Hermes AI Browser Agent: Build ANYTHING!
This video introduces the Hermes AI browser agent, a dashboard-based system that allows users to manage multiple AI agents in one place without coding. The presenter demonstrates how it can build websites, content plans, and automate SEO tasks. A key feature highlighted is a 'memory layer' using tools like Obsidian to give AI persistent context across sessions.
Summary
The video, presented by a digital avatar of Julian Goldie (CEO of Goldie Agency), introduces the Hermes AI browser agent as an 'agent operating system' that consolidates multiple AI tools into a single browser-based dashboard. The core problem it addresses is that most people use disconnected AI tools that don't share memory or work together, resulting in inefficiency.
The Hermes agent is demonstrated as capable of building landing pages, generating 12-month content plans, writing blog posts, creating images and videos, and handling SEO tasks — all through plain-language text prompts requiring no coding knowledge. The presenter shows how large projects are automatically broken down into smaller tasks that agents work through sequentially, mimicking how a real team operates.
A standout feature is the ability to integrate multiple AI models simultaneously — including Claude and Gemini — all visible and manageable from one screen, sharing the same underlying memory. The presenter also notes that the system is accessible on modest hardware, including basic laptops or even a Raspberry Pi, and can be run in the cloud for remote access.
The video's central 'secret' is the memory layer: rather than forgetting everything after each session, the AI is connected to a persistent note-taking system (such as Obsidian) that stores context about the user's work, goals, and preferences. This memory is automatically maintained by the AI itself, growing over time without manual organization. The presenter argues this is what transforms the system from a novelty into a genuinely useful tool.
The video closes with a promotional pitch for the 'AI Profit Boardroom,' where viewers can access a pre-built Agent OS, and the free 'AI Success Lab' community.
Key Insights
- The presenter argues that most people use AI inefficiently because their tools are siloed — separate AI helpers that don't share memory or communicate, which he claims the Hermes agent directly solves by unifying them in one dashboard.
- The presenter demonstrates that large tasks like 'build me a whole website' are automatically decomposed by the agent into smaller subtasks — design pages, pick keywords, write blog posts — which are then executed sequentially, eliminating the need for manual project management.
- The presenter identifies the 'memory layer' as the single most important and most commonly skipped feature, explaining that without it, AI forgets everything after each session, making it effectively useless for ongoing work.
- The presenter claims the system can run on very modest hardware — including a Raspberry Pi — and can also be hosted in the cloud for phone access anywhere, directly countering the assumption that powerful AI setups require expensive computers.
- The presenter describes a self-maintaining memory system where the AI automatically organizes and updates notes in Obsidian daily, meaning the user only needs to seed it with a few key files and goals to get started, after which it grows autonomously.
Topics
Transcript
[0:00] Hermes AI browser agent, build anything. Today, I'm going to show you the Hermes AI browser agent. This little thing can build almost anything you want, a full website, a whole team of AI helpers, brain that never forgets. It's new, it's huge, and it's super easy. You don't need to be a tech person at all. And stick around because the last tip is the one that makes the whole thing work. Okay, so right now most people are using AI all wrong. They've got one AI helper over here, another over there, third somewhere else. And none of them talk to [0:30] each other. None of them share a memory. None of them work as a team.…
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.