AI News Today | Julian Goldie Podcast

Ruflo for Claude Code: Build Multi‑Agent Swarms + Automate Research & Content to ObsidianThe video demonstrates Ruflo, a free Claude extension for deploying multi-agent swarms to coordinate autonomous workflows in Claude Code. It shows how to install Ruflo via GitHub CLI commands, verify it’s configured inside Claude, and then prompt Claude to suggest best-use swarms based on the user’s context by connecting to an Obsidian vault for memory. The presenter runs a content production workflow (SEO keyword/article briefing) in the AI agents automation niche, saving outputs directly into Obsidian as markdown while multiple agents work in parallel and report progress. It explains why Ruflo matters (automation, learning over time, persistent memory, tool integrations, scaling up to large swarms), uses a restaurant-kitchen analogy for how routing and specialist agents work, and notes you must explicitly prompt Claude to use Ruflo. The episode ends with Air Profit Boardroom resources, token-usage cautions, and brief Q&A on Hermes configuration and security.00:00 Ruflo Overview00:22 Install and Verify Setup00:58 Finding Best Use Cases01:38 Add Obsidian Context02:22 Choose Workflow and Inputs02:51 Why Ruflo Matters03:47 Swarm Results in Obsidian04:13 How Swarms Work04:45 Prompting and Live Briefs05:31 Full Guide and Recap06:20 Community and Coaching Plug06:40 Live Q&A and Wrap Up

Build an Autonomous AI Company with Paperclip + Hermes Agent (The GOLDIE Method)The script explains how to use Paperclip with the Hermes Agent adapter to run a coordinated team of AI agents instead of a single chat-based agent. It demonstrates building an org chart (e.g., CEO, marketing roles, engineer, tester), setting a mission/goal so all agents share context, and using Paperclip’s dashboard, ticketing system, and scheduled “Heartbeats” to launch agents, delegate tasks via new issues, review and iterate on results, and then expand by adding more agents, goals, and tools. An example shows a Hermes tester completing AI SEO keyword research and generating an SEO strategy with live updates. It positions this workflow as the “GOLDIE Method” (Goal, Org chart, Launch, Delegate, Iterate, Expand) and contrasts Paperclip with Hermes Workspace and Aeon UI, emphasizing multi-agent coordination, multi-provider support, and multi-company setups.00:00 Paperclip With Hermes00:19 Agent Team Dashboard01:49 Goldie Method Overview02:08 Set The Mission Goal02:44 Build The Org Chart03:19 Launch With Heartbeats03:45 Delegate New Issues04:35 Iterate With Feedback05:24 Expand Your AI Company05:58 Mindset Shift Beliefs07:36 Multi Company Examples08:22 Hermes Vs Paperclip Recap10:33 Community And Coaching11:22 Live Q And A Comparisons15:28 Final Wrap Up

Use Hermes Agent for FREE with Step 3.5 Flash (15 Days) — Full Setup GuideThe script demonstrates how to set up Hermes Agent to run for free using Step via the News Portal configuration, highlighting that Step 3.5 Flash is available free for the next 15 days. It walks through installing Hermes from GitHub, running `hermes setup` in the terminal, selecting News Portal, switching to Step Fun/Step 3.5 Flash, skipping remaining configuration prompts, and restarting the gateway to confirm the model is operational. It explains what Step 3.5 Flash is (262K context window, ranked 16th on OpenRouter Weekly), notes it’s strong at reasoning but weaker at coding, and mentions other free options like Qwen 3.6 Plus and OwlAlpha (1M token context on OpenRouter). It also shows how to switch models with `/model` and promotes the AI Profit Boardroom community and training.00:00 Free Hermes Setup00:28 Terminal Install Steps01:05 Verify Step Flash Works01:21 Model Specs Benchmarks02:04 More Free Model Options02:41 Install Switch Models03:46 Training Community Pitch04:19 Live Q&A Wrap Up

Open WebUI vs Hermes Desktop: Best Setup for Using Hermes Agent (Pros, Cons, and Team Access)Julian answers an AI Profit Boardroom question comparing Open WebUI vs the Hermes Desktop app for using Hermes Agent, explaining why most people should avoid the terminal UI and use a friendlier interface. He shows that Open WebUI is simpler and feels like ChatGPT but doesn’t natively surface Hermes features like skills, prompts, knowledge, persona, memory, models, message tracking, channels, or scheduled tasks, while Hermes Desktop provides deeper customization, smoother Hermes integration, office view, gateway connections, profiles, and unified session history across CLI/API/TUI. He recommends starting with Hermes Desktop for day-to-day use, but notes Open WebUI’s key advantage is multi-user access with permissions for teams. He also plugs a full guide inside the AI Profit Boardroom community with prompts, SOPs, and a 30-day roadmap.00:00 Open WebUI vs Desktop00:24 Open WebUI Setup01:14 Why Not Terminal02:17 Side by Side Comparison03:16 Desktop Features Edge04:11 Office View and Tools04:54 Recommendation and Mindset06:08 Deep Dive Desktop Dashboard07:11 What Desktop App Is07:46 When Open WebUI Wins08:22 Boardroom Guide and Community09:48 Live Q&A and AI Stack10:34 Wrap Up and Focus

Claude + Hermes MCP: The Ultimate AI Delegation SystemLearn how to connect Claude to the Hermes agent using the Model Context Protocol (MCP) to automate your workflow. Discover the Goldie Delegation Loop, a new paradigm for AI-powered business automation that turns Claude into the brain and Hermes into the hands.00:00 - Intro: Linking Claude to Hermes01:25 - Managing Permissions & Security02:14 - Live Test: Scheduling Tasks04:24 - The Goldie Delegation Loop04:42 - Brain, Bridge, and Hands Explained08:32 - What is MCP?12:17 - Marketing Agency Use Cases14:19 - OMI & Obsidian Integration

Hermes Agent Tutorial: Run a Free 24/7 AI Worker (Workspace, Swarms, Paperclip, SEO & Mac Computer Use)The video explains how to use Hermes Agent as a free, always-on AI worker to automate tasks like content, research, client work, SEO, and workflows without coding. It answers community Q&As on installing and starting Hermes and Hermes Workspace (running Hermes Gateway, launching Workspace, and troubleshooting terminal issues with Claude), switching models and setting up OpenAI Codex, and exporting reusable skills, templates, and frameworks to share with students. It clarifies swarms vs agents in Hermes Workspace, recommending swarms only for large projects. It discusses integrating Paperclip with Hermes via an adapter and organizing agents with a CEO role, shows SEO tactics for ranking in Google and AI search using useful content, schema, and cross-platform posting, and mentions automating avatar video editing with HyperFrames and HeyGen CLI. It also highlights macOS background “computer use” and using LM Studio with Hermes.00:00 Hermes Agent Overview01:06 Hermes Workspace Setup03:15 Export Skills For Students04:05 Switch Models And Prompting06:54 Join The Community QandA07:10 Paperclip Team Setup08:56 AI Ready Website SEO12:11 Swarms Versus Agents15:56 Hermes World Game Mode17:28 Automation Tools Roundup20:16 Computer Use And LM Studio21:57 Wrap Up And Next Steps

