User
Write something
Hermes Agent on Orgo - Practical Guide
Hey guys, I've decided to launch a mini course on deploying a Hermes Agent on Orgo and configuring it for a client, including a step-by-step checklist with copy/paste commands. Wanted to offer it for free to you guys for feedback/testimonials. Please let me know if you're interested!
I cloned Grok Bot in an afternoon.
Here's the full stack (and the business hiding inside it) Last week Grok Bot cut everyone's usage limits. I run 8 bots on it. A chief of staff, a Skool moderator, a Slack drafter, a YouTube comment bot, a Bookface outreach bot, and a few more. Overnight, all of them were rationed. So instead of waiting for xAI to fix it, I tried something different: I had my agents reverse engineer Grok Bot and build me my own. It worked. I recorded the whole thing, every prompt, start to finish. Video is below. Here's the breakdown. What actually happened 1. The design. I pointed Claude Opus 5.5 at the real Grok Bot app on my Mac and told it to click through every screen with computer use, then rebuild it in Paper MCP. About 30 minutes later I had a near pixel-perfect replica: same screens, same icons, same layout. 2. The backend. In parallel, a second agent ran the Reverse Engineer Anything repo (443K stars on GitHub) on a Linux cloud computer and mapped how Grok Bot works: the bots, the API, the interface. 3. The build. The build agent read the design thread, read the architecture, and built it. A couple of hours from my first prompt, I had a working clone. Google sign-in, Grok 4.7 behind every bot, app connectors, routines, and each bot on its own cloud computer that I can take over and control. While all that ran, a third agent on a GPU box edited the video you're about to watch. My MacBook never got warm. The stack - T3 Code: where the agents live. One workspace running Claude and Codex across 5 machines: my MacBook plus Linux, GPU, Mac mini and Windows cloud computers. - Reverse Engineer Anything: maps how an existing app works. - Paper MCP: design tool for agents. This is what nailed the UI. - xAI API: the models, voice, image and video, files, X search. Most of what Grok Bot is. - Composio: sign-in and every app connector (Gmail, Slack, all of it). - Orgo: a computer for every bot. (Yes, that's my company. It's also the piece xAI doesn't give you.)
New here, question on Claude subscription
Hey guys! It’s been a while since I’ve been watching your videos, and I’m really happy to finally be part of the community. I’m planning to try your Grok bot clone, but I wanted to check first that I won’t risk getting banned on my monthly subscription by using it. I was using Hermes back in January and got banned from Claude. Just curious what you think about it, and whether they’ve stopped banning people for using tools outside the official harness.
3
0
When does an AI agent become a real system?
I’ve been thinking about this after seeing so many impressive agent builds lately. It’s pretty easy to get excited when an agent can browse, use tools, send messages, update a CRM, or even hand work off to another agent. But I think the interesting part starts after the demo. What happens when the agent makes a mistake? What happens when a client changes something in their process? Where does the context live? Who checks whether the task was actually completed? And if something fails at 2am, does the system recover or does someone get a notification and become the human fallback? That seems to be where the difference between “I built an AI agent” and “I’m running an AI system for a business” starts to show. I’m curious how everyone here is approaching this. At what point do you personally consider an agent production-ready rather than just a really good demo?
The Gap Between Agent Demos and Client Delivery
Watching a computer-use agent click through an interface on video makes automated operations look almost solved. The friction usually starts the moment you try handing that exact workflow over to run reliably inside a messy client setup. Most of the real challenge seems less about setting up the agent logic and more about keeping track of edge cases without sitting there watching it execute. For those running these for real businesses, where does the workflow usually break down first?
1-30 of 154
Agent Empire
skool.com/agentempire
Build, run, and sell managed AI agents for your business or for clients. A free community founded by Nick Vasilescu.
Leaderboard (30-day)
Powered by