AI News Today | Julian Goldie Podcast

How to Build Your Own Agent OS

32 min · 27. maj 2026
episode How to Build Your Own Agent OS cover

Description

Build Your Own Agent Operating System (Free 7-Layer Blueprint + Infinite Context Memory)The speaker presents a step-by-step blueprint for building a personal “agent operating system” that centralizes multiple AI agents into one local dashboard with searchable, previewable history and persistent memory. After spending 100+ hours and nine failed attempts duct-taping tools together, they outline five key mistakes to avoid: treating AI as a tool instead of a system, paying for subscriptions before using free options, relying on weak in-app memory, building brittle n8n automations, and letting outputs disappear into random folders. The solution uses a seven-layer architecture—foundation, memory (Omi + Obsidian), brain (routed models), agents (e.g., Hermes, OpenClaw, Claude Code), command center (Next.js Mission Control), production surfaces (studio/SEO/goals/workspaces), and a loop that writes outputs back into memory—so agents can work autonomously and improve over time.00:00 [https://www.youtube.com/watch?v=bsYbA9ZyYtI] Why Agents Need OS00:56 [https://www.youtube.com/watch?v=bsYbA9ZyYtI&t=56s] Dashboard Tour02:13 [https://www.youtube.com/watch?v=bsYbA9ZyYtI&t=133s] Seven Layer Stack03:08 [https://www.youtube.com/watch?v=bsYbA9ZyYtI&t=188s] Why I Built This05:36 [https://www.youtube.com/watch?v=bsYbA9ZyYtI&t=336s] Nine Failed Attempts06:18 [https://www.youtube.com/watch?v=bsYbA9ZyYtI&t=378s] Mistake One Tools07:12 [https://www.youtube.com/watch?v=bsYbA9ZyYtI&t=432s] Mistake Two Free Stack09:21 [https://www.youtube.com/watch?v=bsYbA9ZyYtI&t=561s] Mistake Three Memory11:14 [https://www.youtube.com/watch?v=bsYbA9ZyYtI&t=674s] Mistake Four Skip n8n13:31 [https://www.youtube.com/watch?v=bsYbA9ZyYtI&t=811s] Mistake Five Organize Outputs15:35 [https://www.youtube.com/watch?v=bsYbA9ZyYtI&t=935s] Old Way vs New17:26 [https://www.youtube.com/watch?v=bsYbA9ZyYtI&t=1046s] Blueprint Seven Layers18:03 [https://www.youtube.com/watch?v=bsYbA9ZyYtI&t=1083s] Seven Layer Blueprint19:15 [https://www.youtube.com/watch?v=bsYbA9ZyYtI&t=1155s] Hardware And Memory20:14 [https://www.youtube.com/watch?v=bsYbA9ZyYtI&t=1214s] Models And Agents22:08 [https://www.youtube.com/watch?v=bsYbA9ZyYtI&t=1328s] Mission Control Dashboard22:53 [https://www.youtube.com/watch?v=bsYbA9ZyYtI&t=1373s] Production Workflows24:37 [https://www.youtube.com/watch?v=bsYbA9ZyYtI&t=1477s] Feedback Loop Layer25:23 [https://www.youtube.com/watch?v=bsYbA9ZyYtI&t=1523s] Build Journey And Proof26:52 [https://www.youtube.com/watch?v=bsYbA9ZyYtI&t=1612s] Limiting Beliefs Debunked28:09 [https://www.youtube.com/watch?v=bsYbA9ZyYtI&t=1689s] Live Q And A29:56 [https://www.youtube.com/watch?v=bsYbA9ZyYtI&t=1796s] Final Recap And Offer31:05 [https://www.youtube.com/watch?v=bsYbA9ZyYtI&t=1865s] Community Coaching Support32:34 [https://www.youtube.com/watch?v=bsYbA9ZyYtI&t=1954s] Closing Thoughts

Comments

0

Be the first to comment

Sign up now and become a member of the AI News Today | Julian Goldie Podcast community!

Get Started

1 month for 9 kr.

Then 99 kr. / month · Cancel anytime.

  • Podcasts kun på Podimo
  • 20 lydbogstimer pr. måned
  • Gratis podcasts

All episodes

589 episodes

episode GPT-5.6 is ABSURD! artwork

GPT-5.6 is ABSURD!

GPT 5.6 Just Dropped: Sol vs Terra vs Luna + 50 Real-World Builds in Agent OSThe script reviews the release of GPT 5.6 and showcases 50 real-world builds created primarily with the flagship Sol model, including smooth web games (Doom-style, 3D racing, Space Invaders, pool physics, raycaster maze, RPG) and polished websites and dashboards. It explains the three new GPT 5.6 models—Sol (flagship), Terra (day-to-day workhorse), and Luna (fast, cheap, token-efficient)—and suggests when to use each, including a slower Pro option. It demonstrates using GPT 5.6 inside Codex and Agent OS via OAuth, highlights autonomous /goal” mode in a sandbox, and notes image generation and workspace organization. It also describes video creation via a Remotion-based video agent and using GPT with the Hermes system (web search, images, voice). Finally, it compares Sol with Fable 5 on cost and quality and promotes getting the Agent OS setup through the AI Profit Boardroom.00:00 GPT 5.6 First Look00:22 Showcase Builds00:41 Sol Terra Luna Explained01:51 Best Setup With Codex02:16 Goal Mode Autonomy03:12 Agent OS Workflow04:01 Video Agent Pipeline04:23 Hermes Agents Overview05:23 Goals Board Productivity05:54 More Game Demos07:32 Luna Terra Comparison08:37 Versus Fable 5 Pricing09:21 Codex Versus Claude UX10:08 Get Agent OS Access11:16 Final Thoughts

Yesterday11 min
episode GPT 5.6 vs Fable 5: Who Wins? artwork

GPT 5.6 vs Fable 5: Who Wins?

