Hermes Agent + Obsidian + Omi = Second Brain!
The presenter demonstrates how to combine Omi and Obsidian as free tools to give AI agents like Hermes persistent, automatically updated memory. By recording daily activity via Omi and syncing it to an Obsidian vault, any locally running AI agent can access rich personal context without manual updates.
Summary
The video walks through a setup that uses two free tools—Omi and Obsidian—to give AI agents like Hermes significantly richer personal context and memory. The presenter highlights four key benefits: no manual memory training is required, the setup is fast and easy, it is free, and it works across multiple AI agents including Open Claw, Claude, and others.
Omi is described as a always-on recording tool that captures microphone input and screen activity throughout the day. It automatically organizes these recordings into memories, a task/goal summary, and a visual brain map. The presenter notes that in just a couple of weeks of use, over 650 memories were generated, including granular details like sleep times and music preferences. Omi can also sync with wearables and be invoked on-screen at any time via a keyboard shortcut, though the free tier limits message queries to around 33 per month.
Obsidian serves as the local vault where Omi exports all of these memories as structured notes. Because Hermes runs locally, it can directly access the Obsidian file path to read and use those memories as context, effectively giving the agent a continuously updated personal knowledge base. The presenter demonstrates the same approach working in Open Claw by simply providing the Obsidian file path as a context source.
The presenter also mentions that Omi supports exporting to Notion, calendars, emails, local files, and can update memory inside Claude, ChatGPT, and Gemini. The video closes with a promotion of the presenter's paid community, 'AI Profit Worm,' which offers full tutorials, courses on Open Claw and Hermes, weekly coaching calls, and local networking features.
Key Insights
- The presenter claims that Omi generated over 650 memories in just a couple of weeks by continuously recording screen activity and microphone input, reaching a level of detail that includes sleep schedules and music preferences.
- The presenter argues that because Hermes runs locally, it can directly read an Obsidian vault file path, allowing it to consume all Omi-generated memories as context without any manual input from the user.
- The presenter explains that using Omi solely to write memories to Obsidian—rather than for interactive messaging—means users never hit the free-tier message limit, making the core workflow entirely free.
- The presenter demonstrates that the same Obsidian file path method works across multiple AI agents, including Open Claw, by simply providing the file path as a context source, making the memory system agent-agnostic.
- The presenter notes that Omi supports exporting memory not just to Obsidian but also to Notion, calendars, emails, and can directly update memory inside Claude, ChatGPT, and Gemini, framing it as a broadly compatible second-brain infrastructure.
Topics
Transcript
[0:00] Today, I'm going to show you two free tools to make Hermes 10 times better when it comes to context, when it comes to memory, and the powerful thing about this is when you set this up, number one, you don't need to train your AI agents for memory anymore. It will automatically do it. And number two, it's going to be super fast and easy. Number three, it's free. And number four, you can actually plug this in across all your AI agents, whether that's Open Claw, Pi, whether that's Hermes agent, whether that's Claude, Code, etc. So, let me break down exactly what we're doing and how this works. So, [0:32] essentially, inside Hermes agent, I've got…
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.