Hermes HA

Quickstart

This guide takes you from zero to your first Hermes conversation in about 60 seconds.

Prerequisites

  • OS: Linux, macOS, or WSL2 on Windows.
  • Model: An LLM with at least a 64,000-token context window. Most hosted models (Claude, GPT, Gemini, Qwen, DeepSeek) qualify.
  • API key: For OpenAI, Anthropic, OpenRouter, Nous Portal, or any OpenAI-compatible endpoint.

1. Install

curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash

Then reload your shell: source ~/.bashrc or source ~/.zshrc.

2. Configure

Run the interactive setup wizard:

hermes setup

Or configure each part separately:

hermes model   # pick your LLM provider
hermes tools   # enable toolsets
hermes env     # manage API keys

3. Launch

hermes          # classic CLI
hermes --tui    # terminal UI with overlays

Next steps

  • Run hermes --continue to resume your previous session.
  • Use /help inside the REPL to discover slash commands.
  • Browse agentskills.io to install community skills.
  • Continue to Installation for Docker, SSH, and serverless setups.