Hermes Agent: The New OpenClaw?
Imran walks through how to install and use Hermes Agent, positioning it as a superior alternative to Open Claw due to its built-in memory system, stability, and token cost efficiency. The episode covers installation on Mac and Android, connecting with tools like Obsidian and G Stack, creating skills, and practical use cases for personal and professional automation.
Summary
The episode features Imran explaining Hermes Agent to host Greg, framing it as a potential replacement for Open Claw. Imran outlines three core problems he experienced with Open Claw: no persistent memory requiring constant re-instruction, frequent gateway restarts (sometimes hourly), and opaque token spending. Hermes Agent addresses all three by providing a built-in memory system that writes successful task completions to a SQLite database, improved stability (no restarts needed in over a week), and clear model/cost visibility via Open Router integration.
Imran demonstrates the installation process, which is a single command on Mac, Linux, or Windows Subsystem for Linux, and highlights that Hermes ships with 40+ built-in tools covering browsing, web search, cron jobs, image generation, and home assistant capabilities, along with pre-installed Apple ecosystem skills (Notes, Reminders, iMessage, Find My) on Mac.
A significant portion covers Hermes on Android via the Termux app, which gives the agent access to phone sensors, camera, Wi-Fi, SMS, and device controls through the Termux API. Imran suggests this enables cheap, always-on agent hardware as an alternative to sold-out Mac Minis, with potential applications in social media automation that posts natively from a device to avoid API reach penalties.
On cost optimization, Imran reports reducing his token spend from roughly $130 every five days to about $10 every five days — a 90%+ reduction — by switching to Hermes with Open Router and converting recurring tasks into deterministic code rather than re-running LLM inference each time.
The conversation covers agent design philosophy: Imran runs four agents named after Muppets, but recommends most people maintain one or two (personal and work). He uses Obsidian as a clean frontend for agent-generated markdown dashboards, replacing walls of Telegram text. He also discusses G Stack by Garry Tan (Y Combinator's startup methodology encoded as an agent skill) and a self-built psychiatrist-style skill based on Joseph Weizenbaum's ELIZA program. Imran closes by emphasizing that customizing the agent is not the core skill — using it to actually get work done is.
About this episode
I sit down with Imran Muthuvappa to get a hands-on walkthrough of Hermes Agent, a personal AI agent that ships with built-in memory, 40+ tools, and pre-installed skills out of the box. Imran walks me through why he migrated from OpenClaw, how to install Hermes on a Mac or even an Android phone via Termux, and how he cut his token spend by roughly 90% using OpenRouter. We get into agent design (one agent vs. multiple), connecting Hermes to Telegram and Obsidian, and the kinds of prompts that turn a personal agent into a daily operating system. By the end, I have a practical roadmap to install Hermes, pick a model, and start automating real parts of my life and business Timestamps 00:00 – Intro 01:38 – Why Imran Left OpenClaw (Memory, Gateway, Tokens) 04:26 – Hermes Setup Tour and 40+ Built-In Tools 07:06 – Installing Hermes on Mac, Linux, and WSL 12:21 – Telegram and Android Agents 17:09 – Auditing Your Life With Your Agent 20:04 – Must-Know Hermes Tips: Updates, Tailscale, Telegram 21:07 – Should You Migrate From OpenClaw? 25:58 – Hermes + Obsidian as a Daily Dashboard 27:16 – Must-Use Prompts for a Personal Agent 31:29 – Must-Install Skills: Obsidian, Honcho Memory, G-Stack 33:04 – What G-Stack Is and Why It Matters 34:18 – Customization Is a Trap; Output Is the Skill 35:19 – Closing Thoughts Key Points * Hermes Agent solves OpenClaw's three biggest pain points: built-in memory (writes to SQLite on successful tasks), gateway stability, and token visibility. * Installation is a single command on Mac, Linux, or WSL, and Hermes ships with 40+ tools and popular skills (Apple Notes, Reminders, iMessage, Find My) pre-installed. * Switching to Hermes with OpenRouter can cut token spend by roughly 90%, from about $130 per five days to around $10 per five days in Imran's case. * You can run Hermes on a cheap Android phone via Termux + Termux API, unlocking SMS, sensors, and on-device social posting as a cheap alternative to a Mac Mini. * The real skill is defaulting to your agent for work, then meta-prompting it nightly: "What am I procrastinating? What should I automate? What tool can you build me tonight?" * Imran recommends pairing Hermes with Obsidian for a clean daily dashboard and installing G-Stack (a Y Combinator-style startup skill from Gary Tan) if you are building a product. Number Section Summaries 1. Why OpenClaw Falls Short Imran opens with the three problems that pushed him off OpenClaw: no memory (repeating the same instructions), gateway restarts as often as once an hour, and zero visibility into token spend. Hermes fixes each directly and has stayed stable for him for over a week at a time. 2. What You Get Out of the Box Hermes ships with 40+ built-in tools (browser, web search, cron, image generation, home assistant) and pre-installed skills for Mac users (Apple Notes, Reminders, Find My, iMessage). You skip the skills-hub scavenger hunt and start working immediately. 3. Installation and Model Selection On Mac, Linux, or WSL you run one command; Mac users may need Xcode Developer Tools first. `hermes model` lets you pick providers, and Imran recommends OpenRouter for transparent pricing, free models like NVIDIA's NemoTron, and access to Anthropic models at a glance. 4. Hermes on Android and the Muppets Fleet Imran runs multiple agents named after Muppets, including "Cookie Monster" on a Solana Seeker phone via Termux. The Termux API exposes the camera, SMS, Wi-Fi, brightness, and vibration, making an Android phone a cheap, always-on, SIM-enabled agent device for things like on-device social posting and SMS 2FA automation. 