Run Hermes Agent 24/7 for FREE (Qwen 3.6 Plus + OwlAlpha Setup Guide)The video explains how to run Hermes Agent for free using two models: Qwen 3.6 Plus on News Portal and OwlAlpha via OpenRouter, both offering a million-token context window. It walks through the step-by-step setup in the terminal: using Hermes setup, selecting News Portal, logging in, choosing the free Qwen 3.6 Plus model, and testing it, then shows how to switch to OwlAlpha in OpenRouter when token or rate limits are hit. The script highlights Qwen’s speed, multilingual ability, and strengths in analysis, writing, and coding, and notes that free models may log prompts. It also promotes the AI Profit Boardroom community with guides, prompts, training, coaching calls, and automation requests, and answers questions about using Hermes on Android and via Telegram/WhatsApp.00:00 Run Hermes Free00:48 Qwen Setup Walkthrough02:09 Test and Recap02:53 Why Qwen Matters03:51 Token Limits and Backup04:06 OwlAlpha via OpenRouter04:42 Privacy Notes05:22 Wrap Up and Resources05:53 AI Profit Boardroom Tour07:00 Android and Rate Limits Q&A08:25 Final Goodbye

Hermes Agent Computer Use (New Update): Your Mac AI That Clicks, Types & Works in the BackgroundThe video covers a new “Computer Use” update for Hermes Agent that lets an AI operate a Mac desktop in the background—clicking, typing, scrolling, and dragging without moving your cursor or interrupting your work—using an MCP server. The host walks through updating Hermes, installing Computer Use via a CLI command, granting macOS Accessibility permissions, and notes it’s experimental with safety guardrails and approval prompts for risky actions. They demonstrate Hermes opening Apple Notes and creating a new, personalized journal note with ten time-saving ideas, then attempt a more complex Obsidian organization task that proves slower and less reliable. They also show Hermes opening Terminal to run Hermes and type “hello,” discuss model options (needs vision), token/screenshot costs, and how to switch/setup models, and direct viewers to the AI Profit Boardroom for a guide with prompts and a roadmap.00:00 Hermes Gets Superpowers01:02 What Computer Use Does01:40 Install and Update Hermes03:34 Permissions and Safety Notes04:50 How to Use It06:17 Quick Test Open Notes06:53 Auto Journal Note Demo08:37 Obsidian Second Brain Attempt10:18 Prompting Framework11:51 Models Costs and Limits13:37 Hermes Talks to Itself15:50 Results Recap and Limits16:56 Common Objections Answered17:50 Guide and Community Plug18:56 Switch Models in Hermes

OpenClaw 5.9 Pre-Release: Real-Time Discord Voice Agent, iMessage Catch-Up, WeChat + Breaking Change WarningOpenClaw 5.9 appears on GitHub as a pre-release beta, adding major updates including a revamped Discord voice experience with a new default “agent proxy” mode for real-time listening and speaking using OpenAI or ElevenLabs voice models, plus improved interruption and echo handling. It introduces iMessage catch-up so the agent processes messages received while offline, but removes the BlueBubbles method, which can break existing iMessage setups unless migrated to Apple’s direct Mac connection. The update also adds personal WeChat (Tencent Weixin) support, adds Mistral Medium 3.5, retires Gemini 3 Pro in favor of Gemini 3.1 Pro Preview, and adds AWS Bedrock service tier controls. Additional fixes cover Telegram, Slack threads, Discord group chats, startup performance, backups, Windows/macOS issues, Docker cleanup, and security, alongside guidance to back up and test before updating.00:00 OpenClaw 5.9 Overview00:47 Beta Warning and Roadmap01:22 Discord Voice Overhaul01:44 Agent Proxy Details03:36 iMessage Catch Up Mode04:36 Breaking Change Blue Bubbles05:14 WeChat and Model Updates05:58 CLI and Platform Fixes06:33 Community and Tutorials Plug07:04 Major Bug Fix Roundup09:43 How to Update Safely11:13 Final Wrap Up

237 Ways to Use Hermes Agent for Free (Automate Email, Build Websites, Fix Buggy AI Tools)The video showcases a curated list of 237 real-world Hermes Agent use cases and demonstrates how non-developers can set up automations step by step. Key examples include scheduling Hermes to summarize an email inbox and post the digest to Slack or Discord, having Hermes research you online and deploy a landing page using tools like Firecrawl and Netlify, and using Hermes’ systematic debugging skill to troubleshoot a buggy local OpenClaw setup by referencing GitHub issues and terminal logs. It also highlights Hermes Desktop, a free Mac app that provides a UI to manage sessions, profiles, models, tools, memory, and chat. The script argues Hermes is a 24/7 AI employee with memory and autonomous actions, addresses common objections, and promotes a full guide and community in the AI Profit Ballroom.00:00 237 Free Use Cases00:53 Use Case Library Tour01:37 Email Summary to Slack02:10 Ask Hermes to Build03:59 Auto Landing Page Deploy04:43 Fixing OpenClaw Bugs06:50 Hermes Desktop UI08:30 Categories and Recap09:19 Limiting Beliefs Busted10:14 Full Guide and Offer12:00 Live Q&A and Wrap

Build a Perfect AI Memory System (Hermes Agent + Obsidian + Omi) — Free SetupThe script explains how to make a Hermes Agent far more useful by giving it persistent memory using three free tools: Hermes Agent, Obsidian, and Omi. Omi runs in the background recording screen and microphone activity to generate daily “memories,” then syncs them into an Obsidian vault as readable markdown notes; Hermes can then read those local files to understand your goals, projects, schedule, and preferences without re-explaining context each session. The presenter demonstrates syncing to increase the memory count and shows how this added context helps Hermes suggest personalized improvements, dashboards, and automations like daily digests, memory cleanup, content idea extraction, and weekly performance reports. The video addresses common objections (complexity, manual upkeep, cost, and needing memory) and introduces the “Infinite Context Engine” framework, plus mentions a guide, prompts, and community/coaching resources in the AI Profit Boardroom.00:00 Perfect Memory System01:03 How the Setup Works02:43 Omi to Obsidian Sync03:07 Chatting With Memories04:08 Hermes Reads Your Vault05:25 Automation Ideas From Logs07:06 Why Memory Beats Smarts08:02 Three Free Tools Explained09:41 Common Objections Debunked11:43 Infinite Context Engine12:36 Guide and Community Offer14:29 Live Q&A Wrap Up

