# Running & deploying

> Laptop, Mac mini, VPS, Docker or cloud sandbox: where Hermes should live.

Canonical: https://hermeswatcher.com/topics/deployment

Where Hermes runs decides what it can reach, whether it is awake when a job is due, and what it costs. These resources compare the options and cover terminal backends, profiles, the API server and safe updates.

## Guides, tools and workflows

- [Build a useful GitHub issue review](https://hermeswatcher.com/workflows/github-issue-review.md): Turn a bounded set of repository issues into a source-linked review with suggested next steps.
- [Know whether an automation actually worked](https://hermeswatcher.com/workflows/reliable-recurring-automation.md): Separate scheduled attempts, useful output, and successful delivery so unattended tasks can be trusted.
- [Skills: reusable procedures for repeated work](https://hermeswatcher.com/tools/skills.md): Package a successful procedure so Hermes can load the relevant instructions when a similar task returns.
- [Plugins: add tools and lifecycle behavior](https://hermeswatcher.com/tools/plugins.md): Extend Hermes with custom tools, hooks, and integrations when instructions alone cannot supply the needed capability.
- [MCP: connect external tool servers](https://hermeswatcher.com/tools/mcp.md): Expose selected tools from a local or remote MCP server to Hermes without building a native tool first.
- [Models and providers: configure the actual inference route](https://hermeswatcher.com/tools/models.md): Understand which model handles conversation and which auxiliary models handle supporting tasks before diagnosing quality or cost.
- [Scheduled tasks: automate a proven run](https://hermeswatcher.com/tools/scheduling.md): Run bounded tasks on a schedule and retain separate evidence of execution, useful output, and delivery.
- [Context files: give a project durable instructions](https://hermeswatcher.com/tools/context-files.md): Keep project rules, conventions, and operating boundaries in files that Hermes can discover from the working directory.
- [GitHub: inspect repositories before automating changes](https://hermeswatcher.com/tools/github.md): Build repository research and review workflows through documented GitHub CLI or separately configured MCP routes.
- [Deployment: separate the agent host from its execution sandbox](https://hermeswatcher.com/tools/deployment.md): Understand the difference between running Hermes in a container and using a container only for terminal commands.
- [CLI: run bounded tasks and inspect the working environment](https://hermeswatcher.com/tools/cli.md): Use the terminal interface for interactive work, bounded single queries, explicit tool selection, and resumable sessions.
- [Desktop: manage conversations and inspect artifacts visually](https://hermeswatcher.com/tools/desktop.md): Use the native desktop interface to work with the same Hermes core, sessions, configuration, skills, and memory.
- [API server: use Hermes from any OpenAI-compatible client](https://hermeswatcher.com/tools/api-server.md): Expose Hermes as an OpenAI-compatible HTTP endpoint so chat frontends and scripts can talk to your agent.
- [Terminal backends: choose where the agent's commands run](https://hermeswatcher.com/tools/terminal-backends.md): Run the agent's shell commands locally, in Docker, on a remote host over SSH, or in cloud sandboxes like Modal, Daytona and Vercel Sandbox.
- [How to run Hermes Agent in Docker](https://hermeswatcher.com/learn/install-hermes-agent-docker.md): Hermes Agent has an official Docker image for amd64 and arm64. Run the setup wizard, then start the gateway with your data on a mounted volume.
- [How to run Hermes Agent 24/7 on a VPS or home server](https://hermeswatcher.com/learn/run-hermes-agent-24-7.md): Keep Hermes Agent online around the clock: install the gateway as a service, enable linger or a system service, and lock it down before going public.
- [Where Hermes Agent runs: host vs work environment](https://hermeswatcher.com/learn/where-hermes-runs.md): Decide where the agent, its tools and its lasting files live before moving a workflow to a server.
- [Hermes Agent terminal can't find files or programs](https://hermeswatcher.com/troubleshoot/terminal-cannot-find-files-or-programs.md): Check where the command actually runs, then verify paths and dependencies inside that environment.
- [Hermes Agent terminal backends: local, Docker, SSH, cloud](https://hermeswatcher.com/learn/choosing-a-terminal-backend.md): What each of Hermes's seven terminal backends does, what it isolates, what persists between sessions, and how to pick one for your situation.
- [Hermes Agent profiles: separate agents for separate jobs](https://hermeswatcher.com/learn/profiles-separate-agents.md): How Hermes profiles give you independent agents on one machine, what they isolate (and what they don't), and the commands for creating, switching, sharing and running them.
- [How to update Hermes Agent safely](https://hermeswatcher.com/learn/updating-hermes-safely.md): What hermes update actually does, how to preview and back up before updating, how release channels work, and how to recover if an update goes wrong.
- [Hermes Agent install or update failed](https://hermeswatcher.com/troubleshoot/install-or-update-failed.md): Symptom-led fixes for a Hermes install script that errors out, a missing hermes command, Python or permission problems, and updates that leave things half-done.
- [Hermes Agent web dashboard: a quick tour](https://hermeswatcher.com/learn/web-dashboard-tour.md): What the local dashboard can do, which pages save you the most time, and how to reach it from another machine without exposing your API keys.
- [Hermes Agent on Windows: command not found and other fixes](https://hermeswatcher.com/troubleshoot/windows-specific-problems.md): Work through the documented Windows pitfalls for native installs and WSL2, from PATH and encoding to editors, shell scripts and the login-time gateway task.
- [How to set up Hermes Agent with Open WebUI and the API server](https://hermeswatcher.com/learn/hermes-agent-open-webui-setup.md): Use Open WebUI with the Hermes API server. Set a strong key, keep loopback private and understand Docker reachability and host tool access.
- [Running a Karpathy-style LLM wiki through a Telegram bot on a small VPS](https://hermeswatcher.com/case-studies/jsong-llm-wiki): The author replaced a hand-maintained Obsidian vault with a markdown wiki that Hermes Agent keeps up to date: sources get sent to a Telegram bot, and the agent files, cross-links, logs and lints them. What makes it interesting is that the agent does the bookkeeping. The author still picks what goes in.
- [Three separate Hermes profiles for coding, research and illustration, each with its own Telegram bot](https://hermeswatcher.com/case-studies/avichawla-masterclass-three-agents): A tutorial that explains Hermes Agent's memory, skills and self-improvement features, then builds three specialist agents as separate profiles. One is a programmer that hands work to Claude Code, one is a researcher that sends a daily digest on a schedule, and one is a designer with a learned drawing style. Each agent has its own Telegram bot.

