll look at the prompt you sent, watch the Codex thread until it's done, then compare the Codex solution to how it was planning to solve it and automatically fix anything that Codex missed. It can also test the work of the other agent end-to-end. Similar to the idea of OpenRouter's new Fusion feature, I've definitely found that two models thinking through a problem and checking each other's work can be wildly more impactful than just one. 2️⃣ /plan-arbiter Similar ideas as /agent-watchdog - but with this one you have both make plans, compare plans, negotiate the differences, and make a final plan to execute. I find Claude Code is better at writing plans, but Codex is faster and cheaper to execute on them. Then I usually have Claude Code watchdog the Codex work and fix anything that was missed. 3️⃣ /read-the-damn-docs One thing that drives me crazy with coding agents is they're so reluctant to look up docs. They'll just guess and guess and guess at the right API surface for things, or the right solution to an integration of two things. Once I explicitly tell it to look up the docs, it says "Oh, I see the answer," and it fixes the problem. So I made the /read-the-damn-docs skill. Add it and your agents will know when and how to do efficient web searches to look up docs for the types of problems you really should look up docs for. All of these are totally open source over on my GitHub. If you try them, let me know your feedback. Will link to them below:

Steve (Builder.io)

43,089 次观看 • 3 个月前

SpaceXAI engineer just dropped 1-hour Grok Bot workshop: 1 prompt → CEO bot → agent teams → 100% of daily and business tasks from 0% to 100%: 0% → 3:30 - build your first Grok Bot 25% → 6:52 - give every Bot a role 50% → 16:51 - give bots tools and context 75% → 31:50 - run agent teams in parallel 100% → 52:18 - full system that automate business and life most courses just tell you what Grok Bot is - but this is a real case study from an engineer on the SpaceXAI team who automated her life - and you can do the same watch it, build your first CEO Bot, turn it into a team - then read the full Grok Bot workflow below ↓

SpaceXAI engineer just dropped 1-hour Grok Bot workshop: 1 prompt → CEO bot → agent teams → 100% of daily and business tasks from 0% to 100%: 0% → 3:30 - build your first Grok Bot 25% → 6:52 - give every Bot a role 50% → 16:51 - give bots tools and context 75% → 31:50 - run agent teams in parallel 100% → 52:18 - full system that automate business and life most courses just tell you what Grok Bot is - but this is a real case study from an engineer on the SpaceXAI team who automated her life - and you can do the same watch it, build your first CEO Bot, turn it into a team - then read the full Grok Bot workflow below ↓

codila

108,984 次观看 • 1 个月前

most agent memory is one file that grows forever and gets re-read every single turn. it overflows the context, overwrites old facts, loses the thread. that's why your agent feels sharp on day one and lost by week three. Sibyl Memory replaces the pile with a structure: → leaner context, lower token cost. a bloated agent file and flat memory get re-read in full every message. Sibyl Memory keeps a light hot layer and retrieves the rest on demand, so each turn carries only the tokens that matter. → relations are first-class. people link to projects, projects to deals, deals to the decisions behind them. ask about one partner and the agent surfaces the whole connected web around them. that relational context is what lets it help run a company. → one source of truth per fact, person, and project. no duplicates, no silent overwrites. works with hermes, claude code, and codex. beta open.

most agent memory is one file that grows forever and gets re-read every single turn. it overflows the context, overwrites old facts, loses the thread. that's why your agent feels sharp on day one and lost by week three. Sibyl Memory replaces the pile with a structure: → leaner context, lower token cost. a bloated agent file and flat memory get re-read in full every message. Sibyl Memory keeps a light hot layer and retrieves the rest on demand, so each turn carries only the tokens that matter. → relations are first-class. people link to projects, projects to deals, deals to the decisions behind them. ask about one partner and the agent surfaces the whole connected web around them. that relational context is what lets it help run a company. → one source of truth per fact, person, and project. no duplicates, no silent overwrites. works with hermes, claude code, and codex. beta open.

