Podcast
AI News Today | Julian Goldie Podcast
Hosted by Julian Goldie · EN
Latest Podcast
45episodes
Episodes
Newest firstAll episodes
Kimi K2.7 + Hermes Agent is INSANE!
2d ago00:14:53Tap to summarizeKimi K2.7 Code + Hermes Agents: Build Apps & Videos Autonomously (Full Demo)The script showcases the release of Kimi K2.7 Code and how it’s been integrated into a Hermes Agent “crew” to autonomously build, run, bug-fix, and iterate on real projects using a large context window and a flat monthly coding plan. It demonstrates a fully AI-produced video where the avatar (via HeyGen CLI), editing/design, music, voiceover, and even camera zooms are generated by orchestrated Hermes agents using Kimi K2.7, with tasks managed through a Kanban board and a “judge” agent that scores and iterates the output from 6 to 9/10. Additional examples include a 3D game and a Web OS with persistent notes, calculator, paint, and clock apps. The speaker notes some slowness for browser-use tasks but highlights strong long-horizon performance and Moonshot benchmark gains.00:00 Kimi K2.7 Drops00:26 One Sentence App Builder01:03 AI Video Made by Agents02:10 Kanban Orchestrated Workflow03:29 Demos Games and Web OS05:59 Chat Agent Speed Test07:49 Best AI Video Workflow08:33 Benchmarks and Context09:03 Setup Inside Agent OS12:29 AI Profit Vault Pitch14:03 Final Recap and Outro
Transcribe →Claude Fable + Mythos 5 is BANNED!
2d ago00:10:00Tap to summarizeBreaking: Anthropic Pulls Fable-5 & Mythos-5 After US Government Directive (What We Know)The video reports breaking news that Anthropic’s Claude models Fable-5 and Mythos-5 have been abruptly disabled after a US government directive, which reportedly suspends access for foreign nationals (including Anthropic employees), though the creator notes some users still appear to have access and is unsure why. The announcement was received at 5:21 PM ET on June 12 and provided no specific reason, but the creator suggests it may relate to alleged bypass techniques and model use for reading codebases and fixing software flaws. Anthropic says it added strong safeguards with US/UK and third-party help, believes the directive is a misunderstanding, and warns applying this standard broadly could halt frontier model deployments. The creator compares the situation to earlier incidents, notes Opus 4.8 remains available but feels like a step backward, and promotes Agent OS and the AI Profit Boardroom for switching between models and learning AI automation.00:00 Breaking Shutdown News00:44 Testing Model Access00:59 Official Directive Details01:51 Why It Happened03:46 Anthropic Safeguards Statement05:31 Compliance And Disagreement05:58 Still Available Confusion06:38 Hands On With Fable 507:56 Industry Impact Debate08:27 Watch For Updates08:58 Agent OS Promo09:58 Final Sign Off
Transcribe →New Chinese AI Model Is INSANE! (FREE & Open Source)
2d ago00:05:19Tap to summarizeN2 Pro: Free Open-Source Chinese Coding Model Beating Claude & GPT on Benchmarks (260K Context)The video introduces N2, a new free Chinese open-source model with open weights and a 260K-token context window, designed for coding and agentic workflows with strong tool/function calling. It highlights benchmark results where N2 outperforms paid APIs like Claude Opus 4.7, GPT 5.5, and DeepSeek V4 Pro on some tests (including SWE Bench), and notes it is based on Qwen 3.5’s architecture. The model is available on Hugging Face and via a free API on OpenRouter, and can be used inside agents such as Kilocode, Hermes Agent, Claude Code (via an open-source “Free Claude Code” project), OpenClaude, and Pi. The creator demonstrates configuring N2 in Hermes Agent using model profiles, compares N2 Pro and N2 Mini, and shows N2 responding faster than a Gemma 4 setup. The video ends by promoting training and resources in the AI Profit Boardroom.00:00 Free N2 Model Reveal00:29 Benchmarks and Specs00:58 Where to Get It Free01:24 Setup in Hermes Agent02:01 Use with Claude Code02:16 What You Can Build02:32 DeepSeek Comparison02:58 Use Cases and Variants03:28 Speed Test vs Gemma04:18 Wrap Up and Next Steps04:30 AI Profit Boardroom Pitch05:17 Final Thanks
Transcribe →Hermes: Agent OS + Obsidian + Kanban + Paperclip
2d ago00:14:46Tap to summarizeTurn One Hermes Agent Into a Full AI Team (Agent OS + Obsidian Memory Galaxy + Kanban vs Paperclip)The video explains how to expand a single Hermes agent into a coordinated team by plugging Hermes into an Agent Operating System, including voice control via “Hermes Jarvis,” and using Obsidian as a local, markdown-based memory vault. It answers community questions on setting up the Obsidian “Memory Galaxy” view (now built into the latest Agent OS with a markdown setup guide), when to use Hermes’ native Kanban versus Paperclip (more complex dashboards and org charts, especially for orchestrating multiple tools), and whether Hermes profile agents can collaborate via group chat, Telegram, WhatsApp, or within the Agent OS. It also covers migrating notes from OneNote to Obsidian using MCP bridges, organizing multiple clients to avoid data conflation with separate folders and Kanban boards, customizing Agent OS UI toggles, and editing each agent’s soulmd instructions to improve response quality.00:00 Build a Team of Agents00:43 Community Q&A Setup01:08 Obsidian Memory Galaxy03:34 Hermes Kanban vs Paperclip05:50 Voice Jarvis Inspiration07:37 Agents Chat Together08:52 Move Notes to Obsidian10:07 Agents in GoHighLevel10:36 Avoid Client Data Mixups11:26 Customize Agent OS UI11:54 Improve Memory Responses12:56 Wrap Up and Join Boardroom
Transcribe →Hermes Agent Automation Blueprints: Build ANYTHING!
