Overview
Hermes Agent by Nous Research is an open-source AI assistant that gives you a personal agent with tool use, browser automation, and messaging integrations.
This AMI is fully pre-configured on Ubuntu 24.04 LTS. Launch, SSH in, and start using your AI agent in under 2 minutes.
What is included:
- Hermes Agent with all extras (messaging, cron, MCP, browser tools, Home Assistant)
- Python 3.11 via uv with virtual environment
- Google Chrome and Playwright for browser automation
- noVNC for visual browser access on port 6080
- Docker Engine with Compose and Buildx
- Caddy web server for automatic HTTPS reverse proxy
- Tailscale for private networking and secure remote access
- Developer tools: GitHub CLI, jq, yq, ripgrep, fd-find, ffmpeg, tmux, htop
Supported LLM providers: OpenRouter, Anthropic Claude, OpenAI, or any OpenAI-compatible API.
Getting started: SSH in, run hermes setup, choose your provider, start chatting.
Highlights
- Ready in 2 minutes - SSH in, run hermes setup, pick your LLM provider and start chatting
- Full browser stack - Chrome, Playwright, noVNC pre-installed for visual web automation tasks
- Batteries included - Docker, Caddy (auto-HTTPS), Tailscale VPN, and dev tools pre-configured
Details
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
Pricing
Dimension | Cost/hour |
|---|---|
t3.small Recommended | $0.03 |
t3.micro | $0.03 |
m7i.2xlarge | $0.05 |
t3.2xlarge | $0.05 |
m7a.large | $0.04 |
t3.medium | $0.03 |
t2.medium | $0.03 |
t3.nano | $0.03 |
m7a.4xlarge | $0.05 |
t3a.nano | $0.03 |
Vendor refund policy
Standard AWS refund policy
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
Initial release. Hermes Agent pre-configured with browser automation (Chrome, Playwright, noVNC), Docker, Caddy, Tailscale, and developer tools on Ubuntu 24.04 LTS.
Additional details
Usage instructions
- SSH into the instance: ssh ubuntu@<instance-ip>
- Run: hermes setup
- Choose your LLM provider and enter your API key
- Start chatting: hermes
Secure access (recommended): From your local machine: ssh -L 3000:127.0.0.1:3000 ubuntu@<instance-ip> Then open: http://localhost:3000
For HTTPS with a domain, edit /etc/caddy/Caddyfile and run: sudo systemctl enable --now caddy
noVNC browser access: http://<instance-ip>:6080/vnc.html
Pre-installed: Docker, Caddy, Tailscale, Playwright, Chrome, GitHub CLI, ripgrep, ffmpeg
Documentation: https://hermes-agent.nousresearch.com/docs
Support
Vendor support
Community support via GitHub Issues and Nous Research Discord. For AMI-specific issues, contact the publisher through AWS Marketplace.
- GitHub: https://github.com/NousResearch/hermes-agent/issues
- Docs:
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products


