Hermes Obsidian is Insane (FREE!) 🤯
The video introduces a free method using Obsidian, a markdown-based notes app, to create a shared memory system for AI tools like ChatGPT and Claude. By pointing multiple AI agents to one centralized Obsidian vault, users avoid repeatedly re-explaining context. Notes can even be captured automatically, ensuring all AI tools operate from the same knowledge base.
Summary
The video presents a solution to a common frustration with AI tools: they start from scratch with every new session, forgetting the user's goals, projects, and prior work. This forces users to constantly re-explain their context, which is inefficient and time-consuming.
The proposed solution centers on Obsidian, a free notes application that stores content as plain markdown files. The speaker argues that by building a centralized 'vault' of personal notes, goals, and project information, users can point any AI agent to that single source of truth. Once set up, the AI can immediately answer questions like 'What did I work on last month?' without needing any additional context from the user.
A key advantage highlighted is automation: users don't need to manually write notes into the vault, as tools can capture and sync information automatically. Additionally, because all AI agents — whether ChatGPT, Claude, or others — read from the same vault, they stop producing contradictory outputs. The result is a unified, consistent AI experience across different tools and sessions.
Key Insights
- The speaker claims that AI tools like ChatGPT and Claude currently forget all user context between sessions, forcing users to repeatedly re-explain their goals and projects every time.
- The speaker argues that Obsidian, a free markdown-based notes app, can serve as a single shared memory that any AI agent can read from, eliminating the need to re-establish context.
- The speaker contends that once an AI is pointed at the Obsidian vault, it can instantly answer questions like 'What did I work on last month?' without any additional user input.
- The speaker states that notes don't need to be written manually by the user — tools can capture and sync them into the vault automatically.
- The speaker argues that having all AI agents read from the same vault prevents them from contradicting each other, so ChatGPT used on Monday and Claude used on Tuesday will produce consistent, unified responses.
Topics
Transcript
[0:00] Free, Hermes Obsidian is insane. This free trick gives chat GPT, Claude, and your AI agents one shared brain in one setup. Right now, your AI starts from scratch every single time. It forgets your goals, your projects, everything you've done. So, you keep re-explaining yourself over and over. That stops today. With Obsidian, a free notes app that's just markdown files, you can build one shared memory that every AI agent reads from. Your notes, your goals, your all-in-one vault. Point your AI at it once, and from then on, it already knows you. Ask it, "What did I work on last month?" And it actually knows instantly, no re-explaining. The [0:30] best part, you don't even write…
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.