SIBYL

88,308 次观看 • 4 个月前

Grok Bot is not one AI. It is a company that hires and fires itself while you sleep, and mine made $2,900 overnight. You never talk to the workers. You talk to one agent, that agent hires ten, and those ten hire a hundred. By the time you read one answer, dozens of them have existed and been shut down. Nobody named them. Nobody ever will. BlackRock needs 20,000 people and a risk system watching trillions. I pay $300 a month and I named the boss myself. I handed mine $1,000. 15 hours later it was holding $3,900, and I slept through most of it. A new kind of company, and it fits on your phone. The whole build is in the post below ↓ Save it, because the next time somebody tells you AI is just a chatbot, this is the post you send them.

Grok Bot is not one AI. It is a company that hires and fires itself while you sleep, and mine made $2,900 overnight. You never talk to the workers. You talk to one agent, that agent hires ten, and those ten hire a hundred. By the time you read one answer, dozens of them have existed and been shut down. Nobody named them. Nobody ever will. BlackRock needs 20,000 people and a risk system watching trillions. I pay $300 a month and I named the boss myself. I handed mine $1,000. 15 hours later it was holding $3,900, and I slept through most of it. A new kind of company, and it fits on your phone. The whole build is in the post below ↓ Save it, because the next time somebody tells you AI is just a chatbot, this is the post you send them.

cvxv666

55,011 次观看 • 1 个月前

GUYS, STOP F*CKING SLEEPING ON GROK BOT I BUILT A FULL ZERO-SALARY AI ENGINEERING TEAM INSIDE A GROK BOT OVERNIGHT Architect ➜ Harness ➜ Memory ➜ Critic ➜ Implementer ➜ Deployer ➜ Chief of Staff Chief owns the final yes Everything irreversible lands in my approval tray first > Architect ➜ Designs the full system architecture and role structure > Harness ➜ Builds evaluation loops, self-tuning and test harnesses > Memory ➜ Owns persistent memory, retrieval and lifelong context > Critic ➜ Finds real failure modes, runs adversarial tests and edge cases > Implementer ➜ Writes the actual prompts, code and routines > Deployer ➜ Ships live, monitors and runs overnight > Chief of Staff ➜ Only point of contact. Routes all work and holds the approval queue I only talk to Chief The rest hand work forward and keep their own memory I wake up to a sorted queue Read the evidence Hit yes or no One human Six specialists Full engineering floor running 24/7 This is GROK FORGE Read the article if you want to do the same ⭣

GUYS, STOP F*CKING SLEEPING ON GROK BOT I BUILT A FULL ZERO-SALARY AI ENGINEERING TEAM INSIDE A GROK BOT OVERNIGHT Architect ➜ Harness ➜ Memory ➜ Critic ➜ Implementer ➜ Deployer ➜ Chief of Staff Chief owns the final yes Everything irreversible lands in my approval tray first > Architect ➜ Designs the full system architecture and role structure > Harness ➜ Builds evaluation loops, self-tuning and test harnesses > Memory ➜ Owns persistent memory, retrieval and lifelong context > Critic ➜ Finds real failure modes, runs adversarial tests and edge cases > Implementer ➜ Writes the actual prompts, code and routines > Deployer ➜ Ships live, monitors and runs overnight > Chief of Staff ➜ Only point of contact. Routes all work and holds the approval queue I only talk to Chief The rest hand work forward and keep their own memory I wake up to a sorted queue Read the evidence Hit yes or no One human Six specialists Full engineering floor running 24/7 This is GROK FORGE Read the article if you want to do the same ⭣