5. Designing Your Agent Stack One agent is usually enough; two makes sense if you want to keep work and personal separate. Cron jobs vs. sub-agents is still an open question, but sub-agents let you assign cheaper models to deterministic tasks. Pairing Hermes with Obsidian (Markdown files the agent organizes for you) gives you a readable daily dashboard on phone and desktop. 6. Skills, Prompts: Obsidian, Honcho Dev Memory, and G-Stack (Gary Tan's YC-style startup skill). The prompts that compound: "What have I been procrastinating?" "What is the most important thing today?" "What task should I automate?" "What tool can you build me tonight?" The real skill is defaulting to the agent for daily work; customization is the rabbit hole to avoid. The #1 tool to find startup ideas/trends - https://www.ideabrowser.com/ LCA helps Fortune 500s and fast-growing startups build their future - from Warner Music to Fortnite to Dropbox. We turn 'what if' into reality with AI, apps, and next-gen products https://latecheckout.agency/ The Vibe Marketer - Resources for people into vibe marketing/marketing with AI: https://www.thevibemarketer.com/ FIND ME ON SOCIAL X/Twitter: https://twitter.com/gregisenberg Instagram: https://instagram.com/gregisenberg/ LinkedIn: https://www.linkedin.com/in/gisenberg/ FIND IMRAN ON SOCIAL X/Twitter: https://x.com/imranye Alif: https://alif.build/
Key Insights
- Imran argues that Open Claw's lack of persistent memory meant users had to re-explain the same instructions repeatedly, and its gateway required restarting as often as once an hour, making setup overhead outweigh actual productivity gains.
- Imran claims Hermes Agent uses a SQLite database to log all past tasks, enabling it to retroactively search conversation history for things like API keys that were mentioned but never formally saved to environment variables.
- Imran reports achieving a greater than 90% reduction in token spend — from approximately $130 every five days down to $10 every five days — by switching to Hermes with Open Router and converting recurring tasks into static code instead of repeated LLM inference.
- Imran demonstrates that Hermes Agent can be installed on an Android phone via Termux, and that adding the Termux API app grants the agent access to phone sensors, camera, SMS, Wi-Fi controls, and the vibration motor, effectively creating a low-cost always-on agent device.
- Imran suggests that posting social media content directly from an Android device running Hermes — rather than through a scheduling API — could preserve algorithmic reach because the post appears to originate from a real device with a genuine MAC address.
- Imran describes using a local speech-to-text model to send an 8-minute Telegram voice message cataloguing his fridge and pantry contents, then having the agent generate daily recipe suggestions based on available ingredients and fitness goals, which he says removes significant mental load.
- Imran explains that G Stack — built by Y Combinator CEO Garry Tan originally for Claude Code — encodes YC's week-over-week startup improvement methodology as a free, installable agent skill, making previously exclusive accelerator-style guidance broadly accessible.
- Imran argues that learning to use Hermes Agent is not the actual skill — customizing and tinkering with the agent is a distraction, and the real value is in what work gets completed with it, citing his ability to engage with 20–30% more founders at his fund as the tangible outcome.
Topics
Transcript
[0:00] Hermes agent, you're seeing it everywhere. People are calling it the open claw killer and today's episode is about how you can actually install it, how you can connect it with G stack by Gary Tan, how you can connect it to Obsidian, how you can create skills. We go through step by step how you can get started with Hermes agent. This is everything you need to know for how to run it, get started and actually how you can even use it on an Android device. So, enjoy the episode. It's with my dear friend Imran who just explains technical [0:31] concepts in such a such a clear way. It's a breath of fresh air. Enjoy the…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Greg Isenberg
What are Agentic Loops?
Professor Ross Mike explains agentic loops — AI systems that self-iterate without human input — and argues they are largely impractical for most developers due to high token costs and poor assumption-making. He distinguishes between 'human in the loop' (iterative, guided development) and fully automated loops, recommending loops only for constrained, binary-feedback processes like code review. He shares his own GP loop use case as a rare valid example.
Clearest Explanation of AI Agents as Customers
The speaker argues that AI agents are becoming the primary 'customers' of the internet, replacing human users as the dominant force driving web traffic and commerce. This shift requires entirely new infrastructure — from agent-native inboxes and wallets to machine-readable websites — creating massive startup opportunities. The speaker frames this as a bifurcation of the internet into a human layer and an agent layer.
How to use Obsidian with Claude in 61 seconds
This short tutorial outlines three levels of using Obsidian with Claude AI to accelerate professional learning and career resilience. It covers connecting Obsidian to Claude via MCP, using the Smart Connections plugin to identify skill gaps, and prompting Claude to generate a public learning plan based on your notes.
Been playing with this cool ai tool from genspark
The video demonstrates how GenSpark's AI tool can automate LinkedIn job post lead generation by identifying decision makers and drafting personalized cold emails. It then presents a business model called 'Outcome as a Service,' where users build competitor-tracking workflows and sell daily briefings to clients for recurring revenue.
Hermes Agent Explained
The transcript introduces Hermes, an AI agent that retains memory across sessions unlike standard LLMs. It highlights key features including cost-efficient reasoning via Open Router with Quen 3.6 Plus, Obsidian integration for persistent context, and cron job automation for token-free repetitive tasks. The entire stack is noted to run on an Android phone.