AI News Today | Julian Goldie Podcast

Hermes Oracle & Jarvis: One-Click SEO News Posts, Agent OS Updates + Community Wins (FAQs)This episode answers recent FAQs about the Hermes-based Agent Operating System, highlighting Hermes Oracle for pulling trending Twitter news and publishing SEO blog posts to WordPress in one click, plus outreach tools, lead generation, and goal mode. It demos Hermes Jarvis, a voice-activated setup using ChatGPT’s real-time audio API to open websites and apps, with Auto vs Agent mode for speed vs control and adjustable permissions. The video shares community builds including automated image+blog SEO workflows, a multi-layer omni-channel CRM for travel sites and an app, and a Paperclip-orchestrated team of agents using local/free “Claude Code.” It compares learning paths (n8n vs MCP, and Claude/Hermes as no-code workflow builders), shows NotebookLM MCP and Obsidian memory-layer integrations, recommends focusing on one main tool, and points viewers to the AI Profit Boardroom for the latest Agent OS zip, daily updates, tutorials, coaching calls, and community support.00:00 Agent OS Updates Overview00:35 New Models and Agents01:41 Community SEO Automations03:07 n8n vs MCP Guidance04:18 Paperclip Agent Teams06:27 Free Claude Code Setup07:08 Community Wins and Culture08:17 Obsidian and NotebookLM MCP09:48 Model Outages and Switching10:25 Morning Brief Automation12:44 Learning Systems with Anki13:37 Jarvis Voice Control Demo15:06 Stop Tool Hopping16:50 Jarvis Speed Fixes17:31 Wrap Up and Get Agent OS

Hermes Oracle: Automated AI News Research + Obsidian Memory (Sweep, Rank, Angle, Ship)The script introduces Hermes Oracle, a UI-based system built on Hermes Agent to search the web and X for the latest, most useful news, helping users stay current without manual scrolling or relying on less actionable “latest news” prompts in tools like Claude. Each update is automatically swept from X, ranked by usefulness and conversation size, and enriched with an angle, hook, quotes, source links, and an option to draft a post, following a “sweep, rank, angle, ship” workflow. Hermes Oracle runs on a single Hermes agent using Groq OAuth, so users with a Twitter subscription can log in without API keys. Results are saved into an Obsidian “Memory Galaxy” vault to create a searchable archive and continuously improve agent context. The script also pitches the AI Profit Boardroom’s full Agent OS bundle, setup walkthrough, coaching, and community access.00:00 Hermes Oracle Overview02:15 Why Old Methods Fail03:39 Angles Drafts And Ranking05:43 Sweep Rank Angle Ship06:50 One Agent Setup07:40 Obsidian Memory Galaxy09:23 Why It Compounds10:07 Agent OS Ecosystem11:20 Recap And Next Steps11:39 AI Profit Boardroom Offer12:35 Community Support And Close

Agent Operating System Q&A: Updates, Hermes Migration, Hardware, Fusion vs Fugu + Jarvis Voice ControlThe episode answers recent AI Profit Boardroom questions about using and updating a linked “agent operating system” that includes agents for news, memory (“memory galaxy”), music, video, SEO, and more, with daily updates delivered via zip files and an update command/markdown. It highlights community contributions like generating local AI avatar videos on an RTX 5090 and adding memory to agents. The host explains migrating a Claude-based agent OS to Hermes by having Claude orchestrate and integrate Hermes, recommends a MacBook Pro for frequent travel when not running local models, and warns about the “illusion of progress,” advising time audits and eliminating/delegating before automating. It covers token-limit management, free NVIDIA API use in Hermes, replacing Gemini CLI with Antigravity, using Claude without an API key via CLI, integrating OpenRouter Fusion and Sakana Fugu (with benchmarks and long generation times), and demonstrates a Jarvis-style real-time, voice-activated Hermes setup plus Obsidian customization and Boardroom training/coaching resources.00:00 Agent OS Overview00:54 Keeping It Updated02:07 Community Wins Spotlight03:26 Migrating Claude To Hermes05:06 Hardware Setup Tips05:55 Avoid Fake Progress07:06 Token Limits Fixes08:02 Free APIs And CLIs09:23 Fusion And Fugu Benchmarks12:24 Building Dashboards With Codex14:24 Systems Over Models16:04 Hermes Jarvis Demo17:40 Obsidian Customization18:36 Fugu Ultra Practical Use19:35 Boardroom Training And Wrap

Hermes Agent Computer Use Update: Background Desktop Control Now on Windows, Linux & macOSHermes Agent’s “computer use” feature has a new update adding Windows and Linux support and improving macOS, allowing Hermes Jarvis to control a computer by reading the screen and clicking/typing in the background without moving your real cursor or interrupting your work. The script demos opening Obsidian, websites, Google, and writing a note via real-time mode and a more powerful agent mode that can run tasks in the background. It explains the “Hermes Takeover Engine” workflow, emphasizes cross-OS support, and notes you can use different AI “brains” (including local/free options) rather than being locked to one model. Safety is highlighted through approval prompts before potentially destructive actions, plus a stop button. The episode contrasts this with slower, screen-taking tools like Claude Computer Use and promotes the AI Profit Boardroom/Agent OS for setup, training, and support.00:00 Update Overview00:16 Live Demo Basics00:37 Agent Mode Tasks01:18 Voice Interaction Demo01:43 Takeover Engine Explained02:57 Five Step Quiet Control03:43 Models Setup Commands05:45 Agent OS Pitch06:20 Safety Approvals06:52 Why Hermes Beats Others08:40 Key Takeaways09:07 Join And Wrap Up