## Questions

- [What are terminal backends?](https://hermeswatcher.com/faq#terminal-backends)
- [Can I run Hermes on a cheap VPS and talk to it from my phone?](https://hermeswatcher.com/faq#run-on-vps)
- [How do I run Hermes in Docker?](https://hermeswatcher.com/faq#run-in-docker)
- [Can I run more than one agent on the same machine?](https://hermeswatcher.com/faq#profiles-multiple-agents)
- [How do I move Hermes, or a single profile or bot, to another computer?](https://hermeswatcher.com/faq#move-to-new-machine)
- [Can I talk to Hermes with my voice, and can it make phone calls?](https://hermeswatcher.com/faq#voice-mode)
- [Is there a web interface for managing Hermes?](https://hermeswatcher.com/faq#web-dashboard)
- [Can I use Hermes inside VS Code, Zed or JetBrains?](https://hermeswatcher.com/faq#use-in-code-editor)
- [Is there an official Hermes mobile app for iOS or Android?](https://hermeswatcher.com/faq#official-mobile-app)
- [Can Hermes Desktop connect to a remote agent on a VPS, NAS or Hermes Cloud without running the agent locally?](https://hermeswatcher.com/faq#desktop-remote-gateway)
- [What is Bot Screen, where does it run, and how heavy is it?](https://hermeswatcher.com/faq#bot-screen)
- [How do I watch the agent, or take over for a login, 2FA or CAPTCHA, and does it keep going afterwards?](https://hermeswatcher.com/faq#take-over-logins-captchas)
- [Can a cloud or VPS agent control my local computer, and why does Desktop act differently on a remote gateway?](https://hermeswatcher.com/faq#remote-gateway-what-runs-where)
- [What is Hermes Cloud, how is it priced, and is storage persistent?](https://hermeswatcher.com/faq#what-is-hermes-cloud)
- [How do I back up my Hermes setup?](https://hermeswatcher.com/faq#back-up-hermes)

All answers: https://hermeswatcher.com/faq.md

---

HermesWatcher is an independent guide. It is not affiliated with or endorsed by Nous Research. The [official Hermes Agent documentation](https://hermes-agent.nousresearch.com/docs) and [repository](https://github.com/NousResearch/hermes-agent) from Nous Research are the authority; each page here lists the official sources it was written from. If this site and the official docs disagree, trust the official docs. Index for agents: https://hermeswatcher.com/llms.txt