Agent OS Just Changed AI Forever…

Agent OS Just Changed AI Forever…

Agent Operating System Q&A: Model Restrictions, Local AI, Hermes Jarvis, SEO & Video AutomationThe episode answers community questions about the Agent Operating System and how to get the most from it, highlighting Hermes Oracle for news and SEO automation, Hermes Jarvis as a voice-activated agent, and managing all agents and client instances from one interface using separate profiles. It argues that gated frontier models like GPT 5.6 previews and the removal of Fable 5 matter less than building robust systems that can swap models in and out, including using alternatives like Fusion or Sakana Fugu and open-weight local options such as GLM 5.2. The host discusses a high-volume posting strategy with strict quality control, rising demand for local model setups for privacy and cost, automating video production via a video agent and avatar workflow training, using Paperclip for fact-checking and multi-agent teams, Windows support, SEO article generation and deployment, UI improvements to the Kanban board, and examples of AI-assisted game creation, while promoting the AI Profit Boardroom for daily Q&A, tutorials, coaching calls, and the Agent OS zip file.00:00 [https://www.youtube.com/watch?v=MnIH1VWLfpw] Agent OS Overview01:13 [https://www.youtube.com/watch?v=MnIH1VWLfpw&t=73s] Model Access Concerns03:16 [https://www.youtube.com/watch?v=MnIH1VWLfpw&t=196s] Posting Strategy Growth04:41 [https://www.youtube.com/watch?v=MnIH1VWLfpw&t=281s] Local Models for Clients05:36 [https://www.youtube.com/watch?v=MnIH1VWLfpw&t=336s] Managing Client Agents07:10 [https://www.youtube.com/watch?v=MnIH1VWLfpw&t=430s] Automating Video Creation07:57 [https://www.youtube.com/watch?v=MnIH1VWLfpw&t=477s] Fact Checking Workflow08:36 [https://www.youtube.com/watch?v=MnIH1VWLfpw&t=516s] Windows Install Support08:54 [https://www.youtube.com/watch?v=MnIH1VWLfpw&t=534s] Hermes Jarvis Voice Agent10:09 [https://www.youtube.com/watch?v=MnIH1VWLfpw&t=609s] Paperclip Social Team11:57 [https://www.youtube.com/watch?v=MnIH1VWLfpw&t=717s] Systems Over Models12:37 [https://www.youtube.com/watch?v=MnIH1VWLfpw&t=757s] Hermes Desktop vs OS13:28 [https://www.youtube.com/watch?v=MnIH1VWLfpw&t=808s] Using GLM in Claude Code15:21 [https://www.youtube.com/watch?v=MnIH1VWLfpw&t=921s] SEO Blog Automation16:15 [https://www.youtube.com/watch?v=MnIH1VWLfpw&t=975s] AI Game Development Demos18:09 [https://www.youtube.com/watch?v=MnIH1VWLfpw&t=1089s] Kanban Board Upgrade19:58 [https://www.youtube.com/watch?v=MnIH1VWLfpw&t=1198s] Join the Boardroom21:02 [https://www.youtube.com/watch?v=MnIH1VWLfpw&t=1262s] Easy Setup Testimonials22:14 [https://www.youtube.com/watch?v=MnIH1VWLfpw&t=1334s] Final Wrap Up

Hermes Mixture of Agents DESTROYS Fable 5?

