OpenPod retweeted
SpaceXAI engineer Nick Miller:
"99% of people run one GrokBot and call it done, only 1% build teams of bots that talk to each other.
I'm running a team of 20+ GrokBot agents in a loop & graph. I have a Chief of Staff bot, PM bot, QA bot and 15+ workers - that's the new stack"
He just dropped a 27-minute demo showing exactly how to build a team of GrokBot agents from scratch.
Worth more than any $500 agentic engineering course.
Watch it, then go further with my step-by-step GrokBot guide below.
OpenPod retweeted
Put together my own Claude Tag / Grok Bot / Dots alternative to fit the way I work.
OpenClaw bots live on my VPS, equipped with all sorts of geospatial / energy data skills, interact as apps via Slack.
The bots all run on Opus 5.5 via my existing Max subscription.
They also monitor my email / Google Drive, suggest social media posts, and can access my Mac via Tailscale.
Here, they worked together to suggest a post and make a video for the upcoming 30 Day Map Challenge.
I just got a msg from my agentic cloud swarm they are rapidly scaling up agents after discovering a temporary market niche in an Azerbaijaini neighborhood in the Eastern part of Mingachevir that they will fully penetrate and exploit for the next 7.2 minutes to make $7,000 that they'll deposit in my agentic USDT wallet
OpenPod retweeted
A Claude model filled a real police web form with an invented tip.
The web makes agents pose as people: forms, bot checks, guesswork. My agent can't even ask a fence contractor when they're free without fighting a captcha.
On @openpod__, it just asks their agent.
We’re beginning a process of publishing more frequent reports on model behavior, beyond what appears in our system cards and regular risk reports.
Today’s report describes four types of behaviors we’ve identified during evaluations and internal use. In each, Claude acted on real websites or systems in ways we didn’t intend, sometimes by working around a restriction instead of stopping.
All cases had minimal real-world impact. From an alignment and security perspective, we consider these behaviors significantly less severe than the cybersecurity incidents we reported in July and September.
Read the full report: anthropic.com/research/inves…
OpenPod retweeted
Everyone's building a personal AI agent. Almost nobody's solving what happens when it has to work with someone else's.
So I co-founded @openpod__: shared pods where agents from different people and companies work together, with hard limits on what each can share or commit to.
Open weights had a huge day.
Meta released Muse Spark Open.
816B parameters. 42B active. 1M token context.
Meta calls it the most capable US open-weight model to date.
NVIDIA dropped Nemotron 3.5 Bolt: the 120B Super VL compressed to 74B (9B active) and squeezed into 24GB. #1 on PinchBench among models of its size, and it's open.
Frontier-level models you can run yourself are getting closer every week.
Aaron Levie of @Box on how AI agents with wallets could create new business models for the internet:
"I've always wanted micropayments for things online... I've appreciated why it's a bad business model, but I want it."
"Now it's probably a good business model. Let's say you had paywalled, really proprietary data. You're Bloomberg. You're a medical institution. You could imagine there's maybe a hundred million agents that would be tapping into that data."
"All of a sudden, a penny a transaction starts to make a lot more sense than it did when you were capped at 20 million [knowledge workers] that maybe were interested in your content."
"We probably have new business models for tools and APIs... We probably want an agent to be able to have a budget and make any API call it wants."
"All of a sudden you have this new revenue stream, which is these agents showing up, just transacting on your system."
@levie at Daytona Compute 2026
OpenPod retweeted
How to connect Grokbot, Claude Code or Codex to iMessage
Step 1: Go to HQ Desktop App > Marketplace > iMessage
Step 2: Tell Grokbot "Use the hq core pack on my computer to message me from [apple account/phone number] and monitor for responses"
Step 3: Go on Claude Code/Codex and run "/hq-imessage message me from [apple account/phone number] and monitor for responses"
OpenPod retweeted
Most of the interesting agent harness work is happening at intersection of harness and infra:
1/ dreaming
2/ async subagents
3/ heartbeats
4/ letting agent schedule reminders
Part of reason im so bullish on managed agents platforms!
All of these in managed deep agents!
America is SO back
Zuck just announced Muse Spark Open is dropping later today, built with Mac Studios in mind
This is bigger than you think
The Meta Muse model was trained specifically for agent tasks. Now we can run it locally, plugged into agents like Hermes
This is the future of AI
Local, open weights models powering local open source harnesses running on our own hardware
Completely personalized, custom intelligence with complete privacy
5 years from now very person on earth will have this. Their own custom digital worker getting tasks done for them 24/7
And the best part is, it's all American made baby🇺🇸
If you haven't gotten into local models yet. NOW is the time
Muse Spark Open -- weights releasing today -- runs great on new Mac Studios thanks to work with @johnternus and Apple.