Build a Custom AI Content Rewriter Automation (No Code) + 4 Fixes for Repetitive AI OutputThe video shows a live, real-time build of a no-code AI automation that rewrites existing content for any audience or niche in seconds using Claude and a few prompts. The creator walks through a community member’s request inside the AI Profit Boardroom, tests her original case-study rewriting prompt, notes issues with messy and repetitive outputs, and then improves the prompt to be more relevant and actionable. Key fixes include adding important instructions at the top of the prompt, giving the AI a list of repetitive elements to avoid, using Claude instead of ChatGPT for better writing, and creating a Claude project with example files and custom instructions that specify what to avoid. It ends with an invitation to post automation requests and join the AI Profit Boardroom for coaching, community, and updated trainings.00:00 Build AI Automation Live00:44 Member Request Overview01:46 Testing The Prompt02:24 Rewriting Approach Shift03:20 Four Prompt Fixes04:57 Daily Builds In Community05:28 Join AI Profit Boardroom05:51 Courses And Daily Updates06:15 Final Link And Wrap

Make Hermes Agent 10x More Powerful: Autonomy Settings, Local LLMs, and Parallel Agent SwarmsThe video explains how to upgrade Hermes Agent from a basic chat tool into a more autonomous system by adjusting key settings and workflows shared in a Q&A from the AI Profit Boardroom community. It covers solutions for Mac Mini performance issues by running Hermes in the cloud (e.g., Hostinger), and addresses concerns about agents feeling non-proactive by editing the soul.md file to change how the agent thinks and responds, plus using /goal for an autonomous task loop. The script also shows how to run Hermes on Windows/Mac, switch models with /model, and connect to local LLMs via LM Studio or Ollama. It demonstrates running multiple agents in parallel using Hermes Workspace (swarm feature), outlines using profiles for different Telegram groups, compares Hermes vs OpenClaw, and ends with an invitation to join the AI Profit Boardroom for coaching, tutorials, and community support.00:00 Hermes Agent Upgrade00:54 Hosting Performance Fixes01:38 Autonomy Problem Setup03:09 Soulmd Prompt Tuning05:26 Goal Loop Automation06:37 Local Setup Basics07:03 Local LLM Model Switch08:21 Parallel Agent Swarms10:57 Hermes Versus OpenClaw13:12 Workspace UI Tour15:22 Telegram Dedicated Agents16:17 Self Hosted Company Agent17:34 Wrap Up And Community

Elon Just Gave Claude 220,000 H100s: Anthropic’s Compute Surge, Mythos, and What Changes for BusinessThe script explains how Anthropic’s recent compute constraints behind Claude—rate limits, peak-hour slowdowns, and interruptions—are being rapidly eased after Anthropic signed a live deal to use SpaceX’s Colossus-1 GPU cluster in Memphis (over 300 MW and 220,000 NVIDIA H100s). As a result, Anthropic doubled Claude Code five-hour rate limits for paid plans, removed peak-hour reductions, and significantly increased Opus API rate limits. It argues Elon Musk’s motivation is largely economic (idle GPUs after xAI moved training to Colossus-2) and strategic against OpenAI. The script also covers Anthropic’s broader infrastructure deals (Amazon, Google/Broadcom, Microsoft/NVIDIA, Fluid Stack, and reported Google Cloud spend), enterprise ambitions, and the unreleased Mythos model’s security-testing capabilities, plus related government controversy and implications for business workflows and AI coding competition (including Cursor).⁠00:00⁠ Elon Powers Claude⁠00:43⁠ Claude Compute Crunch⁠01:47⁠ SpaceX Colossus Deal⁠03:45⁠ Why Elon Helped⁠05:00⁠ Business Impact Boost⁠06:54⁠ Mythos Security Leap⁠08:48⁠ What It Means Now⁠10:11⁠ Cursor And GPU Wars⁠11:24⁠ Stop Waiting Start Building⁠12:57⁠ Final Takeaways

Automate Anything with ChatGPT: Build Custom AI Agents FastLearn how to save hours every week by building custom ChatGPT automations for your business tasks. This video demonstrates a live build of a client proposal generator using a unique strategy to optimize AI performance.00:00 - Intro00:26 - Custom Automation Strategy01:17 - Setting Up a Custom GPT01:54 - Using Claude for Expert Prompts02:47 - Configuring the Automation03:24 - Live Testing: Proposal Generator03:58 - Recap & Community Access

Hermes Workspace: The Ultimate Command Center for AI AgentsTransform your AI agents from simple chat interfaces into a powerful command center with Hermes Workspace. Learn how to manage agent swarms, schedule tasks, and give your AI long-term memory with no coding required.00:00 - Intro: Why you need a Workspace01:07 - Installing Hermes Workspace02:12 - Terminal vs. Workspace UI04:52 - Dashboard & File Management06:13 - Hermes vs. Aon UI08:10 - Automation, Jobs & Kanban09:14 - Mastering Swarm Mode10:20 - Smart Routing & Memory14:59 - The Agent Empire Framework

Run Hermes Agent for FREE! (New Owl Alpha Model Setup)Learn how to set up and run the powerful Hermes Agent completely for free using the brand-new Owl Alpha model via OpenRouter. This guide shows you how to automate your workflows without writing a single line of code, even if you are a total beginner.00:00 - 00:00 - Intro: The Hermes Agent Upgrade01:23 - How to Install Hermes Agent02:15 - Connecting Free OpenRouter APIs03:41 - Setting Up the Owl Alpha Model05:00 - The Power of Self-Improving Agents06:40 - Owl Alpha vs. Traditional Models07:50 - AI Agent Myths Debunked08:34 - 30-Day AI Business Roadmap

Boost Your Hermes Agent: Full Setup, UI Tips & Mobile AccessLearn how to optimize your Hermes agent for maximum performance, whether you're running it locally or on a VPS. We explore the best UI alternatives to the terminal, how to access your agent from your iPhone, and the hardware you actually need for results.00:00 - Intro: Fixing Your Hermes Agent00:30 - AI Profit Boardroom Q&A01:16 - Fixing Performance & RAM Issues03:04 - Hermes Workspace vs. Terminal UI05:02 - How to Use Hermes on Your iPhone06:17 - Creating Videos with Hyperframes07:10 - Best Hardware for Local AI08:55 - Why Hermes is Trending Globally

Hermes Agent Desktop App (Free) for macOS: Setup + Kanban, Memory, Scheduled Tasks & ProfilesThe video introduces a new free Hermes Agent desktop app for macOS that replaces the messy terminal experience with a clean, organized interface. It shows how to set it up by running Hermes Web UI locally, downloading the latest desktop app release, dragging it into Applications, and updating it, while demonstrating real usage like building and deploying a website via Netlify using a personal access token. The host tours key desktop features including chat history, scheduled tasks, a Kanban board, skills, memory, spaces for local files, profiles, to-dos that auto-update, insights, a dashboard, and logs for errors. It explains switching and creating profiles (optionally with API keys) and argues the dedicated app is more persistent and easier than a browser or terminal, with a built-in test connection.00:00 Hermes Desktop App Overview01:01 Download and Install on Mac01:46 Update and First Launch02:05 Real World Demo Website Build03:09 Hosting and Netlify Workflow04:49 Desktop UI Tour Tasks to Logs06:57 Why Desktop Beats Terminal07:44 Profiles Setup and Switching08:14 Common Concerns Answered08:54 Roadmap Training and Community09:59 Skills Plugins MCPs and Profiles10:33 Wrap Up and Goodbye