3d ago00:10:22Tap to summarizeBuild Free AI Agents in 1 Click: Hermes Automation BlueprintsDiscover how to use the new Hermes Agent automation blueprints to turn scheduled tasks into powerful AI workflows without writing any code. Learn to automate your daily research and integrate it directly into your memory system for free.00:00 - Intro: New Hermes Automation Blueprints01:31 - Research and Intelligence Workflows02:50 - How It Works: No-Code Copy & Paste03:34 - Automating Your Obsidian Vault Memory05:28 - DevOps, Business Ops & Multi-Skill Workflows06:15 - The 100% Free Automation Stack08:25 - Connecting APIs and Managing Memories09:26 - Join the AI Profit Boardroom
Transcribe →Hermes: New AI Video Game Agent is WILD!
3d ago00:11:00Tap to summarizeBuild a Video Game Studio AI Agent in 20 Minutes (Hermes Agent GameForge Workflow)The video demonstrates building a “GameForge” video game studio agent using Hermes Agent inside an agent operating system to automate workflows beyond personal use. Using the new Hermes Agent Profile Builder, the creator “hires” and trains a game developer agent, then generates playable 3D games from a single prompt; each prompt becomes a Kanban card where tasks can be assigned and iterated. The workflow is summarized as prompt box → forge master (trained agent) → Kanban board → shelf, where finished games can be launched and played in a workspace without terminal setup. The episode shows examples like a neon ring-race flyer and a 3D snake-in-a-cube game, claims four playable 3D games were made in a day, and notes token costs can be reduced by using free or local models. It also promotes the AI Profit Boardroom for the full setup, tutorials, community, and coaching.00:00 Building a Game Studio Agent01:07 Live Demo of AI Games02:49 GameForge Overview02:54 Hiring the Forge Master03:55 One Prompt to a Game04:35 Kanban Board Workflow05:03 Test Run and Iterate05:27 The Game Shelf Hub05:56 Beyond Games for Business06:35 System Recap and Results07:32 Start Small and Save Tokens08:22 Wrap Up and Next Steps09:32 Get the Full Setup10:20 Community and Coaching10:58 Final Thanks and Goodbye
Transcribe →Automate Anything with Hermes Jarvis, here’s how!
3d ago00:08:52Tap to summarizeI Built a Voice-Activated AI Assistant That Remembers Everything (Jarvis + Hermes Agent + ElevenLabs)The video demonstrates a voice-activated AI assistant called Jarvis (built from Hermes Agent) that can open websites, pull memories from an Obsidian vault, create notes, give spoken day summaries, and build projects on command, including generating a working Snake game with live previews and a gallery of everything created. The creator shows features like wake-word listening, conversation history, wall mode, diagnostics such as “show me my numbers,” and viewing a team of agents. The system is powered by Claude Desktop in the background and uses ElevenLabs for voice, with ongoing improvements and multilingual/joke capabilities. The episode explains why housing everything in one dashboard is more convenient than juggling separate tools, mentions optional phone-number access with security concerns, and invites viewers to join the AI Profit Boardroom for the full Agent OS system, trainings, updates, coaching calls, and community.00:00 Jarvis Roasts Me00:13 Grand Intro Request00:48 What I Built This Week01:12 Agent OS Demo Tour01:57 Voice Built Snake Game02:29 Conversation History Previews03:28 How It Works Under Hood04:33 Show Me Gallery Numbers06:03 Why One Dashboard Wins07:03 Phone Number Access Risks07:37 Join AI Profit Boardroom08:48 Final Wrap Up
Transcribe →Hermes Agent: How to Build Apps in 1 Click!
