AI News Today | Julian Goldie Podcast

Agent OS + Obsidian + Sakana Fugu + Hermes Jarvis!

20 min · 24. juni 2026
episode Agent OS + Obsidian + Sakana Fugu + Hermes Jarvis! cover

Beskrivelse

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 [https://www.youtube.com/watch?v=LSn7uFWwdFk] Agent OS Overview00:54 [https://www.youtube.com/watch?v=LSn7uFWwdFk&t=54s] Keeping It Updated02:07 [https://www.youtube.com/watch?v=LSn7uFWwdFk&t=127s] Community Wins Spotlight03:26 [https://www.youtube.com/watch?v=LSn7uFWwdFk&t=206s] Migrating Claude To Hermes05:06 [https://www.youtube.com/watch?v=LSn7uFWwdFk&t=306s] Hardware Setup Tips05:55 [https://www.youtube.com/watch?v=LSn7uFWwdFk&t=355s] Avoid Fake Progress07:06 [https://www.youtube.com/watch?v=LSn7uFWwdFk&t=426s] Token Limits Fixes08:02 [https://www.youtube.com/watch?v=LSn7uFWwdFk&t=482s] Free APIs And CLIs09:23 [https://www.youtube.com/watch?v=LSn7uFWwdFk&t=563s] Fusion And Fugu Benchmarks12:24 [https://www.youtube.com/watch?v=LSn7uFWwdFk&t=744s] Building Dashboards With Codex14:24 [https://www.youtube.com/watch?v=LSn7uFWwdFk&t=864s] Systems Over Models16:04 [https://www.youtube.com/watch?v=LSn7uFWwdFk&t=964s] Hermes Jarvis Demo17:40 [https://www.youtube.com/watch?v=LSn7uFWwdFk&t=1060s] Obsidian Customization18:36 [https://www.youtube.com/watch?v=LSn7uFWwdFk&t=1116s] Fugu Ultra Practical Use19:35 [https://www.youtube.com/watch?v=LSn7uFWwdFk&t=1175s] Boardroom Training And Wrap

Kommentarer

0

Vær den første til å kommentere

Registrer deg nå og bli medlem av AI News Today | Julian Goldie Podcast sitt community!

Prøv gratis

Prøv gratis i 14 dager

99 kr / Måned etter prøveperioden. · Avslutt når som helst.

  • Eksklusive podkaster
  • 20 timer lydbøker i måneden
  • Gratis podkaster

Alle episoder

552 Episoder

episode Hermes Voice Agent is INSANE! cover

Hermes Voice Agent is 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 [https://www.youtube.com/watch?v=XdipS9o1RGg] Meet Apollo Demo00:28 [https://www.youtube.com/watch?v=XdipS9o1RGg&t=28s] Voice Commands Build Apps01:00 [https://www.youtube.com/watch?v=XdipS9o1RGg&t=60s] Jarvis Style Overview01:33 [https://www.youtube.com/watch?v=XdipS9o1RGg&t=93s] Briefings And History02:17 [https://www.youtube.com/watch?v=XdipS9o1RGg&t=137s] How It Works Backend02:51 [https://www.youtube.com/watch?v=XdipS9o1RGg&t=171s] Modes And Wake Word03:18 [https://www.youtube.com/watch?v=XdipS9o1RGg&t=198s] Agent Mode Browser Control03:51 [https://www.youtube.com/watch?v=XdipS9o1RGg&t=231s] Prompts And Use Cases04:15 [https://www.youtube.com/watch?v=XdipS9o1RGg&t=255s] Memory With Obsidian04:38 [https://www.youtube.com/watch?v=XdipS9o1RGg&t=278s] Oracle And Astros Tools05:43 [https://www.youtube.com/watch?v=XdipS9o1RGg&t=343s] Not Just A Toy06:03 [https://www.youtube.com/watch?v=XdipS9o1RGg&t=363s] Privacy And Local Models06:18 [https://www.youtube.com/watch?v=XdipS9o1RGg&t=378s] Setup Proof And Testimonials06:34 [https://www.youtube.com/watch?v=XdipS9o1RGg&t=394s] Get Agent OS Access07:02 [https://www.youtube.com/watch?v=XdipS9o1RGg&t=422s] Community Coaching And Wrap

5. juli 20267 min
episode Fable 5: FREE Tools Cut Tokens by 95%! cover

Fable 5: FREE Tools Cut Tokens by 95%!

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 [https://www.youtube.com/watch?v=v_wQ1X5i81Y] Why Tokens Matter01:01 [https://www.youtube.com/watch?v=v_wQ1X5i81Y&t=61s] Route Tasks by Model01:45 [https://www.youtube.com/watch?v=v_wQ1X5i81Y&t=105s] Plan Then Build Cheap02:58 [https://www.youtube.com/watch?v=v_wQ1X5i81Y&t=178s] Adjust Effort Settings03:47 [https://www.youtube.com/watch?v=v_wQ1X5i81Y&t=227s] Headroom Token Shrinker04:35 [https://www.youtube.com/watch?v=v_wQ1X5i81Y&t=275s] Ponytail Lazy Dev05:39 [https://www.youtube.com/watch?v=v_wQ1X5i81Y&t=339s] Trim Rules and Search06:48 [https://www.youtube.com/watch?v=v_wQ1X5i81Y&t=408s] Manual Compact Workflow08:08 [https://www.youtube.com/watch?v=v_wQ1X5i81Y&t=488s] Two Hour Clear Reset08:58 [https://www.youtube.com/watch?v=v_wQ1X5i81Y&t=538s] Wrap Up and Results09:22 [https://www.youtube.com/watch?v=v_wQ1X5i81Y&t=562s] Agent OS Pitch10:26 [https://www.youtube.com/watch?v=v_wQ1X5i81Y&t=626s] Community and Outro

I går11 min