AI News Today | Julian Goldie Podcast

OmniRoute: Code with AI for Free Forever (90 Free Providers + Auto Fallback + Token Savings)This episode demos OmniRoute, a free open-source AI gateway that lets coding tools like Claude Code and Cursor route through a single local endpoint to 237 providers, including 90 that are free forever, with automatic fallback when limits are hit. The presenter shows OmniRoute generating projects (an animated star field, a to-do list app, a virtual keyboard, and a landing page) with code and live previews, and highlights token-minimization that can cut usage by 15–95%. Setup is shown as quick via simple terminal commands, runs across 42 languages, and supports variants like auto/fast and auto/coding plus 17 routing strategies including Fusion. The video also explains how OmniRoute is integrated into an Agent OS “free coding engine” with saving/visualizing builds, and closes by promoting the AI Profit Boardroom community, trainings, and coaching calls.00:00 OmniRoute Overview01:10 Setup in Agent OS01:40 Quick Install Steps01:59 Building a To-Do App02:17 Why Free Tiers Fail03:09 Key Benefits Recap03:22 Five Layer Routing04:01 Speed Demo Build04:56 Provider Disappear Fallback05:35 Models and Routing Modes06:07 Fusion Strategy Explained06:33 Full Agent OS Pitch07:01 Community and Training07:44 How to Join and Outro

Agent A1: New Free Local Chinese Agentic Model (35B MoE) + Benchmarks, Speed & SetupThe video reviews Agent A1, a newly released free Chinese local model designed for agentic tasks, showing it running privately and offline inside an Agent Factory workflow alongside free Claude code. The host demos outputs like a landing page, a neon snake game, a “Dragon Realm” open-world game, a keyboard mini app, and a 3D solar system visualization, noting fast replies and that builds save to a workspace with optional voice control. Agent A1 is a 35B mixture-of-experts model (3B active) with a 256k context window, created by Intern Science in Shanghai and optimized for long-horizon search, engineering, scientific research, instruction following, and tool calling. It ranks #2 on the creator’s local leaderboard, outperforming Gemma 4 but trailing Qwable, and is reported around 95 tokens/sec locally on a Mac Studio M4. The video explains strengths/weaknesses, shows running via Ollama and configuring Hermes profiles, and promotes an Agent OS bundle plus OmniRoute routing across 90 free models.00:00 Meet Agent A100:31 Live Local Build Demo00:53 Leaderboard And Examples01:36 What A1 Actually Is02:29 Benchmarks Breakdown03:08 More Builds In Action03:45 Specs Speed And Context04:40 How To Run Locally04:43 Strengths And Weaknesses05:41 Hermes Setup Steps06:13 Agent OS And OmniRoute06:51 Get The Full Setup07:34 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

Hyperframes + Hermes Agent is INSANE!

Hermes Astros is Absolutely INSANE!

Meet Hermes Apollo: A Local, Voice-Activated Jarvis Inside Agent OS (Build Apps, Briefings & Browser Control)The script demonstrates Hermes Apollo, a voice-activated assistant inside Agent OS that responds quickly via ChatGPT real-time and can run agentic tasks through a backend agent using GLM 5.2. The presenter shows Apollo telling a joke, teaching a Chinese word (“xie xie”), building a snake game and a 24-hour countdown timer with previews, and opening a website by voice. Apollo supports wake-word hands-free use, wall mode, chat and build history, weekly/monthly briefings, memory recall via an Obsidian “memory galaxy,” and can switch to agent mode to control the browser. The broader system includes Hermes Oracle for trending Twitter news and Hermes Astros for competitor monitoring and content idea generation. The presenter emphasizes speed, usefulness beyond Siri, local/private operation options, and invites viewers to get the full setup in the AI Profit Boardroom with tutorials, guides, coaching calls, and community support.00:00 Meet Apollo Demo00:28 Voice Commands Build Apps01:00 Jarvis Style Overview01:33 Briefings And History02:17 How It Works Backend02:51 Modes And Wake Word03:18 Agent Mode Browser Control03:51 Prompts And Use Cases04:15 Memory With Obsidian04:38 Oracle And Astros Tools05:43 Not Just A Toy06:03 Privacy And Local Models06:18 Setup Proof And Testimonials06:34 Get Agent OS Access07:02 Community Coaching And Wrap