Hermes Agent Mixture of Agents (MoA) Presets: Build a Model Panel to Beat Gated Frontier ModelsHermes Agent has released Mixture of Agents (MoA) Presets, allowing multiple AI models to run in parallel and be aggregated into a single stronger answer, similar to systems like Fusion and Sakana Fugu. The script explains this as a workaround for gated or limited-preview frontier models (e.g., GPT 5.6 and Claude Fable 5) by improving performance through a “panel of experts” approach rather than relying on one model. It introduces Hermes Bench, noting claimed reference MoA scores 8% higher than Opus and 11% higher than GPT, and highlights top performance from an Opus 4.8 + GPT-5.5 aggregator. Viewers are shown how to update Hermes, select MoA presets via terminal and dashboard, configure via desktop app or config.yaml, and switch presets with provider commands.00:00 [https://www.youtube.com/watch?v=C0lsQVUWLqY] Hermes MoA Presets00:43 [https://www.youtube.com/watch?v=C0lsQVUWLqY&t=43s] Why Models Are Gated02:09 [https://www.youtube.com/watch?v=C0lsQVUWLqY&t=129s] Update and Enable MoA04:06 [https://www.youtube.com/watch?v=C0lsQVUWLqY&t=246s] Commands and Config04:49 [https://www.youtube.com/watch?v=C0lsQVUWLqY&t=289s] Top Hermes Bench Combos05:04 [https://www.youtube.com/watch?v=C0lsQVUWLqY&t=304s] Panel Beats Genius05:47 [https://www.youtube.com/watch?v=C0lsQVUWLqY&t=347s] Fusion and Alternatives06:35 [https://www.youtube.com/watch?v=C0lsQVUWLqY&t=395s] Build Systems Not Models07:34 [https://www.youtube.com/watch?v=C0lsQVUWLqY&t=454s] Agent OS Workflow08:42 [https://www.youtube.com/watch?v=C0lsQVUWLqY&t=522s] Old Way vs New Way09:39 [https://www.youtube.com/watch?v=C0lsQVUWLqY&t=579s] AI Profit Boardroom10:58 [https://www.youtube.com/watch?v=C0lsQVUWLqY&t=658s] Wrap Up and Links

Fable 5 is Coming Back?

Fable 5 & Mythos-5 Update: Partial Lift, Limited Access, and Why You Need an Agent OSThe script discusses new updates on Anthropic’s Fable 5 and Mythos-5, citing reports that the Trump administration struck a deal allowing Mythos-5 to be released to a vetted group of 100 companies and some federal agencies, framing this as a partial lift after both models were pulled worldwide. It compares this gating trend to OpenAI’s GPT-5.6 limited preview and raises questions about whether access will be US-only and whether public access to frontier models is ending, especially as China releases open-weights models like GLM 5.2. The creator argues viewers should “focus on the system, not the model,” promoting an agent operating system that can swap between models and maintain workflows, memory, and prompts, and advertises the AI Profit Boardroom community and training.00:00 [https://www.youtube.com/watch?v=c0Qi9_FuvAw] Mythos-5 Deal Update00:41 [https://www.youtube.com/watch?v=c0Qi9_FuvAw&t=41s] Gated Access Explained01:12 [https://www.youtube.com/watch?v=c0Qi9_FuvAw&t=72s] Negotiations and Timeline02:38 [https://www.youtube.com/watch?v=c0Qi9_FuvAw&t=158s] Agents Beat Model Gates05:14 [https://www.youtube.com/watch?v=c0Qi9_FuvAw&t=314s] Stop Chasing Models07:08 [https://www.youtube.com/watch?v=c0Qi9_FuvAw&t=428s] Agent OS Demo Highlights08:45 [https://www.youtube.com/watch?v=c0Qi9_FuvAw&t=525s] Boardroom Offer Breakdown09:38 [https://www.youtube.com/watch?v=c0Qi9_FuvAw&t=578s] Community Tour and Wrap

NEW GPT 5.6 is INSANE!