Stop Prompting, Start Loop Engineering: Build Self-Iterating AI Agent SystemsThe script explains why “loop engineering” is replacing manual prompting: instead of iterating with an AI yourself, you define what “done” looks like, let an agent act, and use an independent judge model to verify results and repeat until the goal is met. It cites industry figures and examples (including Anthropic and NVIDIA’s GTC keynote) to argue that better loops, not better prompts, will power future self-iterating agent systems. The speaker describes a doer/judge loop structure and shows four implementations inside an “agent operating system”: a Fusion loop with configurable rounds and separate builder/judge models, an agent Kanban board with planner/builder/reviewer roles, a Fusion “boardroom” combining multiple model outputs via a judge, and a Sakana/Fugu council approach. It also describes an Obsidian-based memory system and promotes the AI Profit Boardroom community and resources.00:00 Why Loops Beat Prompts00:48 What Loop Engineering Means03:39 Prompting vs Looping04:44 Doer and Judge Framework05:37 Fusion Loop Walkthrough06:26 Agent Kanban Loops07:21 Fusion Boardroom Method08:31 Sakana Fugu Council09:05 Agent OS Bundle Overview10:01 Memory Feedback Loop11:26 Getting Started and Proof12:01 Join the Community12:35 Final Wrap Up

Hermes Agent OS: Build Your Own Autonomous AI System (No Code)Discover how to transform standard AI models into a powerful Agentic Operating System featuring voice control, autonomous loops, and specialized agents. Learn why prompting is dead and how loop engineering allows non-technical users to build complex video, music, and SEO workflows automatically.00:00 - Intro: The Hermes Agent OS00:13 - Real-Time Voice Control & Jarvis01:24 - Studio & Personal AI Butler01:49 - Goal Mode: Why Prompting is Dead04:10 - Specialized Music & Video Agents06:24 - Orchestrating Agent Organizations08:31 - Fully Automated SEO Loops10:16 - How to Build it Without Code

Sakana Fugu (Fugu Ultra) Just Dropped: Multi‑Agent API vs Fusion, Fable 5 & GLM 5.2 BenchmarksThe video covers a new release from Japanese AI lab Sakana called Sakana Fugu, a multi-agent orchestration system accessible via a single model API, including a higher-end option called Fugu Ultra that reportedly matches frontier models like Fable and Mythos. The host explains the panel-style approach (similar to Fusion) where multiple models produce responses that are synthesized into one answer, then shares early hands-on tests generating a polished website, a maze game, a galaxy simulation, and an orbit simulation. They review benchmark comparisons (noting SW Bench Pro favors Fable 5) and side-by-side output quality against GLM 5.2, Opus 4.8, and Fusion, while warning about self-reported benchmark claims and recommending independent testing via their Goldy Bench. They show integrating Sakana into their Agent OS, discuss latency and use cases (Fugu vs Fugu Ultra), pricing differences versus Fusion, and how to access the API via sakana.ai, then promote the AI Profit Boardroom community and daily Agent OS updates.00:00 Sakana Fugu Launch01:11 Early Demos Showcase02:06 Fusion Style Overview02:23 Benchmark Performance03:06 Head To Head GLM04:45 Versus Opus Comparison05:12 Benchmark Hype Warning05:52 Agent OS Integration06:42 Using The Sakana API07:37 Fugu Versus Ultra08:32 Orbit Demo Results09:04 Fugu Versus Fusion09:37 Saving Outputs Workflow10:05 Cost And Pricing11:07 Wrap Up And Community

Fusion by OpenRouter: One-Prompt Game Builds, Panel-of-Models AI, and Benchmark Results vs Opus 4.8The video introduces OpenRouter’s new Fusion API, designed to reach Fable 5-level intelligence by running five models as a panel and using a judge to critique and fuse their responses into one output from a single API call. The creator demos multiple projects generated from one prompt, including a 3D maze, Dragon Realm open-world game, block breaker, neon racer, pool emulator, voxel dash, raycast game, and Outrun, then compares Fusion outputs side-by-side against Claude Opus 4.8, showing Fusion’s versions as more playable and polished. The episode reviews OpenRouter benchmark claims, notes Fusion can reach comparable performance at about half the cost, and explains premium vs budget panels across 42 tasks. It also shows integrating Fusion into an agent operating system workspace, while highlighting the main drawback: slow response times and workflow friction.00:00 Fusion Game Demos01:03 How Fusion Works01:44 Benchmarks and Cost03:58 More One Prompt Creations04:21 Fusion vs Opus Comparisons06:26 Agent OS Integration07:18 Limitations and Verdict07:55 Community and Resources09:16 Final Wrap Up