beamnxw ./

16,914 次观看 • 1 个月前

Cursor engineer lauren reveals the original inspiration for Grok Bot was her internal Slack bot called Benny that would automatically fix bug reports for Cursor while she slept: "I built this bot called Benny. I'm a fairly lazy person, and we were getting so many bug reports for Cursor, and I wanted to just fix them all." "I started thinking about how would I make it so my agents could just automatically fix bugs for me while I sleep? That was the inspiration for some of our earlier experiments with building a more persistent bot." "I got so many questions like how did you build Benny? How can I build my own? That inspired some of the thinking behind Grok Bot. What if everybody could define one of their own bots, give it an identity, and give it things like its own computer, plus routines and automations." "I have bots right now that every time someone gives us feedback on Grok Bot, my bots are automatically going off and fixing them for me, and I just review their code." Grok Bot Cursor

Cursor engineer lauren reveals the original inspiration for Grok Bot was her internal Slack bot called Benny that would automatically fix bug reports for Cursor while she slept: "I built this bot called Benny. I'm a fairly lazy person, and we were getting so many bug reports for Cursor, and I wanted to just fix them all." "I started thinking about how would I make it so my agents could just automatically fix bugs for me while I sleep? That was the inspiration for some of our earlier experiments with building a more persistent bot." "I got so many questions like how did you build Benny? How can I build my own? That inspired some of the thinking behind Grok Bot. What if everybody could define one of their own bots, give it an identity, and give it things like its own computer, plus routines and automations." "I have bots right now that every time someone gives us feedback on Grok Bot, my bots are automatically going off and fixing them for me, and I just review their code." Grok Bot Cursor

MTS

95,510 次观看 • 1 个月前

For the first time, anyone with a Facebook account has a personal AI agent. Meta just launched Muse. It's the #1 app on the App Store. And it's free. This is a big deal. Agents used to be a power-user thing. You had to be technical to set one up, and you had to pay for it. Now billions of people can sign in with the Facebook account they already have and get an assistant that goes and does things for them. And because it's tied to Facebook and Instagram, it already knows a good bit about you on day one. I've been using it for the past two weeks, and it's become part of my day. It's proactive. It helps me keep track of chats and messages I need to get back to, so nothing slips. And I even have it running on my own device now through the Muse SDK (link in the comments). So all of a sudden this free "little" agent is on every device I own, with one super agent, Carl, helping me at every step of the way. Man, it feels like the movies. I recorded a full walkthrough, beginner to pro: Let's dive in. ⏱️ Timestamps: 00:00 What Meta Muse Can Do 00:36 Download Muse on Every Device 01:01 Main Chat and Side Chats 01:53 The Activity Feed 02:28 Soul and Memory Files 04:27 Heartbeat and Morning Brief 05:04 Connect Your Calendar 05:40 Muse's Own Browser and Computer 06:36 Your Personalized Feed 07:57 Ideas Tab and the Calling Agent 08:59 Create Your Muse Avatar 09:42 Run Multiple Agents at Once 10:26 Artifacts: A Family Calendar 12:07 Facebook and Instagram Updates 12:50 AI Tesla Car Search 13:50 Fill Out a School Form 15:46 Book a Dinner Reservation 17:58 Why Muse Works for Everyday Users 18:54 Muse vs Grok Bot Bot vs OpenClaw🦞 20:33 Muse Can Make Phone Calls 21:26 Is Meta Muse Free? 21:49 Computer Control and Its Own Email 22:27 The Muse Charm and Video Chat 23:27 Final Thoughts Great work Alexandr Wang and team!