GPT-5.6 Sol, Terra & Luna: Limited Preview, Benchmarks, Access (and Why Systems Beat Models)The episode breaks down OpenAI’s GPT-5.6 release, explaining that it’s currently a limited preview available only to about 20 partner organizations via Codex and the API at the request of the US government, with general access hoped for in the coming weeks and possibly restricted by country. It introduces the three new models—Sol (frontier, with Sol Ultra and Sol), Terra (balanced, competitive with GPT-5.5 at roughly half the cost), and Luna (fast, affordable for high-volume work)—and highlights benchmark claims such as Sol Ultra’s 91.9 on Terminal Bench 2.1 while noting other tests where competitors still lead. The speaker argues that chasing new model launches is a mistake and recommends building a model-proof “agent operating system” with a swap layer, multiple models on tap, task routing, and owned memory so models can be swapped in and out with minimal effort, then promotes access to their Agent OS and community.00:00 [https://www.youtube.com/watch?v=j6oLT0ZGjP8] GPT 5.6 Overview00:23 [https://www.youtube.com/watch?v=j6oLT0ZGjP8&t=23s] Preview Access Limits00:42 [https://www.youtube.com/watch?v=j6oLT0ZGjP8&t=42s] Meet Sol Terra Luna01:45 [https://www.youtube.com/watch?v=j6oLT0ZGjP8&t=105s] Release Timing Uncertainty03:12 [https://www.youtube.com/watch?v=j6oLT0ZGjP8&t=192s] Benchmarks Breakdown05:27 [https://www.youtube.com/watch?v=j6oLT0ZGjP8&t=327s] Stop Chasing Models07:54 [https://www.youtube.com/watch?v=j6oLT0ZGjP8&t=474s] Model Proof System08:16 [https://www.youtube.com/watch?v=j6oLT0ZGjP8&t=496s] Swap Layer Routing Memory10:43 [https://www.youtube.com/watch?v=j6oLT0ZGjP8&t=643s] Common Objections Answered12:36 [https://www.youtube.com/watch?v=j6oLT0ZGjP8&t=756s] Agent OS Offer13:22 [https://www.youtube.com/watch?v=j6oLT0ZGjP8&t=802s] Community Tour14:19 [https://www.youtube.com/watch?v=j6oLT0ZGjP8&t=859s] Final Call To Action

Codex + Claude Code + Agent OS Is INSANE!

Agent OS Q&A: Using Codex, Claude Code, Local LLMs, GLM 5.2, Team Setups, Updates & AI Video EditingJulian answers recent community questions about his Agent Operating System, a system for linking and orchestrating AI agents with features like voice control via Hermes Jarvis, a Memory Galaxy connected to an Obsidian vault, Kanban orchestration, and a local agent engine. He explains multiple ways to use a Codex subscription inside Agent OS (Codex tab, Hermes with GPT‑4.5 and image generation, OpenCloude integration, and a new Codex plugin inside Claude Code), and emphasizes building repeatable systems rather than relying on prompts or specific models. He discusses Qwen 3.6 vs Qwen Agent World, options for connecting Codex/Claude Code to local models via config changes or Ollama, and why GLM 5.2 performs strongly versus other models while being openly available. He also covers simplifying Agent OS for teams with hidden UI sections and SOPs, faster AI video assembly via Agent OS/Remotion workflows, how to update Agent OS via the latest zip and update file, and creating a shared company “brain” with a shared Obsidian vault.00:00 [https://www.youtube.com/watch?v=bjfIdTpxINY] Agent OS Overview00:48 [https://www.youtube.com/watch?v=bjfIdTpxINY&t=48s] Using Codex Inside OS02:24 [https://www.youtube.com/watch?v=bjfIdTpxINY&t=144s] Systems Over Prompts04:00 [https://www.youtube.com/watch?v=bjfIdTpxINY&t=240s] Qwen Agent World Talk04:37 [https://www.youtube.com/watch?v=bjfIdTpxINY&t=277s] Local LLM Connections05:16 [https://www.youtube.com/watch?v=bjfIdTpxINY&t=316s] Why GLM 5.2 Wins07:08 [https://www.youtube.com/watch?v=bjfIdTpxINY&t=428s] Sharing OS With Team09:14 [https://www.youtube.com/watch?v=bjfIdTpxINY&t=554s] Fast SaaS Video Creation10:37 [https://www.youtube.com/watch?v=bjfIdTpxINY&t=637s] Best Ollama Model Setup11:48 [https://www.youtube.com/watch?v=bjfIdTpxINY&t=708s] Updating Agent OS Builds12:27 [https://www.youtube.com/watch?v=bjfIdTpxINY&t=747s] Memory Galaxy Workflow13:06 [https://www.youtube.com/watch?v=bjfIdTpxINY&t=786s] Team Profiles Shared Brain14:24 [https://www.youtube.com/watch?v=bjfIdTpxINY&t=864s] Wrap Up Join Boardroom