Claude Agent OS is INSANE! 🤯
Julian presents a comprehensive Claude-based agent operating system that integrates multiple AI models, automated workflows, and a persistent memory system to automate daily tasks. The system runs 24/7 and uses free or existing subscriptions, combining tools like voice agents, content creation, competitor monitoring, and real-time news analysis into a single unified dashboard.
Summary
Julian demonstrates an AI agent operating system built entirely with Claude that orchestrates multiple AI agents (Hermes, Claude, Anti-gravity, DeepSeek) working together in the background. The system uses Obsidian as a free, open-source memory management layer that automatically captures notes, links context, and builds a knowledge graph accessible to all agents. When new models like Claude Opus 5 or DeepSeek are released, they can be instantly integrated without retraining or breaking existing automations. The platform includes specialized agents: Hermes Oracle pulls trending news every 24 hours and auto-generates social media and SEO content; Hermes Astros monitors competitors and keywords to provide six personalized content ideas daily; a voice agent (Hermes Apollo) provides real-time Jarvis-like interactions with wake-word activation; and a video agent automates full video production with AI avatars, B-roll, voiceovers, and editing. The system features a mission control dashboard showing agent status, goal tracking, and history logs. Julian emphasizes that this requires no additional cost beyond existing subscriptions (can use free APIs and CLIs), is non-technical to set up and use, and is customizable to individual workflows. He spends 3-4 hours daily improving it and shares iterations with the AI Profit Blueprint community, which offers weekly coaching calls, step-by-step tutorials, and a local meetup map for members.
Key Insights
- Julian claims the system doesn't fall behind on new models because it's designed so that whenever a new model comes out, it can be instantly swapped in without breaking existing automations, unlike traditional setups that require retraining or reprompting.
- The entire operating system was built with Claude using existing subscriptions, meaning users can implement it at zero additional cost by plugging in free APIs, CLIs, and open-source tools they already use.
- Julian identifies the core value of the system as automating anything repeatable in one's day-to-day work, rather than treating it as a general-purpose tool, by timing tasks and creating a list of which workflows recur.
- The Hermes Oracle agent runs a 24-hour cycle to pull trending news and automatically generate both social media and SEO content options with a single click, eliminating the need to manually research industry trends.
- Julian emphasizes that the system is designed for non-technical users and cites over 207 pages of testimonials from community members who have successfully built and deployed their own versions without HTML or coding knowledge.
Topics
Transcript
[0:00] This new Claude agent operating system is the most powerful thing we've ever built. So, this is a system where I have all of our AI agents working together. So, you can see for example, we have Hermes, we have Claude, we have anti-gravity. And this is all running 24/7 in the background whilst I would I do other things. So, what this actually does is it links to our memory system here, which means anytime a new model comes out, we don't fall behind, we don't have to retrain it, we don't have to plug in new prompts. It's already got all of our context preloaded in this [0:30] free system, which is basically Obsidian. Now, also, when…
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.