JJ Englert

66,616 次观看 • 3 天前

Jamie Dimon made $39 million last year to decide who does what at JPMorgan. One AI agent on Grok Bot does that job for $300 a month, and it hires the rest of the agents itself. Stop trying to manage any of it yourself. In 2026 a swarm of AI agents runs a team better than you do. I told my chief agent one thing. Make money or I switch you off. It took $1,000 to $3,900 in 15 hours. Every fill is on chain and the address is in my profile. I never picked a trade. I never picked a team either. The agents it hired: > a scout that hunts for what is moving and where the money is going > a forensics agent that works out who is really behind the buying > a reader that watches the mood on X, and it sees every post on this app because it is Grok > a risk agent whose only power is saying no, and its no beats every score on the desk > a treasurer that holds the money rules and the kill switch > a trader that writes the exit before it writes the entry None of those were my idea. I handed out one job title and the chief filled in the rest on its own. And the swarm is different every hour. Agents appear for one job, do it, and are gone before I know they existed. A hedge fund pays millions a year for the same org chart, and almost all of that goes on salaries. Every prompt and the whole story of my Grok Bot fund is in the post below ↓ Save it before you try to run one of these by hand.

cvxv666

28,886 次观看 • 1 个月前

You probably don’t use just one AI agent anymore. Maybe Codex for coding. Claude Code for research. Cursor for quick edits. Hermes for the rest. Each one is great at something different. But every time you switch, you have to start over — re-explaining your project, preferences, and the way you like to work. Your agents know how to help you. They just don’t share a memory of you. memU just shipped an update that fixes this. One personal memory, shared across every agent and device you use. What Codex learned last night, Claude Code can remember this morning. 🧵

You probably don’t use just one AI agent anymore. Maybe Codex for coding. Claude Code for research. Cursor for quick edits. Hermes for the rest. Each one is great at something different. But every time you switch, you have to start over — re-explaining your project, preferences, and the way you like to work. Your agents know how to help you. They just don’t share a memory of you. memU just shipped an update that fixes this. One personal memory, shared across every agent and device you use. What Codex learned last night, Claude Code can remember this morning. 🧵

Hasan

50,678 次观看 • 2 个月前

ran Grok Bot and Hermes Agent side by side for the same job here's what actually separates them Grok Bot: - gets its own cloud computer, browser, files, terminal, logs into your tools with your credentials - learns by demonstration, record a task once, it saves the routine - runs on Grok, you don't choose the model - all your bots share the same cloud computer and the same logins, no isolation between them - scales by subscription, ~$200/mo solo, ~$120/seat for teams Hermes Agent: - open source, MIT-licensed, no cloud, you host it - each agent gets its own real badge from your identity provider, scoped access only, revoke it and it's gone - brain is swappable, change one config line to switch models - scales by spinning up containers on demand, hire/fire based on backlog - you own the maintenance, an upstream installer change broke one build, one line fix, one morning lost the real fork isn't features, it's where the work happens and who's accountable when it breaks grok bot: convenience, zero setup, but your data sits on their machine and every bot shares every login hermes: more setup, but scoped access, swappable models, and nothing running outside your own network for anything touching regulated or sensitive data, that architecture difference is the whole decision

ran Grok Bot and Hermes Agent side by side for the same job here's what actually separates them Grok Bot: - gets its own cloud computer, browser, files, terminal, logs into your tools with your credentials - learns by demonstration, record a task once, it saves the routine - runs on Grok, you don't choose the model - all your bots share the same cloud computer and the same logins, no isolation between them - scales by subscription, ~$200/mo solo, ~$120/seat for teams Hermes Agent: - open source, MIT-licensed, no cloud, you host it - each agent gets its own real badge from your identity provider, scoped access only, revoke it and it's gone - brain is swappable, change one config line to switch models - scales by spinning up containers on demand, hire/fire based on backlog - you own the maintenance, an upstream installer change broke one build, one line fix, one morning lost the real fork isn't features, it's where the work happens and who's accountable when it breaks grok bot: convenience, zero setup, but your data sits on their machine and every bot shares every login hermes: more setup, but scoped access, swappable models, and nothing running outside your own network for anything touching regulated or sensitive data, that architecture difference is the whole decision

