Hermes new update is HUGE!
A comprehensive review of Hermes AI Agent by Nous Research, positioning it as the most practical and autonomous AI agent available. The speaker demonstrates how they've automated their entire Twitter marketing using Hermes, which posts content autonomously every 30 minutes, and explains the setup process including new features like backup API keys and free integration with Alibaba's Qwen 3.6 model.
Summary
The video provides an in-depth analysis of Hermes AI Agent, described as a self-improving autonomous agent created by Nous Research. The speaker positions Hermes as superior to other AI agents like OpenClaw due to its ability to run 24/7 in the cloud rather than requiring local terminal access. A key demonstration involves a fully automated Twitter account that creates and posts content every 30 minutes, including generating headlines, writing content, creating stories, and adding images - all autonomously achieving significant engagement (400 views mentioned for recent posts).
The technical setup involves a simple 60-second installation process, with the ability to integrate multiple AI models as backups. A significant update allows users to leverage Alibaba's new Qwen 3.6 Plus model, which offers a million token context window for free, specifically designed for agentic coding tasks. The speaker explains that Hermes ranks #2 in personal agents (behind OpenClaw at #1) and includes migration tools for users switching from OpenClaw.
The automation philosophy centers on a six-step blueprint: defining triggers, identifying data sources, and testing actions. Current implementations include auto-posting to social media, competitor intelligence monitoring, daily AI news scanning with filtering and deduplication, and analytics reporting delivered via Telegram. The speaker emphasizes that every automation essentially consists of 'a prompt with a schedule,' where specificity in prompting determines output quality.
Advanced features include agentic profiles for creating multiple specialized AI agents, integration with PaperClip for orchestrating agent teams, and connections to various APIs including Google's Imagen for thumbnail generation. The speaker concludes by promoting their AI Profit Boardroom community, which offers 30-day roadmaps, quick deploy kits, and 100 prompts for Hermes implementation.
About this episode
Want to make money and save time with AI? Join here: https://www.skool.com/ai-profit-lab-7462/about Video notes + links to the tools 👉 https://www.skool.com/ai-profit-lab-7462/about Get a FREE AI Course + Community + 1,000 AI Agents 👉 https://www.skool.com/ai-seo-with-julian-goldie-1553/about We'll be talking about Hermes, doing a Hermes masterclass for AI agents, and showing you how to set up and how to build with it, etc.
Key Insights
- The speaker claims Hermes is the most practical and autonomous AI agent they've tested, superior to alternatives like OpenClaw because it runs 24/7 in the cloud rather than requiring local terminal access
- Hermes demonstrates self-improving capabilities by analyzing its own Twitter content performance and automatically updating its skills files, telling the user it will work to improve content quality in the next 30-minute cycle
- The new Hermes update allows backup API keys, and Alibaba's Qwen 3.6 Plus model provides a free million-token context window specifically designed for agentic tasks, making the entire system potentially free to operate
- Hermes currently ranks #2 in personal agents behind OpenClaw at #1, but the speaker observes many Twitter users are migrating from OpenClaw to Hermes due to its autonomous capabilities
- The speaker's automation philosophy reduces every automation to 'a prompt with a schedule,' emphasizing that specificity in defining what to check, skip, format, and where to send determines the quality of output
Topics
Transcript
[0:01] Today I'm going to be running you through Hermes AI agent. Exactly to use it, how it works step by step, how you can use this to automate and build anything that you want to, and some of the best use cases for getting started with this. Now, you can install Hermes AI gym in literally 60 seconds. It's super easy. You just follow the terminal commands right here, and then you can get started. And from everything that I've tested, I've tested, you know me, you've probably seen my videos, like I've tested pretty much every single AI [0:31] agent out there in the world, and this is by far the most practical and useful and the most…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Julian Goldie SEO
NEW Nvidia Autonomous AI is WILD!! 🤯
Nvidia announced Nemo Clo, a new autonomous AI agent system that operates independently without continuous prompting. Powered by Nemotron 3 Ultra (a 550 billion parameter model), the system is five times faster and cheaper than previous versions, with OpenShell providing secure sandboxed execution.
Laguna XS 2.1: New FREE + Opensource Local AI!
Julian reviews Laguna XS 2.1, a new free open-source local AI coding model from Poolside that performs comparably to Qwen 3.6 and outperforms Claude Haiku on benchmarks. He demonstrates its practical capabilities by building landing pages and functional apps, highlighting its speed, offline functionality, and multiple deployment options through local setup, Claude Code, or OpenRouter's free API.
How to Run Hermes FREE Forever!
The video demonstrates how to run the Hermes AI agent for free using Gemma 4, a local open-source model from Google, with significant speed improvements through MLX optimization. The setup works on Apple Silicon Macs or via free APIs on Open Router, enabling autonomous agents to work offline and privately without subscription costs.
This NEW Chinese AI is INSANE! (FREE + Open Source!)
Long Cap 2.0 is a new open-source Chinese AI model from a food delivery app company that offers 1 million tokens of free context memory, beats GPT-4.5 on SWE bench pro benchmarks, and uses efficient parameter activation to reduce computational overhead while maintaining high performance.
Claude Code is now FREE: Here’s how…
Google's new Gemma 4 model running on Ollama is 90% faster on Apple Silicon, enabling free Claude Code usage locally without token costs. The setup requires three simple steps: downloading Ollama, Gemma 4, and installing into Claude Code, with alternatives available via OpenRouter API for non-Mac users.