AI News Today | Julian Goldie Podcast

Fable 5 is GONE in 24 Hours... Do THIS Now!

Use Claude Code for Free Forever with OmniRoute (231+ Providers, Auto-Fallback, 1 Endpoint)The video shows a new OmniRoute (Omniroot) setup that lets you use Claude Code for free by routing the Claude Code CLI (and tools like Codex, Cursor, Copilot, and others) through a single AI gateway endpoint connected to over 230 providers, including many free options. The creator demonstrates Free Claude Code inside an Agent OS tab to generate projects like an SEO agency website with a workspace and live preview, with files saved locally. OmniRoute compresses tokens using RTK and Caveman to save 15–95% and automatically falls back to other providers when one is rate-limited or unavailable, helping avoid session limits seen in standard Claude. The script also covers routing modes (auto/fast, auto/coding, offline), quick setup via terminal commands or having Claude configure it from GitHub, and promotes the AI Profit Boardroom for the full Agent OS, tutorials, community support, and weekly coaching.00:00 Free Claude Code Setup00:35 Agent OS Demo Builds01:28 Using Omniroot in Codex01:46 How Omniroot Works02:26 Token Savings Fallbacks04:57 Live Preview Workflow06:03 Memory Style Guidelines07:51 Routing Modes Settings08:41 Five Minute Install09:48 Agent OS Boardroom Pitch10:43 Community Training Support11:20 Final Links Wrap Up

Inside My Hermes Agent OS: Competitor Tracking, Outreach Automation, Voice Agent & One-Click ContentThe video tours a custom “Hermes Agent OS” the creator built to make Hermes far more powerful than using it only in the terminal or desktop app. It showcases Hermes Astros, a workflow that monitors competitors and keywords via an API and turns trending topics into content ideas that can be sent in one click to a video agent, NotebookLM, or SEO content. It also demonstrates a Hermes-based outreach tool for on-demand lead generation, validation, enrichment, and AI-built email campaigns. Hermes Apollo is shown as a fast, voice-activated assistant that can open apps, use the browser, build mini apps/websites, run in agent mode, use a wake word, and deliver daily/weekly briefings. Hermes Oracle pulls trending industry news, ranks topics, and can generate and publish first-person articles with formatting and CTAs. The system also includes a studio for media generation, a “mixture of agents” setup combining models, and broader orchestration tools, with access offered via the AI Profit Boardroom.00:00 Hermes Agent Overview00:24 Astros Trend Monitor01:44 Outreach Lead Engine02:49 Apollo Voice Assistant04:37 Oracle News to Content06:36 Studio and Agent Mix08:15 Why Custom OS Wins08:54 Orchestration and Memory09:59 Get the Agent OS10:55 Wrap Up

Agent OS Q&A: CLI Setup, Obsidian Memory, Goal Mode Autonomy, Hermes iMessage + Free Coding (OmniRoot)This episode answers recent AI Profit Boardroom questions about configuring and using the Agent Operating System, including how to set up individual CLIs from the install folder (and hide unused ones), and how to organize client work using an Obsidian memory system with separate project folders or custom workflows. It covers why adding too many skills/rules can slow agents down and shows using forward-slash goal mode in tools like Claude Code and Codex, where a judge model checks progress each loop. The script discusses whether to run local LLMs and Agent OS on one machine or separate machines, recommends keeping them local on one device for simplicity and security, and shares community resources for building a connected Obsidian knowledge graph. It also explains setting up iMessage in Hermes via Channels/BlueBubbles and installing FreeClaude Code and OmniRoot for free coding across many APIs.00:00 Agent OS Q&A Intro00:18 Configuring CLIs Fast01:10 Client Projects Setup02:01 Autonomy Without Slowdowns03:09 One Machine Or Two03:59 Connecting CLIs And Agents04:36 Obsidian Knowledge Graph06:04 Hermes iMessage Setup06:51 Free Claude Code Tour07:41 OmniRoot Free Coding08:33 Wrap Up And Community

RTK Token Savings: Cut LLM Token Usage by ~80% (Plus Ponytail, Headroom & Caveman)The script explains testing RTK, an open-source filter that sits between an AI agent and the shell to remove padding and duplicate output from common commands, reducing token usage while keeping results the same. The presenter reports 82.9% average token savings in their tests, cites RTK’s README claim of 60–90% savings, and notes minimal added latency (~14 ms). An example shows swapping git diff to an RTK version that strips repeated headers and unchanged lines, cutting output from 373,000 to 29,000 characters (92% less) while saving full unshortened output to a file if needed. RTK is described as easy to install on Linux/macOS, small (6.6 MB), and capable of shortening outputs for about 100 everyday commands. The script also covers stacking RTK with other open-source tools—Ponytail, Headroom, and Caveman—to further minimize tokens, and promotes the Agent OS setup and AI Profit Bot community.00:00 RTK Token Savings Intro00:55 How RTK Works01:47 Real Test Results02:28 Step by Step Example04:42 Testing Method05:07 Install and Command Support05:38 Does It Lose Info05:51 Token Minimizer Stack06:36 Caveman Mode Demo07:39 Fable 5 Efficiency Wins08:23 Agent OS and Community09:25 Wrap Up