Claude + Rufflo Agent Swarm: Set Up 100 AI Agents (Free) with Persistent MemoryThe script demonstrates how to upgrade Claude Code using Rufflo (Roughflow), an open-source multi-agent orchestration layer that enables up to 100 specialized AI agents to work in parallel via coordinated “swarm” topologies (hierarchical, mesh, adaptive). It contrasts plain Claude Code with Rufflo’s added features like 98 agents, 60 commands, 30 skills, MCP server hooks, workspace files, background workers, a comms layer, and a persistent vector memory system using HNSW for fast recall across sessions. The video walks through installing Rufflo in the terminal, choosing presets, swarm topology, concurrency, and memory backend, then running a swarm example to build an AI SEO website with roles like architect, front-end dev, SEO specialist, and reviewer. It also notes a web UI option at rufflo.io, integrations beyond Claude, built-in validation/audit trails, and promotes additional training via aiprofitboarding.com and Hermes guides.00:00 Claude Gets Supercharged00:48 What Is Roughflow01:31 Key Features Breakdown02:07 Install and Setup Walkthrough02:54 How Swarms Work03:38 Agents and Web UI Options04:05 Config Presets and Topologies06:23 Persistent Vector Memory07:03 Live Demo Building a Site07:56 Common Objections Answered09:32 Results and Recap10:27 Training and Community Plug11:25 Hermes and Q&A Wrap Up

Hermes HUD: Free Web UI Upgrade for Hermes Agents (Setup + Dashboard Tour vs Hermes Workspace)The video introduces Hermes HUD, a free open-source web UI that makes Hermes agents easier to control than using the terminal by providing a live dashboard to monitor agents in real time, chat in-browser, schedule tasks, diagnose issues, and swap AI models from one screen. The host shows two installation options (pasting commands in the terminal or asking Hermes to install and sync the plugin), gets it running locally in about 2–3 minutes, and tours key sections including Chat, Agents (showing many live agents), Health diagnostics (highlighting broken API keys), Projects, Scheduled Tasks, Sessions/Memory, Plugins, Models, Providers, and Gateways. They compare it with Hermes Dashboard (no chat) and briefly with Hermes Workspace, noting Workspace feels cleaner and offers features like Swarms, while HUD’s biggest benefits are chat and centralized management.00:00 Hermes HUD Upgrade00:52 Install and Sync Setup02:25 HUD Launch and First Look02:58 Chat and Dashboard Basics04:10 Tasks Projects and Health04:41 Agents Models and Providers06:26 What Matters vs Ignore06:42 HUD vs Workspace Comparison07:16 Wrap Up and Training Offer08:07 Live Q&A OAuth Notes

Hermes Agent Overtakes OpenClaw on OpenRouter: Why It’s Winning (and What to Do Next)The video explains how Hermes Agent became the #1 AI agent on OpenRouter, surpassing OpenClaw with 271B tokens versus 245B, despite launching in February 2026 and still being in early beta. The host attributes Hermes’ rise to reliability and ease of use, contrasting it with OpenClaw’s frequent updates that reportedly make it worse, including broken workflows, confusing UI behavior, login issues, and errors like missing API keys even when using OAuth. Live terminal demos show Hermes switching models smoothly while OpenClaw struggles to run and respond. The discussion also touches on perceived safety, community momentum (nearly 1,000 contributors and 140K GitHub stars), business automation use cases like SEO/content workflows, and a recommended GUI option, Hermes Workspace, while predicting Hermes’ growth will continue unless OpenClaw becomes stable.00:00 Hermes Hits Number One01:03 OpenRouter Charts Breakdown02:25 Why OpenClaw Is Slipping05:02 Live Demo OpenClaw Fails06:33 Hermes Just Works Demo08:41 Feature Creep vs Reliability09:41 Business Automation Results11:50 Community Moat and Momentum13:45 Best Hermes Dashboard14:22 Wrap Up and Training Offer

Run Hermes AI Agent Locally for Free with LM StudioLearn how to run the powerful Hermes agent locally and for free using LM Studio. This step-by-step guide shows you how to set up a private, offline AI system using high-performance models like Quen and Gemma on your own computer.00:00 - Intro: Free Local AI Agents00:41 - Setting Up LM Studio01:09 - Choosing the Best Local Models02:03 - Starting the Local Server02:41 - Connecting Hermes to LM Studio03:36 - Switching Models & Providers05:06 - Why Use Local AI Agents?06:01 - Implementation & Next Steps

New Codeex Update: Control Your Browser with This AI AgentCodeex has launched a game-changing update that allows a powerful AI agent to control your Chrome browser directly. Discover how to automate repetitive web tasks, navigate sites, and use background tabs to skyrocket your productivity.00:00 - Intro: New Codeex Browser Agent00:31 - Live Demo: Navigating Chrome01:16 - Step-by-Step Setup Guide01:41 - Enabling the Chrome Plugin03:01 - Understanding Usage Limits03:52 - Multi-Tab & Background Work05:02 - Join the AI Profit Boardroom

Hermes Agent V0.13: Build Your Own FREE Autonomous AI TeamDiscover the massive updates in Hermes Agent V0.13 Tenacity, the open-source tool that lets you run a team of autonomous agents for free. Learn how to use multi-agent Kanban boards, the new goal-locking feature, and advanced video analysis tools to automate your business.00:00 - Intro: Hermes V0.13 Tenacity01:26 - Multi-Agent Kanban Boards04:03 - Forward/Goal Persistence Mode05:57 - Video Analysis & Hyperframes07:32 - Voice Cloning & New Languages10:12 - Security Fixes & MCP Support11:40 - New Dashboard & Plugins14:08 - 10 Biggest Updates Summary

Hermes Agent v0.13 “Tenacity” Release: Multi‑Agent Kanban, Persistent Goals, Session Recovery & Security UpgradesHermes Agent released v0.13, the “Tenacity” update focused on reliability so agents finish tasks instead of getting stuck, drifting, or crashing. The script highlights the team’s rapid development pace (864 commits, 588 PRs, 295 contributors in a week) and explains how to update via the terminal command “Hermes update.” Key additions include multi-agent Kanban for parallel work with heartbeat monitoring, zombie detection, automatic retries, and a hallucination gate; a /goal command to prevent objective drift (“Ralph loop”); session persistence through gateway restarts; and Checkpoints V2 for cleaner state saving with pruning and disk guardrails. It also covers security fixes (eight high-severity issues, redaction on by default, Discord permissions fix, WhatsApp rejecting strangers), new model support, video analysis, voice cloning, expanded messaging platforms, UI/plugin management improvements, self-linting file writes, no-agent cron mode, SearXNG search, new optional skills, and broader language support.00:00 Tenacity Release Overview01:08 Update Stats and Install02:03 Multi Agent Kanban02:56 Reliability Safeguards03:24 Quick Community Invite03:49 Persistent Goal Command05:11 Session Persistence06:04 Checkpoints V2 Storage06:27 Security Fixes07:33 New Models and Providers08:15 Video and Voice Tools09:02 Messaging and Dashboard09:40 Linting and Cron Mode10:34 Search Skills and Languages12:06 What It Means for You13:14 Final Call to Action13:51 Wrap Up and Thanks