10 Ways to Cut Fable 5 Token Usage (Up to 95% Less) — Model Routing, Headroom, Ponytail + MoreThe video explains how to reduce token usage when working with Fable 5, noting it can consume tokens quickly, only allows 50% of a subscription, and will move off-subscription by July 7. It shares 10 practical tactics, including routing tasks to cheaper models (e.g., using Fable 5 only for the hardest work, and Opus/Haiku/GLM 5.2 for general coding), using Fable 5 for planning while a cheaper model implements, lowering the effort level, and installing open-source tools like Headroom (60–95% token savings) and Ponytail (54% less code on average, up to 94%). Additional tips include trimming Claude MD/rules, turning off web search by default, using /compact plus a brief handoff to preserve context, and doing a periodic /clear with a short note to avoid long-session token bloat. The episode also highlights the creator’s Agent Operating System and AI Profit Boardroom community for token-efficiency playbooks, training, and coaching.00:00 Why Tokens Matter01:01 Route Tasks by Model01:45 Plan Then Build Cheap02:58 Adjust Effort Settings03:47 Headroom Token Shrinker04:35 Ponytail Lazy Dev05:39 Trim Rules and Search06:48 Manual Compact Workflow08:08 Two Hour Clear Reset08:58 Wrap Up and Results09:22 Agent OS Pitch10:26 Community and Outro

Agent OS Q&A: How to Start, What to Automate First, and Best Features (Hermes, SEO, Memory)The episode answers recent questions about building and using an agent operating system, emphasizing that once set up it can transform daily work by automating recurring tasks and integrating useful open-source tools like AI film generation and SEO systems. For beginners, the advice is to simplify by only adding the tools you actually use (e.g., just Claude), automate what currently consumes the most time, and personalize the UI and features to increase adoption. For installation on a VPS, viewers are told they can ask their agent to run through the guide’s modules and should avoid installing unnecessary components. The script also discusses staying productive despite “shiny object” distractions, using a video agent and SEO tools for content creation while posting manually to avoid platform penalties, leveraging Hermes Oracle for trending topics and WordPress publishing, teaching workflows via Claude’s browser extension, debugging Paperclip with Claude, and highlights shared memory/knowledge graph, Hermes Astros keyword monitoring, and an AI “SEO office” of agents available through the AI Profit Boardroom community and coaching.00:00 Agent OS Overview01:13 Start Simple First02:32 Install Checklist Tips03:24 Boredom And Focus04:09 Content Automation Stack06:06 Teach Agents Workflows06:36 Fixing Paperclip Bugs07:20 Hermes Agents Demo09:13 Get The Full Setup09:52 Final Thanks

Agent OS: VPS + Elevenlabs + Hermes!

Claude Fable 5: Last 72 Hours to Build & Automate (Before July 7)The script warns that Claude Fable 5 is only available for three more days until July 7 before moving to API-only access, and recommends using the limited window to automate high-impact work rather than building generic web pages. It suggests starting with a quick time audit to identify where you spend the most time, then using Fable 5 (described as the best single-model coding option tested across 42 builds) to build tools for those tasks, followed by testing and iterating across multiple parallel Claude Desktop conversations. It also proposes plugging workflows into a single “mission control” system and, if time is short, using Fable 5 to create detailed step-by-step plans that cheaper models can later implement with similar outputs, based on referenced Kilo AI research.00:00 Fable 5 Deadline Warning00:20 Reverse Engineer Your Work00:57 Why Fable 5 Wins02:01 Time Audit First02:28 Prompt Your First Tool03:05 Test and Iterate Builds03:37 Parallel Projects Mission Control04:51 Plan With Fable 5 Build Cheap07:25 Three Options Recap07:59 Boardroom Offer and OutroJulian Goldie SEO outlines strategies for l