Use OpenAI Codex for Free with OmniRoute (93 Providers + Auto Fallback) in Agent OSThe video demonstrates a “free Codex engine” setup that uses OpenAI’s Codex CLI routed through OmniRoute/OmniRoot to access 93 providers (with auto fallback when a free API runs out or rate limits), allowing Codex to plan, write files, and run commands as usual without a Codex subscription. The creator shows building a sleek SEO agency landing page and a working to‑do list app in about 60–90 seconds, with previews and a workspace to revisit past builds inside an Agent OS environment that can also connect outputs to tools like Claude Code and other agents. The script explains that this approach is cloud-based, lightweight on a basic laptop, and quicker than local models, and claims setup is only a couple of commands. It ends by promoting the AI Profit Ballroom community and training for installing the Agent OS zip and learning OmniRoot/Codex workflows.00:00 Free Codex Overview00:42 Agent OS Demo01:45 Why OmniRoot Wins03:28 Local Models Comparison04:10 How Routing Works05:09 To Do App Test05:59 Old vs New Setup06:53 Three Command Install07:52 FAQs and Token Tips08:55 Goal Mode Idea09:23 Workspace Features09:41 Get the Full Setup10:12 Community and Training10:53 Final Call to Action

OmniRoute: The Free Open-Source AI Coding Gateway That Routes Across 90+ Free ProvidersThe video demos OmniRoute, a free open-source (MIT) tool that lets users code and build apps across popular coding tools via a single endpoint that can route requests through 237 providers, including 90+ free options with automatic fallback when a provider fails or quotas run out. The presenter shows generating and previewing projects like a galaxy-themed landing page and a habit tracker, with saved builds, downloadable code, and workspace organization. OmniRoute also uses two token-minimization playbooks (RTK and Caveman) claiming 15–95% token savings to reduce rate limits, and can be plugged into tools like Claude Code, Codex, and Cursor, including agentic setups via custom endpoints such as Hermes. The episode contrasts this approach with paying multiple subscriptions and promotes a packaged “Agent OS” setup available in the AI Profit Boardroom.00:00 OmniRoute Intro00:29 Live Demo Build01:33 How Routing Works02:21 Token Saving Tricks03:05 Habit Tracker Test05:25 Why Free Beats Local06:03 Problems It Solves07:10 Quick Setup Guide07:49 Boardroom Offer08:51 Community And Tutorials09:26 Final Wrap Up

Hermes Agent v0.18 “Judgment Release” Explained: Mixture of Agents, /learn, /journey & Background Fan-OutHermes Agent released v0.18, the “Judgment Release,” introducing key upgrades the host explains and demonstrates, including Mixture of Agents (combining multiple models for stronger one-shot builds), the /learn command (teach Hermes a new skill from a link and save it for future sessions, with notes logged to an Obsidian vault), and /journey (a timeline recap of what Hermes has learned that can be edited or deleted). The update also adds background fan-out via Delegate Task, letting multiple sub-agents run in the background so chat isn’t blocked, with an example of 12 agents building a website. Additional improvements include cheaper self-improvement routing, security updates, presets for mixtures, and better goal-mode contract completion judged by a judge agent. The host shows four ways to update to v0.18 and promotes their custom agent operating system and AI Profit Boardroom community.00:00 V0.18 Overview00:21 Mixture of Agents01:31 Learn Skills from Links02:48 Journey Memory Timeline03:31 Background Fan Out04:37 Other Improvements and Goal Mode05:37 Agent OS vs Desktop App06:09 How to Update06:45 Get the Agent OS07:15 Community and Wrap Up

Claude Fable 5 Agent OS Demo: Automate Outreach, SEO, Videos, Thumbnails & More (1-Click AI Systems)Julian showcases an “Agent OS” built with Claude Fable 5 that centralizes multiple AI agents to automate business tasks like lead generation and email outreach, pulling trending news from X to draft and publish blog/social content for SEO, and creating images, voice, music, thumbnails, and videos (including AI avatars, scripts, research, and B-roll) in a streamlined workflow. He explains the system’s five-layer structure, including a fully automated “memory galaxy” that stores and updates all useful work, goals, and project context across agents. He demonstrates plugging new tools into the OS (e.g., Open Montage movie creation, Open Design, GLM 5.2, Gemma 4 with MoX), discusses token-saving and using free/local models, references Goldie Bench testing across models/tasks, and promotes access to his system and community via the AI Profit Boardroom with trainings, updates, coaching calls, and support.00:00 Mind Blowing Agent OS00:22 Outreach and Lead Automation01:01 Trending News to SEO Posts01:24 Voice Activated Hermes01:57 Five Layer System Memory02:42 Creative Agents Movies Music03:45 Video Agent One Prompt04:45 Automating SEO and Websites05:38 Build It With Fable 505:56 Testimonials Non Coders Win07:08 Plug In New Models Fast07:45 Token Costs and Free Models08:14 Benchmarks Why Fable 509:13 Other Models Fusion MoA10:21 Get Agent OS Boardroom11:12 Training Coaching Community12:30 Final Wrap Up

Cut 65–69% of Tokens with Claude Code (and Any AI Agent) Using CavemanThe script explains a free, open-source “Caveman” skill that reduces output tokens for Claude Code and other agents (Codex, Gemini, Cursor, Windsurf, Cline, Copilot, and more) by making responses short, blunt, and direct while keeping code, commands, file paths, and error messages unchanged. Installed via a one-line command, it drops a rules text file into each agent’s skills/plugin folder so the agent reads it at the start of every chat. Tests on Fable 5 using five real prompts showed about 69% fewer output tokens (e.g., 1,349 down to 324) and about 37% lower total cost while keeping answers correct; it can be toggled with /caveman and set to light/full/ultra, plus optional tools like Commit/Review/Compress. The video also promotes using Caveman across an agent operating system for compounding savings and mentions the AI Profit Ballroom community and training.00:00 Cut Tokens With Caveman01:16 Why Token Costs Hurt01:58 How Caveman Works02:21 Rules And Safety03:06 Does Shorter Mean Worse04:00 Install Across Agents05:03 Real Token Savings Tests07:29 Old Replies Vs New08:49 Modes And Commands09:47 Agent OS And Extras10:30 Join The Community11:29 Wrap Up