Hermes Agent: Best UIs, Workspace Kanban, Desktop App & Fixing API Key IssuesThe script explores practical ways to get more out of Hermes Agent by improving the user experience beyond the terminal, including testing the open-source Hermes Web UI for web/phone use, a desktop wrapper app, and a new terminal UI dashboard with themes, tabs, and profile switching. It clarifies Hermes is free/open source but requires choosing a model/API (paid via a ChatGPT subscription or free options like OpenRouter’s OwlAlpha), then walks through troubleshooting a failed OpenRouter API issue by swapping providers via Hermes setup and updating keys. The presenter demos Hermes Workspace’s new Kanban feature for assigning tasks to agents, discusses stability and configuration challenges with agents/extensions, compares Hermes with Claude Code (UI, reliability, customization, cost), answers audience questions, and ends by promoting AI Profit Boardroom trainings and community support.00:00 Hermes Agent Overview00:49 Free Models And APIs01:29 Install Hermes Web UI02:24 Fix API Key Errors02:58 Switch Models In Setup05:15 Workspace Kanban Tasks06:40 Hermes Desktop App09:02 Terminal UI Dashboard11:04 Agent Swarms And Stability13:26 Hermes Vs Claude Code15:13 Themes And Final Thoughts16:44 Wrap Up And Community

OpenClaw 5.6 Fixes the 5.5 Doctor Disaster — Stability, Trust & What to Do NextOpenClaw 5.6 releases amid community frustration after 5.5 broke setups by having the Doctor repair tool silently switch some users from ChatGPT/Codex subscription OAuth connections to pay-per-use API routing, causing agents to fail or unexpectedly incur usage charges. Version 5.6 reportedly stops Doctor from altering connection routes and provides a recovery path using commands like setting the OpenAI Codex GPT-5.5 model and validating config, alongside a documented guide. Additional fixes address add-on crashes caused by hidden request data and prevent agent work queues from freezing on webpage fetch timeouts. Reactions are split: some report major performance improvements, while others cite repeated breakages, memory loss scares, and consider switching to Hermes or rolling back. The script advises not updating unless necessary, always backing up, tracking stable versions, and highlights the broader tradeoff between rapid agent innovation and reliability for business use, plus mentions a paid community offering coaching and roadmaps.00:00 OpenClaw 5.6 Fallout01:01 Doctor Tool Broke Billing01:56 How 5.6 Fixes It02:22 Other Stability Fixes03:08 Community Reactions Split04:02 Speed Versus Stability05:02 Update Safety Checklist06:19 Bigger Agent Trend07:24 Learn Early Advantage08:04 Coaching Community Pitch08:52 Hermes Migration Option10:00 Final Wrap Up

New Hermes Agent Skill: AI Now Controls Your Browser (No Code)Learn how to equip your Hermes AI agent with the Browser Harness skill to automate searches, bookings, and form-filling for free. This self-healing tool learns as it works and can run 24/7 in the cloud to handle your manual web tasks.00:00 - Intro: AI Browser Automation00:51 - What is Browser Harness?02:34 - 3 AI Browser Superpowers03:35 - How AI Browser Use Works04:13 - Setup Guide: Remote Debugging05:38 - Demo: Hermes Navigation & Learning07:11 - Summary & Cloud Integration

Google’s Secret AI Agent “Remy” Could Rival OpenClaw (Gemini 24/7 Agent Leaked)The script discusses reports that Google is internally testing an AI agent code-named Remy inside a staff-only version of the Gemini app, supported by an internal document obtained by Business Insider and confirmations from two sources, while Google declined to comment. Remy is described as a 24/7 personal agent for work, school, and daily life that can take actions on a user’s behalf and is expected to be deeply integrated across Google services like Gmail, Calendar, Drive, and Docs, potentially positioning it as an OpenClaw alternative. The speaker expects a potential announcement around Google I/O in May 2026 and highlights key unknowns such as background operation, persistent memory, and third-party integrations outside Google. The script also notes broader momentum around AI agents across the industry, including chipmakers’ interest.00:00 Remy Leak Revealed01:00 Launch Timing and I O Hype02:08 Why Remy Could Go Mainstream02:57 From Chatbot to Action Agent04:50 Memory and Ecosystem Advantage06:15 Outside Integrations and Offline Agents06:57 Google Agent Predictions for 202607:46 Unknowns to Watch at I O08:09 Remy Recap and Confirmations09:02 Community Invite and Wrap Up

OpenClaw 5.4 Beta: Faster Google Meet Voice, New Status Labels, Tool Summaries + Should You Update?This episode covers the OpenClaw 5.4 beta update, highlighting a major speed improvement for Google Meet voice calls when agents dial in via Twilio, with smoother streaming, queue management, and interruption handling powered by Google’s Gemini voice system. It also introduces one-word progress status labels (thinking/searching/writing) across Discord, Telegram, Slack, Matrix, and Microsoft Teams, with cleaner formatted boxes and trimming for long tool runs. OpenClaw now shows summarized tool outputs by default (with an optional raw mode), adds dashboard refinements (active agent indicator, collapsible scheduled tasks, and collapsed duplicate messages), and improves startup performance by deferring heavy initialization and speeding add-on loading. The script advises caution because it’s a beta, recommends backing up first, explains how to install beta and roll back to stable, and suggests waiting if you don’t need the new features.00:00 Open 5.4 Beta Overview00:31 Google Meet Voice Boost01:45 Progress Labels in Chats02:33 Cleaner Tool Summaries03:05 Dashboard and Startup Speed04:05 Should You Update04:28 Backup and Install Steps05:08 Community and Coaching Plug05:46 Final Reminder and Outro

OpenClaw 5.3 Beta: Reliability Fixes, New File Transfer Plugin, and Should You Update?OpenClaw 5.3 beta is presented as a reliability-focused update addressing recent issues like crashes, broken plugins, gateway problems, and undelivered messages. It aims to fix plugin install/update/uninstall failures, stale manifests, missing package directories, and improve Claw Hub fallback error handling. New features and fixes include a file transfer plugin (16MB limit, path-allowlist security), improved Discord typing indicators and status reaction lifecycle, Telegram topic reply delivery fixes and media group timing controls, WhatsApp channel/newsletter messaging plus accurate group-delivery confirmation, and Slack Block Kit trimming to prevent message failures. Startup is faster via deferred loading, a new cross-channel progress streaming mode and /steer command are added, macOS update/doctor automation is improved, memory/recall stability is enhanced, and security tightens around secrets and plugin integrity. The script advises not rushing to update if stable, to back up first, and to test or wait for reports in Discord.00:00 Beta Overview00:28 Plugin Fixes01:16 File Transfer Plugin01:39 Messaging App Updates03:19 Faster Gateway Startup03:35 Progress And Steer04:08 Mac Updates And Stability04:51 Security Hardening05:11 Should You Update05:56 Community And Wrap Up