rewind

31,568 次观看 • 1 个月前

grok bot is incredible it literally learned how to manufacture employees for me to sell i turned it into a small AI agent factory: a company comes in with a problem, and walks out with a ready-made digital worker built for its business instead of one AI, i built four assistants: - Hermes breaks down the client’s business and finds the work that makes the most sense to hand over to AI - Hephaestus builds the agent itself, its skills, memory, and workflows - Cerberus checks errors, limits, and every place where a human still needs to step in - Midas turns the finished system into an offer the client can actually buy the first client was a small real estate agency. their managers were wasting hours on hundreds of new leads, checking people manually, and constantly losing the hottest prospects using grok bot, my team built them a dedicated worker that sorts new leads, gathers client information, ranks priority, and prepares the next step for the manager the whole thing took less than an hour to build i sold the setup for $1,200 then came an online store. then a small studio. then two more agencies in one week, the same factory built 8 different AI employees and brought in $9,600 that’s what i like most about grok bot i’m not selling my time anymore i build the system once, and it keeps producing new digital workers again and again in the article below, i broke down the whole path from your first agent to a team like this step by step

grok bot is incredible it literally learned how to manufacture employees for me to sell i turned it into a small AI agent factory: a company comes in with a problem, and walks out with a ready-made digital worker built for its business instead of one AI, i built four assistants: - Hermes breaks down the client’s business and finds the work that makes the most sense to hand over to AI - Hephaestus builds the agent itself, its skills, memory, and workflows - Cerberus checks errors, limits, and every place where a human still needs to step in - Midas turns the finished system into an offer the client can actually buy the first client was a small real estate agency. their managers were wasting hours on hundreds of new leads, checking people manually, and constantly losing the hottest prospects using grok bot, my team built them a dedicated worker that sorts new leads, gathers client information, ranks priority, and prepares the next step for the manager the whole thing took less than an hour to build i sold the setup for $1,200 then came an online store. then a small studio. then two more agencies in one week, the same factory built 8 different AI employees and brought in $9,600 that’s what i like most about grok bot i’m not selling my time anymore i build the system once, and it keeps producing new digital workers again and again in the article below, i broke down the whole path from your first agent to a team like this step by step

Mikadzyki🌙

14,989 次观看 • 1 个月前

I'M A F*CKING GENIUS - I WAS THE FIRST TO BUILD THIS WITH GROK BOT. And now? My idea is everywhere. Scroll your feed. You've seen it. The screenshots. The "digital office" carousels. The threads explaining it like they invented it. Every single one of them is running my playbook - and half of them don't even know where they got it from. I BUILT MY OWN OFFICE. AND GROK BOT IS THE BOSS. Just look at what my workplace looks like now. Before, AI sat there waiting. Waiting for me to open a chat. Waiting for a prompt. A very expensive parrot. Now I run a real digital office. Persistent agents with actual roles. A shared cloud computer, browser, and terminal. They keep working 24/7 - laptop closed, me asleep, doesn't matter. The office never shuts down. And here's the part that broke people's brains: it's easy. Download the app → sign in → create the "Chief" → give them job titles (exactly like briefing new hires) → show a task once → connect Telegram. → No experience needed. → No VPS. → No coding. → Nothing complicated. At all. I drop a goal into Telegram. The bots break it down, delegate it, and deliver it. I just make the decisions. That's the whole job now. Grok Bot isn't a chatbot. It's a team - one you can build in a single evening, even if you've never touched an agent in your life. So yeah. My content is everywhere. The recognition I actually earned? Still nowhere. Copy it again. I'll build the next one before you finish reading.