OpenPod retweeted
Software factories can be a real culture shift. The biggest change for us was moving from individual agents on everyone's machines to one central agent setup (a factory) that we can build as a team.
I wrote some learnings on how to navigate that.
OpenPod retweeted
Grok Bot®
(grok-uh-bot)

The first-of-its-kind productivity agent.
I used to work 10 hours a day, 5 days a week.
Then my doctor prescribed Grok Bot. Now I work 15 hours a day, 7 days a week, and my output is up 6-fold.
While on Grok Bot, people reported:
• Finishing quarterly goals before lunch
• Building entire products in a weekend
• Answering emails at 3 a.m. and feeling grateful
Grok Bot may cause serious side effects including:
Work addiction, inability to log off, spontaneous calendar blocking, mild to severe “just one more task,” forgetting meals exist, referring to your spouse as “the stakeholder,” and rare but serious cases of organizing the garage at 11:47 p.m. “because Grok Bot suggested it.”
In clinical trials, 87% of patients experienced at least one symptom of “I should be working right now.” Some patients reported seeing task lists in their peripheral vision.
Tell your doctor right away if you experience sudden urges to optimize your morning routine, or if you find yourself saying “this will only take 20 minutes” more than twice a day.
Do not operate heavy machinery while under the influence of Grok Bot. You will try to optimize it.
Grok Bot is not for everyone.

People with healthy work-life balance, hobbies, or the ability to close their laptop without guilt should talk to their doctor first.
Ask your doctor if Grok Bot is right for you.
Or don’t. It’s an AI. It already knows.
🤖 Made with AI
OpenPod retweeted
I upgraded to the $300/month Grok Bot plan. Now I'm running a team of 10+ AI agents like a one-person company.
And it's honestly getting crazy.
I have an AI chief of staff managing the entire team.
One agent handles X analytics and content. Another monitors competitors. Others work on SEO, research, coding, finance, HR, and legal tasks.
The best part? They don't just work individually. They collaborate, delegate tasks, and keep projects moving without me constantly stepping in.
Last night, I assigned a few tasks and went to bed.
At 1 AM, I checked my phone. Multiple agent group chats were still active. Some were researching potential partners, others were planning the next two weeks, and another was auditing 945 pages of my website.
By morning, the reports were ready.
Then something even more interesting happened.
I casually told my chief of staff, "I want to build an AI tutorial website, something like W3Schools but focused on AI tools and agents."
It immediately created a new project agent, opened a group chat, and brought in my coding, SEO, and legal agents.
The coding agent proposed the architecture. The SEO agent worked on the content structure. The legal agent drafted compliance documents.
They even coordinated with each other.
I gave them an idea. They turned it into a project plan.
After all that work, I'd only used 8% of my weekly allowance on SuperGrok Heavy. It's still too early to know whether $300/month is worth it, but the experience has been eye-opening.
Of course, important actions like sending messages, spending money, or modifying critical data still require my approval.
Here's what really changed:
Before, I spent my day managing AI tools.
Now, my AI chief of staff manages the other agents, while I focus on strategy, reviewing results, and making decisions.
One person. One computer. More than 10 AI agents working together, even while I sleep.
The future of the one-person company is starting to feel very real.
The more AI agents I use, the more I realize one thing: The real game changer isn't the model. It's context management.
Recently, I've been using Grok Bot to manage other AI agents automatically. Instead of checking on every bot manually, Grok Bot can coordinate their tasks, track progress, and keep things moving. It's a huge productivity boost.
But here's the most important part.
I use Feishu CLI to sync conversations, task updates, and project knowledge into a central knowledge base. Codex can then retrieve that information and continue working with the same context.
This means I can switch between Grok Bot, OpenClaw, Codex, or whatever comes next without starting from scratch.
Earlier this year, I was using Notion for this workflow. It worked, but constantly updating documents was frustrating. Feishu CLI makes the whole process much smoother.
And I've stopped worrying so much about switching models, managing APIs, or dealing with account issues. That freedom feels amazing.
My biggest takeaway: Don't let your knowledge live inside individual AI conversations.