Open Claw 5.2 Update: Grok 4.3 Default, Major Plugin & Gateway Fixes, Messaging + Voice UpgradesOpen Claw 5.2 is a major release adding Grok 4.3 as the new default XAI model and overhauling the plugin system with improved install/update/repair behavior, dependency reporting, a plugins list flag to check states without loading everything, expanded Doctor repairs, beta-first fallback logic, and an MPM-first registry approach with Claw Hub layered on top. Gateway and agent performance improves by loading only needed plugins, fixing an aggressive heartbeat bug, speeding large session stores with bounded reads and better indexes, and adding a structured heartbeat response tool. Messaging fixes span Discord interaction persistence across restarts and rate-limit handling, Telegram long-message splitting and voice/thread fixes, WhatsApp channel/newsletter routing and quoted image visibility, Slack DM/workspace/app-home and thread tracking, and Signal group allow lists and media size limits. Voice/TTS gains extra-body passthrough, better Twilio/Google Meet routing, and per-call memory; web search adds diagnostics, filtering, retries, and clearer configuration errors, with cautions to back up and update only if needed.00:00 Open Claw 5.2 Overview00:19 Grok 4.3 Default Model00:49 Plugin System Rebuild02:29 Agents and Gateway Performance04:16 AI Profit Board Promo04:50 Messaging Channel Fixes07:41 Voice Calls and TTS08:49 Web Search Updates09:27 Should You Update11:18 How to Update Quickly11:38 Wrap Up and Preferences

Aon UI: The Free Open-Source Dashboard to Control OpenCL (and Multiple AI Agents) From One PlaceThe video shows how to set up Aon UI, a free, open-source desktop dashboard that upgrades OpenCL agent management by replacing messy terminal and gateway workflows with a cleaner UI. The creator demonstrates downloading and updating Aon UI, connecting it to a running OpenCL gateway, and using the dashboard to view, chat with, and switch between multiple parallel agents (e.g., OpenCL, Claude Code, Hermes) in one place, including from a phone. Key features highlighted include conversation history, exporting/renaming/pinning chats, task scheduling, model selection, remote agent connections (e.g., VPS), teams with team leaders, skills upload/import, local file access for assistants (PowerPoint/Word/Excel), voice input, timeout controls, and a desktop pet shortcut. The video closes by promoting the AI Profit Board community for a full roadmap and SOP.00:00 OpenCL Dashboard Upgrade01:01 What Aon UI Does01:24 Download and Install01:37 Multi Agent Teamwork02:35 Connect OpenCL Gateway03:08 Why It Beats Default UI03:59 Settings Models and Remotes04:50 Parallel Chats and Projects06:05 Teams Skills and Desktop Pet07:16 Recap and Community Outro

Hermes Persistent Goals: Run Autonomous AI Agent Projects With One Command (Free Update)The script explains Hermes’ new free update, Persistent Goals, which lets the Hermes agent pursue a single objective autonomously in a loop until completion without frequent prompting. After updating via “hermes update,” users can set a goal with /goal, monitor progress with /goal status, and manage execution with /goal pause, /goal resume, and /goal clear, on both the CLI and gateway. The feature uses a supervisor/judge model to evaluate after each turn whether the goal is complete, continuing as needed within a configurable turn budget (default shown as 20), and users can adjust max turns and the judge model/provider in config. A demo goal builds an SEO-optimized blog website, generates files, and deploys to Netlify, and the script promotes a fuller guide inside the AI Profit Boardroom community.00:00 Goals Update Overview00:40 Persistent Goals Explained01:13 Install and Commands02:03 Live Demo Build Blog02:42 Loop Status and Turn Budget03:51 Use Cases and Behavior04:41 Resume Pause and Config05:35 Website Output and Recap06:31 More Resources and Outro

Hermes Workspace Agent Swarms (Free Update): Run a Team of AI Agents in Parallel + Mobile AccessThe script introduces Hermes Workspace’s free Agent Swarms update, which lets users run multiple Hermes AI agents simultaneously with coordinated roles (planner, builder, reviewer) to avoid agents getting stuck doing tasks sequentially. It shows how to install the free plugin via terminal, run Hermes Gateway, launch the Workspace UI on localhost, update an existing setup, and access the new Swarms section (including optional mobile access). The presenter demonstrates adding preset or custom swarm roles with embedded system prompts and skills, routing a mission by providing a goal, and troubleshooting blocked agents by adjusting settings like the API. A demo swarm builds an SEO-focused automation blog, generating keyword research, competitor analysis, templates, a 90-day content plan, internal linking strategy, and markdown outputs within minutes. The video notes potential bugs and suggests using Claude Code or Hermes locally for setup help, then promotes training in the AI Profit Boardroom and recaps Hermes, Workspace, and Swarm Mode basics.00:00 Agent Swarms Overview01:06 Install and Launch Workspace02:07 Update and Swarms Menu03:01 Roles and Custom Agents03:43 Routing a Real Mission04:49 Office View and Troubleshooting05:19 Swarm Outputs SEO Blog Build07:31 More Features and Caveats08:05 Community and Final Recap

00:00 OpenClaw 4.29 Release Overview00:34 Important Stability Warning00:59 Group Chat Behavior Changes02:25 Follow Up Commitments Feature03:44 People Wiki Memory System05:17 AI Profit Board Community05:46 Nvidia Provider Integration06:23 Message Steering System06:58 Security and Tool Profiles07:22 Channel Platform Improvements07:54 Startup Performance Enhancements08:26 How to Update Safely09:29 Final Thoughts and Community

Hermes Agent V0.12 just dropped — and it's a massive update.This free release (the "Curator Update") brings 1096 code changes, 360 bug fixes, and 213 community contributors. Here's what's new:🧹 Autonomous Curator — runs every 7 days, cleans up old skills, merges duplicates, and keeps your agent sharp automatically⚡ 57% faster startup times🎵 Spotify integration — play music, search songs, manage playlists through your agent📹 Google Meet plugin — your agent can join calls, transcribe, and follow up for you💬 19 messaging platforms now supported (including Microsoft Teams and Tencent YABA)🤖 LM Studio, Comfy UI, and Touch Designer support added🔄 Remote model catalog — new models appear automatically without needing to updateTo update, just run: hermes update00:00 Introduction to Hermes V0.1200:54 How to Update01:26 Autonomous Curator Feature02:58 Performance Improvements03:18 LM Studio Integration03:54 Spotify Integration04:13 Google Meet Plugin05:17 What Changed Overview06:08 Faster Startup Times06:32 Spotify and Google Meet06:51 New Chat Platforms07:06 Additional Features and Providers07:32 Comfy UI and Touch Designer07:46 Remote Model Catalog08:08 Community Contributions08:25 Setup Guide and Recap09:23 Community and Resources

