Hermes Workspace: New Mission Control is INSANE!
The video demonstrates how to set up multiple AI models and agent profiles within Hermes Workspace, while honestly acknowledging the platform's syncing difficulties. The presenter also promotes their own 'Agent Operating System' as a simpler alternative, showing features like agent swarms and model switching. The tutorial is framed around answering a community member's question about adding multiple models to Hermes.
Summary
The video opens by addressing a question from a community member named Code Mind, who asked how to set up multiple models inside Hermes and Hermes Workspace, noting that only the default model appeared to be available. The presenter begins by walking through the installation process, copying a terminal command to install Hermes Workspace, and explains that while installation is straightforward, syncing API keys and backends can be complex.
The presenter demonstrates how to add multiple AI models using the 'hermes model' command, including Mistral, Grok (via an X/Twitter OAuth login), and mentions other options like Llama, OpenAI Codex, and local models via Atomic Chat. He shows how signing into X with an existing Twitter subscription allows users to connect Grok directly into Hermes, selecting Grok 4.3 as an example.
Throughout the tutorial, the presenter is candid about Hermes Workspace's instability, showing real-time errors, slow loading, and syncing failures. He repeatedly turns to Claude (either Claude Desktop or Claude Code) to diagnose and fix backend issues, recommending that users enable 'bypass permissions' in Claude to reduce back-and-forth friction. He notes the workspace requires running multiple local ports and creating API gateways, which is not obvious from the one-click install.
The presenter then pivots to promoting his own 'Agent Operating System' (Agent OS) as a more reliable and feature-rich alternative, highlighting its daily updates, specialized workflows (SEO, video, image generation), Kanban board, and multi-model chat support. He contrasts this with Hermes Workspace's more basic interface and slower update cycle, noting for example that OAuth for Grok wasn't yet supported in Hermes Workspace at the time of recording.
The video concludes with information about the 'AI Profit Boardroom' community, where viewers can access the Agent OS zip file, daily updates, video tutorials, four weekly coaching calls, direct messaging with the presenter, and a local city connection map.
Key Insights
- The presenter argues that Hermes Workspace's one-click install is misleading, as running multiple local ports and creating API gateways makes true setup far more complex than advertised, often requiring Claude to fix backend issues.
- The presenter reveals that users can connect Grok to Hermes by authenticating through their existing Twitter/X subscription via OAuth, effectively repurposing a social media subscription as an AI model login.
- The presenter states that he built the Agent Operating System specifically because Hermes Workspace had persistent syncing problems, and his system delivers daily zip file updates with new features, unlike Hermes Workspace's slower update cycle.
- The presenter claims that enabling 'bypass permissions' in Claude Desktop or Claude Code is essential for smooth AI-assisted setup, because without it users face constant approval prompts that create significant back-and-forth friction.
- The presenter notes that Hermes Workspace lacked OAuth support for Grok at the time of recording, illustrating that because Hermes itself moves so fast, the Workspace UI often lags behind and doesn't yet support newly available models or auth flows.
Topics
Transcript
[0:00] Hermes workspace. Today, I'm going to show you how to run multiple models and Hermes agent profiles all in one single place. Right now, most people are using Hermes are just stuck on one single model with one brain, one set of skills. But, what if your agent could switch between the best AI models on the planet depending on what you need? That's exactly what I'm going to show you today. Also, show you how to add multiple models in Hermes workspace, so you've got the right tool for every single job. I'll show you how to run agent swarms, which is multiple agents all working at the same time. And I'll [0:31] show you the one thing…
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.