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.
Summary
The transcript discusses Hermes Cloud as a cloud-based platform for running AI agents with a free operating system called Agent OS. Unlike local setups that require computers to remain on and consume local resources, Hermes Cloud runs agents continuously in the cloud without user intervention. Three free models are currently available: Solar Pro 4, Matri Longcat 2.0, and Poolside Laguna S 2.1.
The speaker explains that Hermes Cloud solves multiple problems associated with local AI agent deployment: agents no longer require the user's computer to be powered on, they don't slow down local machines, they operate in isolated sandboxes preventing access to personal files, and they can be accessed from multiple devices. Setup is simplified—users perform one-click deployment without managing servers or virtual machines.
The platform integrates with Agent OS through three main modules: Paperclick (for managing agents and tasks), Idea Factory (for automating workflows), and the custom workflows themselves. Key workflows mentioned include Hermes Oracle (tracks trending news), Hermes Muse (generates content ideas), and Hermes Astros (analyzes competitors and identifies content angles). These workflows run continuously without user involvement.
The speaker addresses a specific question about connecting Google Cloud VMs to Agent OS, recommending Hermes Cloud's built-in infrastructure instead. For those preferring on-premises solutions, Tailscale provides secure remote access to locally-running agents. The speaker emphasizes that cloud-based agents work independently during off-hours, progressing on tasks while users sleep, creating an 'AI colleague' rather than just a tool.
Two options are presented: AI Profit Boardroom (paid community with weekly coaching, daily training, and pre-built Agent OS ZIP files) and AI Success Lab (free community with 92,000+ members offering 50+ free AI tools, 200+ SEO prompts, and 1,008 AI workflows).
Key Insights
- Hermes Cloud solves the fundamental problem that most people face with AI agents: local setup limits agents to run only when the user's computer is powered on, slowing down the machine and creating security risks with agent access to real files
- The speaker argues that deploying agents in an isolated sandbox is not just convenient but 'the only way to safely deploy agents' because if an agent malfunctions, its actions remain limited and pose no risk to the user's device
- Cloud-based agents create a fundamental difference in capability: local agents work during user work hours, but cloud agents work independently 24/7, processing content and monitoring tasks while users sleep, transforming an AI tool into an 'AI colleague'
- The free models on Hermes Cloud are interchangeable—if one model is removed or updated, users can simply switch to another (Long Cat or Pool Side) or run multiple cloud profiles simultaneously to test which 'brain' performs best for their tasks
- Hermes Cloud eliminates infrastructure management complexity that local Ollama setups require, such as managing model files and RAM limitations, because free models are hosted on Hermes's infrastructure rather than the user's
Topics
Transcript
[0:00] Hermes Cloud, together with Agent OS, is something incredible, one of the most useful tools for working with AI agents that I have seen. I'll explain in detail how it works, why it's worth using, and how to set everything up yourself step by step. So, what is it about? Hermes Cloud allows you to run a full-fledged AI agent with a free model as the “brain” inside a cloud operating system for agents. No API keys, no local setup issues, and no worries about whether your computer is turned on . The agent runs in the cloud 24/7, even while you sleep. And the top three models on Hermes are now [0:30] completely free. Solar Pro 4, Matri…
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.
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.
How to Run DeepSeek V4 Flash for FREE!
A tutorial demonstrating how to use DeepSeek V4 Flash for free through Open Code and integration with agent operating systems like Hermes Agent. The speaker showcases building websites and apps using this free AI model and explains how it compares favorably to larger models despite being smaller.