Hermes Agent
Hermes Agent is a self-improving AI agent by Nous Research with a built-in learning loop, enabling it to create skills from experience, persist knowledge, and build a user model across sessions. It solves the problem of static AI assistants by continuously adapting and improving, and is designed for developers and power users who want a versatile, deployable agent that can run on various infrastructures and be accessed from multiple platforms.
🎬 Hermes Agent - Full Tutorial & Setup Guide (For Beginners) · Metics Media
✨ Key features
- Self-improving learning loop with skill creation and memory
- Multi-platform access via CLI, Telegram, Discord, Slack, WhatsApp, Signal
- Scheduled automations with natural language cron jobs
- Delegates tasks to isolated subagents for parallel work
- Runs on local, Docker, SSH, serverless backends
- Model-agnostic with support for many providers
🎯 Use cases
- Automate daily reports and backups via scheduled tasks
- Build a personal assistant accessible from messaging apps
- Create and refine reusable skills for complex workflows
- Run parallel research or data processing tasks with subagents
- Deploy a persistent agent on a cloud VM or serverless environment
📦 Installation
🧰 Requirements: Requires Python 3.11, Node.js, and a model provider API key (e.g., Nous Portal, OpenRouter, OpenAI) or your own endpoint.
Linux, macOS, WSL2, Termux
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
Windows (native, PowerShell)
iex (irm https://hermes-agent.nousresearch.com/install.ps1)
After installation:
source ~/.bashrc # reload shell (or: source ~/.zshrc)
hermes # start chatting!
🚀 Usage
hermes # Interactive CLI — start a conversation
hermes model # Choose your LLM provider and model
hermes tools # Configure which tools are enabled
hermes gateway # Start the messaging gateway (Telegram, Discord, etc.)
hermes setup # Run the full setup wizard (configures everything at once)
❓ FAQ
What operating systems are supported?
Linux, macOS, WSL2, Termux, and native Windows (via PowerShell installer).
Can I use my own LLM provider?
Yes, Hermes supports many providers including Nous Portal, OpenRouter, OpenAI, and your own endpoint, switchable with 'hermes model'.
How do I migrate from OpenClaw?
Run 'hermes claw migrate' to import settings, memories, skills, and API keys from OpenClaw.
Can I talk to Hermes from messaging apps?
Yes, start the gateway with 'hermes gateway start' after setup to use Telegram, Discord, Slack, WhatsApp, Signal, and more.
📊 Repository
🤖 Overview, features, install steps and FAQ were generated from the project's README on Sep 4, 2026. Always check the original source before running commands.