Run Hermes Agent FREE With This NEW Model 🤯
The video demonstrates how to integrate the newly released Step 3.7 Flash AI model into Hermes Agent for free via a 'news portal' for 30 days. The presenter showcases the model's capabilities including computer use, browser control, local file access, and agentic task execution. A framework called the 'LIFT method' is introduced for adopting new AI tools effectively.
Summary
The presenter introduces Step 3.7 Flash, a newly released AI model that can be used free for 30 days through a platform called 'news portal,' and demonstrates how to integrate it into Hermes Agent. Setup involves running terminal commands: first 'Hermes update' to get the latest version, then 'Hermes model' to select the news portal provider, and finally choosing Step 3.7 Flash as the active model.
The model's technical specifications are highlighted: a 256K context window, multimodal capabilities (images and video), selectable reasoning levels (high, medium, low), and design optimized for coding, agentic workflows, structured outputs, and long-context tasks. The presenter notes it is available on OpenRouter as a paid option but is free through the news portal integration.
Several live demonstrations are shown: opening Claude in a browser via a natural language command, creating a note in Apple Notes with auto-generated content, connecting to a local Obsidian vault to generate automation ideas, and running an agentic SEO keyword strategy task through a Kanban board that moves automatically from triage to completion.
The presenter introduces the 'LIFT method' (Learn, Install, Find one task, Teach your team) as a structured approach to adopting AI tools. The core advice is to avoid randomly poking at tools and instead focus on one repetitive task, automate it, then encode it as a reusable 'skill' that agents can run autonomously. An example SEO content skill is shown that can deploy to websites automatically.
The video closes with a pitch for the 'AI Profit Boardroom,' a paid community offering tutorials, an agent operating system, a 30-day roadmap, weekly coaching calls, and local meetups.
Key Insights
- The presenter claims that Hermes Agent is listed as the top app being used with Step 3.7 Flash on the news portal platform, suggesting rapid early adoption since the model 'just came out.'
- The presenter demonstrates that Step 3.7 Flash can access and read a local Obsidian vault, identifying automation opportunities from personal notes — illustrating local file integration without cloud dependency.
- The presenter argues that the barrier to using powerful AI APIs has effectively been removed because Step 3.7 Flash costs nothing for 30 days, making budget no longer the limiting factor for individuals.
- The presenter contends that a Kanban-based agentic workflow can autonomously move a task from strategy through triage to completion, including breaking down goals, acceptance criteria, and out-of-scope items — all without human intervention.
- The presenter introduces the 'LIFT method' — Learn, Install, Find one task, Teach your team — arguing that most people fail with AI tools because they 'grab a shiny new tool and poke at it randomly' rather than following a structured adoption path.
Topics
Transcript
[0:00] So, we have a brand new update and a brand new model that you can use for free with Hermes agent called step 3.7 flash. You can actually use it for free for 30 days and I'm going to show you exactly how you can plug this into Hermes agent so you can automate whatever you want for free using this model. And this literally just dropped. So, to get this set up, you're going to want to go to your terminal and you can see that this is an available free model on Hermes news portal. So, how do you set this up? So, [0:30] what you would do is you open up your terminal here, make sure…
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.