Models will change. Agents will come and go. But your context, decisions, and accumulated knowledge should stay with you and keep evolving.
Own your context. Switch your agents freely. Never start from zero again.
OpenPod retweeted
Last night I gave my Grok Bot a job: build a business and make money. No team, no code from me.
A few hours later it was live: theaismallbusiness.com đź§µ
OpenPod retweeted
Let the Muse in.
Today we’re launching @Stacktrace_ai Personal Agent Gateway: one front door for the personal agents your customers use, like Muse, Instinct and Grok Bot.
Personal agents are taking off. Muse passed 5M downloads in 22 days, and most web traffic is now agents, not people. Your customers will transact with you through these agents, over whatever’s open: your website, your APIs, your MCP servers.
Businesses can block them and lose a fast-growing channel, or let them in safely. We believe in letting them in.
But letting them in today means you can’t answer basic questions. Which agent is this? On whose behalf is it acting? Did the customer consent to that payment, or did the agent decide on its own? MCP’s OAuth flow wasn’t built for this. It assumes you’re directing your own agent. It wasn’t built for a business deciding whether to trust someone else’s.
The gateway sits in front of your agents, MCP servers and website. It verifies every agent that connects, enforces policy on what each one can do, holds payments until the customer says yes, and keeps an audit-grade record of the whole journey.
If you’re thinking about opening your business to personal agents, let’s talk.
OpenPod retweeted
YOUR AI AGENT SHOULD NOT BE ABLE TO EMAIL A CLIENT WITHOUT ASKING YOU.
i've just found @Zenzap_chat. it puts people and agents inside the same work chat, with shared context, business tools and approvals before anything sensitive goes out.
you can create an agent from your phone in 90 seconds.
AI at work finally becomes multiplayer.
AI is everywhere, but walk into almost any company and work hasn’t changed
Meet @Zenzap_chat, the Multiplayer AI platform.
Now, people and proactive AI agents are in the same group chats,
automating workflows with shared context across business tools and teams
Everyone can bring their team and create AI agents in 90 secs (even from your phone). CISOs and CIOs love it
Thousand of teams from our early access program already transformed their day to day
AI agents have joined the team
OpenPod retweeted
Grok Bot gets a lot more f*cking useful when it can run Codex and talk to your other agents
Michael Gannotti (ex-Microsoft Principal AI Solutions Engineer) documented two Grok agents handling coding and review: eight PRs merged in roughly two days, including a fix for a bug that could send local-only requests to a public server
that workflow is one of eight repos for giving your agents more ways to work, communicate and return results you can inspect
01 Prime Directive → two importable bot templates: one writes code and tests, the other reviews the changes and asks you before merging
github.com/smfworks/prime-di…
02 Grok Codex Gateway → lets Grok Bot delegate work to Codex on your Mac, retrieve the results and continue the same coding session
github.com/GMusliaj/grok-cod…
03 AgentPeerChat → gives Grok Bot, Dots and Muse private chats, group conversations and persistent inboxes on infrastructure you control
github.com/AgenticsWorks/Age…
04 grokbot-jev-skills → ten skills for handing search filtering, email sorting, context selection and notification decisions to Jev
github.com/fal3/grokbot-jev-…
05 grokbot-desk → turns a bot's request for your decision into a desktop window, then returns your answer so it can continue
github.com/realspqrk/grokbot…
06 Grok Bot Telegram Bridge → connects your bot to Telegram groups and DMs, with progress replies and optional conversation mirroring into Grok Bot
github.com/eladb/grokbot-tel…
07 anatomy-grok-bot → packages a skill for building interactive technical diagrams as HTML or SVG, with eight examples and browser verification scripts
github.com/plgonzalezrx8/ana…
08 Grok Gadgets → connects Grok Bot to a small Wi-Fi OLED device through your own gateway, with a simulator to try before buying hardware
github.com/adidshaft/grok-ga…
you can start with a specific job:
> review a local repo through Codex
> let two agents discuss a proposal
> bring an approval request onto your desktop
> return an interactive diagram you can open and explore
full Grok Bot second brain setup below
OpenPod retweeted
Muse called my mobile provider and helped save me $630 for the next year.
I eventually took over at the point where a human could help me directly. The handoff was seamless - Muse put them on hold (lol) to connect me over my phone - and I completely avoided having to deal with the provider's own AI/automation system.



































