NEW Hermes MCP Agent Update
Hermes, an open source AI agent, has released an MCP catalog that simplifies tool integration by replacing complex manual setup with a simple menu-driven installation process. The update introduces security controls, parallel execution, and auto-updating capabilities, making tool connection significantly more accessible.
Summary
This transcript covers a brief update on Hermes, an open source AI agent designed to run tasks, remember information, and utilize tools to accomplish work. The core announcement focuses on a new MCP (Model Context Protocol) catalog that dramatically simplifies the previously cumbersome process of connecting tools to the agent.
Prior to this update, connecting tools required users to manually dig through documentation, copy configuration files, and troubleshoot errors through trial and error. The new MCP catalog replaces this friction-heavy process with a curated, reviewed list of tools that users can select from a menu and install with a single command.
Beyond ease of installation, the update also emphasizes security and control. Users can whitelist specific actions they want to allow and block potentially risky ones, giving them granular control over tool permissions. Additional features include automatic tool updates while the agent is running, the ability to run safe tools in parallel for efficiency, and the capability for Hermes itself to act as a tool for other agents, enabling multi-agent workflows.
Key Insights
- The speaker claims that prior to this update, connecting tools to Hermes required manually digging through documentation, copying config files, and troubleshooting errors, framing the old process as a significant barrier to use.
- The speaker describes the MCP catalog as a reviewed list of tools, implying that curation and vetting are built into the catalog to ensure a baseline level of safety before installation.
- The speaker states that users can whitelist specific actions and block risky ones, positioning granular permission control as a core security feature of the new system.
- The speaker highlights that Hermes can auto-update tools while still running, suggesting the system is designed for continuity without requiring downtime or restarts.
- The speaker notes that Hermes can connect as a tool for other agents, indicating the platform is designed to participate in broader multi-agent ecosystems rather than operate only as a standalone system.
Topics
Transcript
[0:00] New Hermes MCE agent update. Hermes just made connecting AI tools dead simple and it's open source. Hermes is an open source AI agent. It runs tasks, remembers things, and uses tools to get work done. The problem? Connecting those tools used to mean digging through docs, copying config files, and praying you didn't break anything. Now there's an MCP catalog, a reviewed list of tools you just pick from a menu, run one command, hit enter, and it installs. Once it's safe, you control exactly what each tool can do, whitelist the actions you want, block the risks you want. It [0:30] even auto updates tools while running, run safe tools in parallel, and connect as a tool…
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.