GPT-5.6 Sol vs Claude Fable 5: Side-by-Side Game & UI Build Test (Who Wins?)The video compares OpenAI’s flagship GPT-5.6 Sol against Anthropic’s Claude Fable 5 in side-by-side tests, focusing on game generations and coded outputs. Sol is described as cheaper on output price and often smoother, less laggy, and strong on action and precision, winning rounds like an open-world dragon game, Dragon Realm, and narrowly edging a 3D racer on graphics, while Fable 5 is portrayed as stronger on atmosphere, detail, and visual appeal, winning decisively on a Skyrim-style Frostfell game and looking smoother and more interesting in a Remotion video-creation build. Overall results are very close, and the narrator says model choice depends on tooling, preferring Fable 5 largely due to Claude Desktop, while recommending running both models together inside an Agent OS workflow.00:00 Sol vs Fable Setup00:52 Dragon Game Showdown01:36 Dragon Realm and Doom02:22 3D Racer Verdict03:09 Crypt Dungeon Test03:34 Skyrim Style Frostfell04:51 Coding Tool Pick05:27 Agent OS Workflow06:16 Costs and OAuth06:57 Goldie Bench Builds07:14 Flight Sim and Neon City08:08 Remotion Video Test08:47 UX and Codex Sites09:17 Run Both in Agent OS10:10 Join the Community10:54 Final Thanks

Yesterday10 min
episode Agent OS: Multi Agent Orchestration and Automation! artwork

Agent OS: Multi Agent Orchestration and Automation!

Agent Operating Systems Explained: Automate Anything with Paperclip, Hermes & a Unified Agent OSThe video explains an “agent operating system” as a single place where multiple AI agents work together to automate tasks and move from idea to implementation quickly, using tools like Paperclip group chat, a one-click pipeline, and integrated models such as Claude, Fable 5, and GPT 5.6 (via API or OAuth). It highlights Hermes and related modules (Jarvis-style voice agent, Mission Control, Oracle, Astros), plus built-in workflows for lead outreach, SEO keyword discovery and publishing, video and music creation, and a shared memory system that keeps all agents in the same context. The episode is framed around recent AI Profit Boardroom community questions and positions the Agent OS as a customizable, time-saving system for building and automating with AI agents.00:00 Agent OS Overview00:17 Core Features Tour01:27 Codex and Model Switching02:09 Multi Device Setup VPS03:35 AI Avatar Creation Tips04:09 Hermes Mission Control05:03 Cheaper Writing Models05:50 AI Marketing Agency Playbook07:17 Mobile Access On The Go07:53 Community Partnerships08:05 Obsidian Memory Vault09:47 Wrap Up and Next Steps

Yesterday10 min
episode GPT 5.6: NEW Agentic OS is INSANE! artwork

GPT 5.6: NEW Agentic OS is INSANE!

GPT 5.6 Command Engine: Run Agents with OAuth (No API Key) in One DashboardThe video introduces GPT 5.6 integrated into an Agent Operating System that uses OAuth with an existing ChatGPT subscription, requiring no API key, and provides a single dashboard to switch between models and tools like GPT 5.6, Codex, Claude, Hermes, Groq, and free options such as OmniRoot/Hy3 when tokens run out. It highlights five benefits of the “GPT 5.6 command engine”: one login, tier switching (Sol, Terra, Luna), goal mode for autonomous background task loops in a sandbox with optional auto-approve, a workspace where all builds are saved and previewable, and a unified command center with memory so nothing is lost. The script argues this setup is more organized and productive than juggling separate apps or tabs and can be customized for different business workflows.00:00 GPT 5.6 Overview00:48 Unified Agent OS01:26 Why Tabs Fail02:22 Five Key Benefits03:13 Old Way vs New04:24 OAuth Setup Guide04:49 Model Tier Choices05:34 Goal Mode Automation06:27 Build Quality Tests07:06 Custom Workflows08:08 Speed and Tokens08:59 Recap and Proof10:07 Join the Community11:31 Final Thanks

Yesterday11 min
episode GPT-5.6 is INSANE! artwork

GPT-5.6 is INSANE!

GPT-5.6 Sol vs Terra vs Luna: New OpenAI Models Tested (Games, Video, Landing Pages) + How to Route ThemThe script reviews OpenAI’s GPT-5.6 rollout and its three model sizes—Sol (flagship for hard multi-step agentic work), Terra (everyday production), and Luna (fast, cheap, high-volume)—and shows results from extensive testing on Goldy Bench, including games, a full video animation, landing pages, and dashboards. It notes shared specs (1M context window, 128K max output, Feb 2026 knowledge cutoff) and compares performance, speed, and cost across the three on the same 3D space game task, where Sol is slower and more expensive but produces larger, higher-quality output. The presenter compares Sol against “Fable 5,” recommends switching models by task tier to control cost, suggests using Codex/Agent OS and Hermes over ChatGPT for better output, and promotes the AI Profit Boardroom community and tools.00:00 GPT 5.6 Overview00:32 Sol Creations Showcase02:20 Video Generation Demo03:07 Specs Pricing Access04:53 Benchmarks Reality Check06:03 Speed Cost Comparison07:17 Web Pages Dashboards08:41 Model Routing Strategy09:57 Agent OS Workflow11:45 Fable 5 Versus Sol13:12 AI Profit Boardroom Pitch14:52 Wrap Up Thanks

Yesterday14 min