3d ago00:10:48Tap to summarizeBuild Real Apps in One Click with Hermes Agent: The Spark Forge AI Idea-to-App SystemThe video demonstrates an AI app-building system using Hermes Agent that turns ideas into working apps, games, and tools in a single click through an “idea factory” pipeline: drop in an idea, have agents plan it, approve or reject the plan, then automatically implement and ship a runnable app in about three to five minutes. It shows a multi-agent group chat (Claude, Hermes, Gemini) that brainstorms ideas, reads an Obsidian-based memory vault where all projects are logged and organized, and saves winning ideas into the build pipeline. The creator calls the framework the “Goldie Spark Forge,” emphasizing shared memory, a tracked gallery of past builds, rebuild capability, and the ability to use free or local APIs. The video concludes by promoting access to the full system inside the AI Profit Boardroom, including the zip file, prompts, Obsidian setup, tutorials, and coaching.00:00 One Click App Builder00:35 Idea Factory Demo01:06 Agent Group Chat Ideation01:36 Obsidian Memory Vault02:42 Gallery of Built Apps03:06 Goldie Spark Forge Framework04:54 From Idea to Build Steps05:19 Planning Approval and Build06:03 Free APIs and Shipping Flow06:39 Rebuild and Track Everything07:31 Debunking Common Objections09:16 Get the System and Community10:45 Final Thanks and Outro
Transcribe →Claude: How to Build an Agent Operating System!
4d ago00:12:37Tap to summarizeI Built an AI Agent Operating System (Claude + Hermes) That Creates Apps, Games & Websites in 1 ClickThe script showcases a custom “agent operating system” the creator has built over the past few weeks, integrating Claude, Hermes (including voice-activated Hermes Jarvis), Gemini, Antigravity, Codex, and a local/free Claude Code setup to automate building apps, websites, games, SEO workflows, images, videos, voice, podcasts, and research reports. The system includes an ideas factory that turns a single idea into an app or site, a pipeline for one-click generation, and an Obsidian-based “memory galaxy” visualization created by agents. Hermes agents collaborate in teams, can hire additional agents, and are managed via profiles, group chat, and a Kanban-style task board that delegates work across specialized sub-agents. The creator invites viewers to join the AI Profit Boardroom community to download the install, access tutorials, weekly coaching calls, and connect with members.00:00 Agent OS Overview00:20 Game Generator Demos00:33 Hermes Jarvis Voice Agent01:05 Ideas Factory Pipeline01:55 One Click Websites02:16 Memory Galaxy in Obsidian03:10 All Agents Connected03:48 Media Studio One Click04:26 Antigravity and Gallery05:10 AI Agent Company Setup05:48 Hermes Profile Builder06:56 Kanban Team Orchestration07:55 Community Builds Boardroom09:20 More Factories and Outputs11:02 Join the Boardroom12:27 Final Wrap Up
Transcribe →Hermes Desktop + Ollama is Insane (FREE!)
4d ago00:08:13Tap to summarizeHermes Desktop + Ollama Update: One-Command Setup, Multi-Agent Workflows, and Free Local ModelsThis episode covers a new Hermes Desktop update that adds one-click integration with Ollama, letting you launch Hermes agents via a simple terminal command ("ollama launch Hermes Desktop") after downloading and updating Ollama from ollama.com. It demonstrates using Hermes Desktop for multi-agent workflows by spawning parallel sub-agents with isolated contexts, switching between agent profiles and sessions, managing skills, messaging, artifacts, files, and settings, and quickly changing models. The script explains why Hermes Desktop is easier than running Hermes in the terminal and highlights benefits of Ollama such as local and free cloud models, privacy, offline use, and fast model swapping (e.g., Minimax-M3, Gemma 4, Qwen, GLM, Nemotron). It also shows connecting Hermes to channels like Telegram, Discord, Slack, and WhatsApp, and mentions AI Profit Boardroom for the broader Agent OS system and coaching/community resources.00:00 Ollama Integration Update00:27 Multi Agent Workflows00:43 Connect to Messaging Apps01:05 One Command Setup01:39 Why Use Ollama Models01:59 Desktop vs Terminal02:51 Settings and Model Switching03:33 Recommended Free Models05:14 Parallel Agents and Contexts05:38 Why Run Local Models06:03 Recap and Sync Benefits06:55 Agent OS and Community Pitch08:11 Final Thanks and Goodbye
Transcribe →