ChatGPT Codex Is Now a Full AI Agent (20% Faster): Email, Browser, Apps, Automations & WebsitesThe script showcases a major ChatGPT/OpenAI Codex update that turns Codex from a coding tool into a full AI agent for everyday work, including controlling the computer and browser, opening apps, managing Gmail, connecting calendar/files, and running scheduled daily automations. The presenter demonstrates installing a Gmail plugin, summarizing inbox requests, drafting/sending an automated daily email update with approval controls (auto-review/full access), and running tasks in parallel while Codex builds a website and navigates it autonomously. They highlight a cleaner design, role-based onboarding, automation templates, and improved computer/browser performance that’s 20% faster. Additional examples include creating slides and spreadsheets, using local apps like Calculator, building games, and having Codex set up other AI tools for non-technical users. The video ends by promoting a paid community and training with tutorials, coaching calls, and support.00:00 Codex Agent Reveal00:50 What’s New in Codex01:45 Connecting Gmail and Permissions02:41 Inbox Summaries and Scheduled Emails04:12 Parallel Agents and Website Build05:50 Browser Control Demo06:43 Slides Spreadsheets and Projects07:59 Local App Control and Reliability09:05 Automation Templates and Why It Matters10:18 Real World Use Cases11:23 Roadmap and Community Offer12:18 Final Thanks

OpenClaw 4.27 Release: Deep Infra Provider, Codex Computer Use, and Major Reliability FixesOpenClaw 4.27 focuses on reliability and stability, adding Deep Infra as a built-in provider for cheaper access to many AI models via one API key across chat, images, audio, video, embeddings, and more. It introduces Codex Computer Use so agents can control the desktop through a setup flow with fail-closed safety checks. File attachments in chat now properly stage non-image files (PDFs, docs, spreadsheets) instead of silently dropping them. Model selection is stricter, preventing silent model switching and making cron jobs fail closed when the chosen model is unavailable unless explicit fallback lists are configured. Major channel fixes improve Telegram (clear token errors, timeouts, preserved images), Slack (ping/pong keepalives, download timeouts, reset phrase handling), Discord (private-by-default replies and async interactions), and Matrix (no duplicate messages), plus faster gateway startup, outbound proxy routing, improved Windows restart handoffs, cleaner session resets, and more reliable memory “dreaming” with caps and retry behavior.00:00 OpenClaw 4.27 Overview00:36 Deep Infra Provider01:48 Codex Computer Use02:52 File Attachments Fixed03:30 Strict Model Selection04:44 Coaching Community Plug05:23 Telegram Stability Fixes06:27 Slack Reliability Updates07:35 Discord Threading Fixes08:37 Gateway Startup and Proxy09:58 Sessions and Memory Reliability11:09 Update Advice and Wrap Up

Hermes AI Agent + ComfyUI: Generate Free Local Images, Video & Audio (No Subscriptions)Hermes’s AI agent has a new ComfyUI skill that lets you generate photorealistic images, video, and audio for free from your computer with no subscriptions, API costs, or complicated setup, and it can even be triggered from your phone. The episode walks through updating Hermes via the terminal, loading the ComfyUI skill, and choosing between a local install or a cloud option using Comfy Cloud (which requires an API key). It explains what ComfyUI is, shows how Hermes installs and runs it locally, and highlights model options including Flux (about 12GB) plus lightweight, general-purpose, and higher-quality video choices. The script also tours ComfyUI templates and utilities like image-to-video, segmentation, upscaling, and background removal, and ends by promoting the AI Profit Board community, coaching calls, tutorials, and courses.00:00 Hermes Unlocks ComfyUI00:55 Update Hermes to Install01:51 Load Skill and Choose Setup02:21 What ComfyUI Actually Is03:09 Local Models and Flux Options03:47 Templates and Editing Tools04:37 Flux Workflows From Your Phone05:22 Sidebar Tour and 11Labs06:46 Troubleshooting With Hermes07:11 Community and Training Outro

Set Up Hermes AI Agent in 1 Click (Free Cloud, Free Local, or Hosted in 20 Seconds)The script explains how to get the Hermes AI agent running quickly with minimal technical effort, outlining three one-click setup options: a free cloud model approach, a free local setup on your own computer, and a hosted “Max Hermes” option on the Minimax platform. It first instructs viewers to download and run Ollamaa, choose a model (suggesting Deep Seek for general tasks), then copy a provided command into the terminal to install Hermes. It contrasts cloud models (free but token-limited) with local models like Gemma four (lightweight but requires downloading and stronger hardware), and mentions recommended models and that Hermes works with over 70 skills. It also demonstrates launching Max Hermes in Minimax, noting tradeoffs like limited integrations, and ends by promoting additional Hermes and AI agent training in the AI Profit Board community.00:00 Hermes One Click Setup00:50 Install Ollamaa First01:08 Pick a Cloud Model02:02 Run Hermes Locally02:52 Cloud vs Local Tradeoffs03:20 Max Hermes Hosted Option04:16 Limits and Perks05:27 Recommended Models and Skills05:59 NVIDIA Nano Omni Option07:13 GitHub Help with Claude07:52 Wrap Up and Next Steps08:06 Training and Community Plug

Run the Hermes AI Agent in Aion UI (100% Free) — Multi‑Agent Dashboard Setup GuideThe video shows how to run the Hermes AI agent inside Aion UI for free instead of using a terminal, highlighting Aion UI as a free, open-source dashboard for managing multiple agents like Hermes, Claude Code, OpenClaw, Gemini CLI, and others. It walks through downloading Aion UI from GitHub releases on Mac/Windows/Linux, opening the app, and verifying Hermes is connected and responding. The script covers key features including switching models, searching conversations, attaching folders/documents for project context, installing agent skills via a marketplace, configuring MCP tools, speech-to-text and image models, setting permissions for agents like Claude Code, and scheduling/automating tasks across multiple agents while keeping them awake. It also demonstrates remote access options (including from a phone), a desktop “pet” overlay, and creating agent teams with a leader agent coordinating others, then closes by promoting the AI Profit Boardroom community for training and coaching.00:00 Hermes Plus Aon UI Intro01:04 Why Aon UI Beats Terminal01:55 Download and Install Aon UI02:32 UI Tour and Skills Marketplace03:47 Connect Hermes and Multi Agent Chats04:22 Project Folders and Context Mode06:24 Scheduled Tasks Across Agents07:29 Models Integrations and Voice08:41 Remote Access and Desktop Pet10:08 Agent Teams and Wrap Up10:58 Community Offer and Outro