I'M A F*CKING GENIUS - I WAS THE FIRST TO BUILD THIS WITH GROK BOT. And now? My idea is everywhere. Scroll your feed. You've seen it. The screenshots. The "digital office" carousels. The threads explaining it like they invented it. Every single one of them is running my playbook - and half of them don't even know where they got it from. I BUILT MY OWN OFFICE. AND GROK BOT IS THE BOSS. Just look at what my workplace looks like now. Before, AI sat there waiting. Waiting for me to open a chat. Waiting for a prompt. A very expensive parrot. Now I run a real digital office. Persistent agents with actual roles. A shared cloud computer, browser, and terminal. They keep working 24/7 - laptop closed, me asleep, doesn't matter. The office never shuts down. And here's the part that broke people's brains: it's easy. Download the app → sign in → create the "Chief" → give them job titles (exactly like briefing new hires) → show a task once → connect Telegram. → No experience needed. → No VPS. → No coding. → Nothing complicated. At all. I drop a goal into Telegram. The bots break it down, delegate it, and deliver it. I just make the decisions. That's the whole job now. Grok Bot isn't a chatbot. It's a team - one you can build in a single evening, even if you've never touched an agent in your life. So yeah. My content is everywhere. The recognition I actually earned? Still nowhere. Copy it again. I'll build the next one before you finish reading.

Aleiah

11,604 次观看 • 1 个月前

HERMES AGENT VS OPENCLAW. a local ai onboarding flow test. a 3.9gb bonsai served on localhost, both agents upstream and latest, i point each one at the endpoint and watch which one even finds it. > hermes opens a provider menu, thirty plus options, local servers sitting right there next to the cloud ones, i hand it 127.0.0.1:8899, it verifies the endpoint, one model visible, auto-detects the model by name, bonsai-27b-q1_0, reads the context length straight off the server, saves it, and starts reasoning and firing real tool calls on my local model. no key. no friction. > openclaw has no menu. it goes hunting for a codex login, an openai key, finds none because there are none, prints no models available three times, defaults to openai/gpt-5.5, a cloud model it cannot reach, and dead ends on run auth login --provider openai. read that back. it asked me for an openai key. to run a model already running on my own machine. it never once looked at localhost. to be fair, openclaw can run local if you hand wire endpoint yourself. what it will not do is find the model already sitting on your box. hermes agent found it in one line. now the part i owe you. the auto-detect that just won, the model name read, the .gguf strip, the context length probe off the server, that is my code, it is in hermes agent main right now, authorship preserved, #2051 and #4218. the wizard fix that stops an agent from silently routing you to someone else's creds, the exact trap openclaw still falls into, mine too, #4210. i contribute to hermes agent, i told you that going in. one agent is built to talk to whatever you are running, the other is built to talk to a cloud api, so one found my model and ran it and the other asked me to log into openai. onboarding flow of both, mapped, below.

HERMES AGENT VS OPENCLAW. a local ai onboarding flow test. a 3.9gb bonsai served on localhost, both agents upstream and latest, i point each one at the endpoint and watch which one even finds it. > hermes opens a provider menu, thirty plus options, local servers sitting right there next to the cloud ones, i hand it 127.0.0.1:8899, it verifies the endpoint, one model visible, auto-detects the model by name, bonsai-27b-q1_0, reads the context length straight off the server, saves it, and starts reasoning and firing real tool calls on my local model. no key. no friction. > openclaw has no menu. it goes hunting for a codex login, an openai key, finds none because there are none, prints no models available three times, defaults to openai/gpt-5.5, a cloud model it cannot reach, and dead ends on run auth login --provider openai. read that back. it asked me for an openai key. to run a model already running on my own machine. it never once looked at localhost. to be fair, openclaw can run local if you hand wire endpoint yourself. what it will not do is find the model already sitting on your box. hermes agent found it in one line. now the part i owe you. the auto-detect that just won, the model name read, the .gguf strip, the context length probe off the server, that is my code, it is in hermes agent main right now, authorship preserved, #2051 and #4218. the wizard fix that stops an agent from silently routing you to someone else's creds, the exact trap openclaw still falls into, mine too, #4210. i contribute to hermes agent, i told you that going in. one agent is built to talk to whatever you are running, the other is built to talk to a cloud api, so one found my model and ran it and the other asked me to log into openai. onboarding flow of both, mapped, below.

Sudo su

23,816 次观看 • 2 个月前