Agent OS Q&A: Hardware, Windows Setup, Local Models, SEO Workflows, NotebookLM MCP + MoreThe video tours an Agent OS “mission control” that connects AI agents, tools, CLIs, and custom workflows (including an agent Kanban, SEO setup, video automation, and an Obsidian-based memory system), then answers community questions. It covers local hardware and model suggestions (Mac Mini/Studio not ideal for local models unless high spec; RTX setups like RTX 590 and DGX Spark; Qwen 3.6 for text and Ernie for images) while noting Agent OS is lightweight if using APIs/CLIs. For Windows, it recommends native setup over WSL. It outlines agency use cases (video pipeline, SEO content deployment, and organizing clients as Obsidian project folders), shows SEO ranking examples, explains connecting NotebookLM via MCP, discusses OS/VPS options, email safety (use a sandboxed email), model choices and a personal benchmark site (goldybench.com), and describes AI Profit Boardroom access, support, updates, and coaching.00:00 Agent OS Overview00:56 Local Hardware Models02:14 Windows Setup Choices02:45 Agency Use Cases04:45 SEO Wins Examples05:43 NotebookLM MCP Integration07:02 OS VPS Hosting Options08:44 Model Picks Benchmarks10:44 Custom Builds Showcase11:23 Automation Email Safety13:30 More Community Q&A15:12 Wrap Up Join Boardroom

Hermes Jarvis: A Real-Time Voice Agent Built on Hermes + Obsidian (Daily Briefings, Wake Word, Fast API)The script demos a real-time, voice-activated version of Hermes called Hermes Jarvis that can respond instantly, open apps like Google and Obsidian, and deliver daily briefings using memories stored in an Obsidian vault, including open items, recent work, what’s on the user’s mind, and news headlines with saved briefing history. The narrator shows conversation history, built-in features (including a meditation app), wall mode on a separate monitor, wake word activation, voice switching, link-reading from chat, and the ability to interrupt Jarvis mid-speech. They explain the system was iterated for weeks using Claude and Claude Desktop and note ChatGPT real-time API replaced ElevenLabs due to speed. The episode ends by inviting feature requests and promoting access to the full setup via the AI Profit Boardroom.00:00 Jokes and Languages00:44 Opening Obsidian Briefing01:40 Hermes Jarvis Demo03:00 How It Was Built03:28 Speed and Tooling Tips05:15 Architecture and Features06:26 Interrupt and Wake Word07:20 Build Voice Agents Now07:27 Join the Community08:06 Wrap Up

Hermes Agent Blank Slate Setup Mode: Build a Faster, Update‑Proof AI AgentThe script explains Hermes Agent’s new Blank Slate Setup Mode, which lets you build an AI agent from the ground up with only the bare minimum (model, files, terminal) and manually enable tools later. It contrasts this with the old “fully loaded” setup where every agent boots with many capabilities and can become slower after updates, citing OpenClaw’s decline as an example. Hermes now offers Quick Setup, Full Setup, and Blank Slate, launched via typing “Hermes setup” in the terminal, with tools added later through “Hermes tools/skills” (e.g., skill opt-in). Benefits highlighted include faster performance (especially on weaker devices), more security, fewer tokens, predictable behavior, and an “update-proof” configuration that won’t load tools you didn’t choose. The presenter shows using separate agent profiles to compare blank slate vs full setups and promotes the Hermes Agent OS/community and coaching at aiprofitborne.com.00:00 Blank Slate Update01:16 Profiles Side by Side02:18 Update Proof Minimal Boot03:59 Setup Options Explained05:54 Why It Matters07:32 Use Cases and Demo08:41 Commands to Enable Tools09:23 Control for Client Work10:39 Key Takeaways Recap11:17 Agent OS Offer12:44 Wrap Up

I Built an Agentic AI Operating System (Voice-Controlled Jarvis + Video/SEO/Music Agents)Julian demonstrates an “agentic operating system” built with Claude that connects multiple AI CLIs, agents, and tools into a single workspace with a large “memory galaxy,” voice control, and web/computer navigation (e.g., “Jarvis” opening his site). He explains how he iterates daily via long livestream coding sessions to automate tasks like Substack and to integrate free tools such as NotebookLM for research and one-click generation of videos, podcasts, quizzes, slide decks, and more. He showcases agents that automate video creation (including multi-minute edited videos with research and B-roll), SEO workflows that grew sites from zero to 220+ daily clicks, and even a drum-and-bass music agent. He also highlights local-model voice coding, a multi-model group chat, benchmark/leaderboard sites, an auto-generated guide site, token/API tracking, and plugging in new models, then promotes getting the system and support via the AI Profit Boardroom community.00:00 Agent OS Overview00:38 Voice Controlled Jarvis01:14 Why Build Daily02:54 Automating With Prompts03:17 NotebookLM Studio Tools03:48 Video Agent Automation04:38 SEO Growth Proof05:32 Music And Local Models06:43 Benchmarks And Guides08:07 Mission Control Workspace09:05 Plug In Any Model09:36 Community And Access11:13 How To Start Today11:46 Inside Profit Boardroom13:07 Final Wrap Up