Claw X: The Free Desktop App That Makes OpenClaw Agent Management Easy (Mac/Windows/Linux)The script introduces Claw X, a free desktop app for managing Open Claw AI agents, positioning it as a cleaner, more reliable alternative to the standard Open Claw gateway, which is described as messy and buggy (especially scheduled tasks, provider/key management, and chat history). It shows how to download Claw X via GitHub releases or build from source, and highlights use cases like a personal assistant, automated monitoring via scheduled agents, developer productivity, and workflow automation. The walkthrough covers the improved UI; easier provider/model and API key configuration with token usage stats; creating and managing multiple agents; managing skills via a marketplace and local folder access; reliable scheduled task management with status views; better chat history navigation; and simpler channel integrations like WhatsApp and Discord. It also mentions multi-agent routing/parallel work and briefly notes Aon UI as an alternative for multiple CLIs, then promotes the creator’s AI Profit Boardroom community for tutorials, coaching, and courses.00:00 Claw X Overview01:03 UI Comparison01:43 Download and Install02:18 Use Cases and Benefits03:26 Models and Providers04:15 Agent Management05:18 Skills and Scheduling06:52 Channels and Integrations07:40 Multi Agent Workflows08:42 Alternatives and Demo09:27 Community and Next Steps

Setup Hermes Web UI: The Ultimate AI Agent Dashboard GuideLearn how to set up and use the Hermes Web UI to manage your autonomous AI agents with a beautiful, responsive interface. This tutorial covers installation, switching between models like Deepseek and Claude, and managing advanced skills, memory, and scheduled tasks.00:00 - 00:00 - Intro00:40 - Quick Start & Installation01:38 - Connecting Models & Providers03:04 - Hermes Agent vs. Claude Code05:31 - Managing Memory & Profiles06:23 - Skills & Scheduled Tasks09:28 - Using the Terminal Dashboard

Hermes Desktop Tutorial: The Best Free AI Agent ManagerDiscover how to simplify AI agent management with the new Hermes Desktop app, a free tool for running local models and switching providers easily. Learn why Hermes is outperforming OpenClaw and how to set up your own virtual 3D office for your agents.00:00 - 00:00 - Intro to Hermes Desktop00:44 - 00:44 - Easy Setup & Prerequisites02:49 - 02:49 - Hermes vs. Claude Code & OpenClaw03:56 - 03:56 - Virtual 3D Office & Profiles05:30 - 05:30 - Connecting Telegram, Discord & Email07:11 - 07:11 - Skills, Memory & Persona Management08:56 - 08:56 - Growth Trends: Hermes vs. OpenClaw10:48 - 10:48 - Summary & Final Verdict

Give Hermes Persistent Memory for Free: OMI + Obsidian Context Setup (Works Across AI Agents)The video shows how to improve Hermes’ context and persistent memory by connecting it to OMI and an Obsidian vault, creating an automatic, fast, and largely free system that works across local AI agents (including Hermes and Open Claw). OMI records conversations and, with enabled screen recording and microphone access, captures daily activity to auto-generate organized “memories,” which can be exported into Obsidian as a growing memories file (over 650 entries in a few weeks). Hermes (and other agents) can then be pointed to the Obsidian file path to read and use these notes for context without manual updates or training. The script also mentions optional OMI features like wearable syncing, limited on-screen Q&A messages, and exporting to other apps (calendar, email, local files, Claude, ChatGPT, Gemini), plus a paid community/tutorial offering.00:00 Upgrade Hermes Memory00:31 OMI and Obsidian Setup01:20 How OMI Captures Context02:10 Syncing to Obsidian Vault02:51 Link Vault to Hermes03:28 Extra OMI Features04:15 Use With OpenClaw04:59 More Integrations and Rewind05:27 Wrap Up and Next Steps

Set Up Open WebUI with Hermes AI Agent (ChatGPT-Style Interface + Docker)The video shows how to set up Open WebUI with the Hermes AI agent to get a modern, self-hosted chat interface instead of relying on Hermes’ terminal UI or the official Hermes dashboard, which lacks a direct chat option. The presenter has Hermes read the GitHub documentation and configure Open WebUI (including the required Hermes API server and environment file), optionally using Docker, then demonstrates creating an account and chatting with Hermes inside Open WebUI. Key benefits highlighted include easier conversation management, multiple accounts, model switching across local and external models, file uploads, notes/knowledge attachments, saved prompts, tool setup (web search, image generation, code interpreter), previews for built code, and mobile plus voice/video support. The episode ends by directing viewers to the AR Profit Boardroom for full guides, courses, coaching calls, and community resources.00:00 Setup Overview00:32 Docs and GitHub Prep01:32 Why Open WebUI02:23 Install with Docker04:01 First Launch and Login04:38 Chat UI and Models05:22 Files and Knowledge06:00 Profiles and Tools07:10 Preview and Fixes08:06 Wrap Up and Resources

AI Agents Can Join Google Meet! OpenClaw 4.24 Mega UpdateOpenClaw 4.24 introduces game-changing features including Google Meet integration, full-power voice call agents, and built-in DeepSeek V4 support. Learn how the new browser automation and WhatsApp voice transcription upgrades are making AI agents more reliable for your business.00:00 - Intro: OpenClaw 4.24 Drop00:23 - Google Meet Integration & Artifacts01:53 - Voice Calls: Agent Console Upgrade03:29 - DeepSeek V4 Flash & Pro Integration05:06 - Browser Automation & Coordinate Clicks06:48 - Telegram, Slack & WhatsApp Fixes08:36 - Memory Systems & MCP Stability10:50 - Conclusion: The Future of Agents

Build & Automate Anything with DeepSeek V4 (Free): Chat Apps, AI Agents, OpenCode, Hermes, Agent ZeroThe video shows how to access and use DeepSeek V4 for free to build apps and automate tasks, starting in the DeepSeek chat by switching between Instant and Expert mode, enabling DeepThink and optional web search, and generating runnable “single HTML” projects that can be previewed or downloaded. The presenter demonstrates creating a Pomodoro timer and simple games (Pong and others) in minutes, then explains using Ollama to run DeepSeek V4 Flash in the cloud within token limits and connect it to multiple agent/coding tools such as OpenCode, ChatGPT Codex, OpenClaw, and Hermes, including scheduling daily research tasks, Telegram control, and browser automation. They discuss improving agent personalization by recording work with OMI and syncing to an Obsidian vault for memory/context, compare model/API cost and capability differences (Flash vs Pro and other models), and show setting up Agent Zero via Docker and OpenRouter to use DeepSeek models, with an invitation to learn more in the AI Profit Boardroom.00:00 DeepSeek V4 Overview00:14 Chat Modes and Settings00:57 Build a Pomodoro Timer01:56 Build a Pong Game02:50 Install Llama for Agents04:09 Choose V4 Flash Model04:53 Preview and Download Apps06:27 Five Terminal Agent Setup08:19 Connect Coding Agents12:32 Run Prompts Across Agents14:24 Failures and Best Harness18:21 Personal Context with OMI20:34 Live Q&A and Tips22:34 Best Use Cases Recap26:02 DeepSeek Setup Options26:45 Hermes Scheduled Tasks28:07 Telegram Remote Control28:55 Browser Automation Agents30:22 API Cost Comparisons35:47 Model Benchmarks Breakdown40:41 Install Agent Zero42:36 Connect DeepSeek via OpenRouter47:35 Local Models and Memory51:47 Wrap Up and Resources