Agent OS + Tailscale: FREE AI Everywhere!
The tutorial demonstrates how to use Tailscale to create a private network connecting an AI Agent Operating System across multiple devices, enabling remote access and control from a phone or any device without exposing the system to the internet. The setup takes approximately 10 minutes and requires creating a free Tailscale account, installing the app on devices, and accessing the Agent OS through a private HTTPS address.
Summary
The speaker introduces 'pocket mission control,' a method for accessing an AI Agent Operating System remotely across devices using Tailscale, a free networking application. Tailscale creates a private encrypted network (called a 'tailnet') that connects devices without requiring router configuration, open ports, or domain purchases. The system allows users to check on AI agents, kick off new jobs, and monitor the Kanban board from anywhere—at the gym, coffee shop, or while traveling—while agents continue working 24/7 in the background.
The setup process involves three layers: the station (the local machine running Agent OS), the wire (Tailscale creating the private tunnel), and the access point (the phone or secondary device). The speaker demonstrates using Claude AI to automate the Tailscale setup process, showing how users can request Claude to configure the system by simply logging into login.tailscale.com and retrieving the private HTTPS address. Once installed on both the computer and phone with the same account credentials, users can access the full Agent OS interface on their mobile device.
Key technical advantages highlighted include end-to-end encryption, automatic certificate handling, and the fact that access is restricted to authenticated account holders only. The speaker addresses common concerns: the system doesn't expose anything to the internet since the address exists only within the private Tailnet, setup is straightforward even for non-technical users, and the system provides full Agent OS functionality on mobile devices. The speaker emphasizes they personally prefer running systems locally but acknowledge the frequent demand for mobile access. The tutorial concludes with promotion of the AI Profit Bot Army community, which provides the full Agent OS, comprehensive Tailscale setup instructions, and ongoing support through weekly coaching calls and training resources.
Key Insights
- The speaker claims that Tailscale allows locally-hosted AI systems to be accessed remotely without exposing them to the internet, requiring no router configuration, open ports, or domain purchases, with certificates automatically handled by the service.
- The speaker demonstrates that users can leverage Claude AI itself to automate the Tailscale setup process by simply asking Claude to configure the system, significantly reducing technical complexity.
- The speaker identifies a critical usability requirement that users must toggle the Tailscale switch on when using the system on their phone, and failure to do so prevents connection.
- The speaker argues that the system maintains security through account authentication, as only users logged into the Tailscale account on both devices can access the private HTTPS address, preventing unauthorized access.
- The speaker states that the complete setup process—from account creation to accessing the Agent OS on a phone—takes approximately 10 minutes and requires only basic steps: create a Tailscale account, connect the Agent OS to the tunnel, install Tailscale on the phone, and log in with the same credentials.
Topics
Transcript
[0:00] I'm about to show you how to put your entire AI agent operating system in your pocket using Tailscale. Today, I'll show you how to control your agents from your phone, from the gym, from the coffee shop, from anywhere on the planet. I call it pocket mission control, so your agents can keep working 24/7. And now you can watch them, check on them, and kick off new jobs all from your phone or from another device. And here's the best part, it's free and it's private, and it only takes about 10 minutes to set up. I just set up mine with a couple of prompts. That's it. And stick with me until the end because there's…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Julian Goldie SEO
Google AI Studio Just Got A Huge Security Upgrade
Google is reportedly developing a new "Security Check" mode for AI Studio that would apply secure coding practices to AI-generated applications. The feature aims to automate security verification during app development, addressing common vulnerabilities like exposed keys, weak authentication, and data access issues before deployment.
New Gemini Skills Update Is WILD!
Google has launched Gemini Skills, a new feature allowing users to save custom instructions once and reuse them repeatedly by typing a slash command, replacing the discontinued Gems feature. Skills can include reference files, be combined together, and are built on an open file format (skill.md) that allows portability across different AI tools.
NEW Codex CLI Update Is ABSURD!
OpenAI's new Codex CLI update transforms terminal-based programming assistance by enabling multiple AI agents to work simultaneously on different tasks, visible in a full-screen control center interface. The update includes features like Agent View, work trees, voice control, and parallel task execution, fundamentally changing how AI assistance operates from sequential Q&A to autonomous team-based work management.
NEW Hermes Cloud + Agent OS is Crazy! 🤯
Hermes Cloud combined with Agent OS enables users to deploy AI agents in the cloud 24/7 using free models without API keys or local setup complexity. The system provides persistent memory, sandbox isolation, and integration with custom workflows like content research, competitor analysis, and news monitoring.
Manus 2.0 Just Changed AI Agents Forever
Manas 2.0 represents a fundamental architectural overhaul that enables users to create games, websites, videos, and automations through simple text requests, with the key innovation being editable components rather than fixed outputs. The platform uses a new Cascade engine that reduces token usage by 23% and improves task speed by 28%, while maintaining all project elements in one connected workspace.