aidrop.itDocs
aidrop.it

Run Hermes Agent in the cloud with your AI agent

Run Nous Research's Hermes Agent around the clock and chat with it on Telegram. Your AI coding agent sets it up on aidrop.it. Learn what a restart resets.

Hermes Agent is an open-source AI assistant from Nous Research that you chat with in Telegram, Discord or a terminal. It remembers you and writes itself new skills as you use it. This page keeps it answering when your computer is off. You paste one paragraph into your AI coding agent (Claude Code, Codex or Cursor), and the agent sets it up on aidrop.it.

The honest limit: the cloud copy starts fresh after every restart, and its learning resets with it unless you keep it somewhere outside.

What you will have at the end

  • Hermes running in the cloud around the clock.
  • A Telegram bot that answers you and nobody else.
  • Your model key kept in your project’s secrets, never in the code.
  • Its personality, your profile and chosen skills saved with its code.

Words you will meet

  • Bot token: the password Telegram gives your bot.
  • API key: a password from an AI company that lets Hermes use its models. Usage is billed to you.
  • Secret: a key aidrop.it keeps for your project and hands to the app when it starts.
  • Skill: a recipe Hermes saves after a task, so it can repeat it.
  • Memory service: an outside service that keeps what Hermes learns about you.

What you need

  • An aidrop.it account with your coding agent connected. See Quickstart.
  • A plan with the 1 GB size: Pro or above (prices on aidrop.it). The 512 MB size on Trial and Starter is likely too small for Hermes.
  • An API key from a model provider, such as Anthropic or OpenRouter. A browser login (Nous Portal, a Claude subscription) does not fit: it is saved on the app’s disk and lost at the next restart.
  • A Telegram bot from @BotFather and your numeric Telegram user ID. See the Hermes Telegram guide.
  • Optional: an account with a memory service that Hermes supports, such as Honcho or Mem0. See memory providers.

Say this to your agent

Say this to your agent
Set up Hermes Agent (https://github.com/NousResearch/hermes-agent) as an
aidrop.it Service so it runs 24/7 and I talk to it on Telegram. Read
aidrop.it's runtime rules before writing anything and follow them.


- Build on the official image nousresearch/hermes-agent, pinned to a
  version tag. Its entrypoint starts s6 as root and switches user, which
  aidrop.it does not allow: override it, run as the image's non-root
  hermes user, and start "hermes gateway run --no-supervise" directly.
- The disk is read-only and wiped on restart. Keep config.yaml, SOUL.md,
  my USER.md and any skills or cron jobs I want to keep in the repo;
  copy them into a Hermes home in the temporary folder at start.
- Telegram only, allowed users: [MY TELEGRAM ID].
- Model: [PROVIDER AND MODEL], with an API key, no browser login.
- Enable the Hermes API server on all interfaces on the platform port
  and use /health as the health check. It can run tools, so protect it
  with a long random API server key.
- Outbound traffic goes through the platform's HTTP proxy; confirm the
  Telegram adapter and model calls use it.
- Secrets on the Project: the model key, the Telegram bot token, the API
  server key [and my memory service key].
- Size: 1 GB.


Push it, build it, and tell me the address, whether the bot answers,
and which secrets I still need to add.

What your agent does

  1. Reads aidrop.it’s rules and writes a small setup on top of the official Hermes package: your settings, its personality file, a start-up script.
  2. Saves the code in a new repository on aidrop.it.
  3. Asks you for the keys. Give them to the agent, or type them on the Project Secrets page in the aidrop.it dashboard.
  4. Builds the app and waits until it runs. If it fails, it reads the error log, fixes the setup and builds again.
  5. Tells you the address and asks you to message your bot.

Check that it works

  • Your agent says the app is running.
  • You message your bot on Telegram and it answers.
  • A friend messages the bot and gets no answer.
  • You turn your computer off and the bot still answers.

What survives a restart

The app has no permanent disk here. What Hermes writes while running sits in a small temporary folder that is emptied on every restart (why).

  • Kept: the settings, personality and skills saved with the code, your keys, the Telegram connection, and whatever a memory service holds.
  • Lost: chat history, its own memory notes, new skills it wrote, and scheduled jobs created from the chat.

To keep a new skill or fact, ask your coding agent to copy it into the repository and deploy again. A memory service keeps what Hermes learns about you, but not skills.

Skip WhatsApp here. Hermes pairs with WhatsApp like WhatsApp Web, through a QR code in a terminal. The pairing is lost on every restart, and the Hermes docs warn this unofficial route risks a ban.

When something goes wrong

What you see What to tell your agent
The app stops right after start “Read the logs. Hermes must start as its own user and write only to the temporary folder.”
The build is green but the app is never ready “Turn on the Hermes API server on the platform port and check its health page.”
The bot never answers “Check the logs for Telegram errors and the bot token secret.”
It forgot a skill it learned “Save that skill in the repository and deploy again.”
It runs out of memory “Move it to the 2 GB size.”

FAQ

Where are the Hermes Agent GitHub and docs?

The code is at github.com/NousResearch/hermes-agent, under the MIT license. The docs are at hermes-agent.nousresearch.com/docs and cover installing, Docker, and connecting chat apps.

Can Hermes Agent use Claude?

Yes. For an always-on copy, use an Anthropic API key, or an OpenRouter key that reaches Claude. Hermes can also sign in with a Claude Max plan, but its docs say that bills as extra usage, and in the cloud the login is lost on restart.

Is Hermes Agent the same as OpenClaw?

No. Both are open-source assistants you reach from chat apps. Hermes is built around learning: it saves skills and memories as you use it. Hermes even has a guide for moving from OpenClaw. See run OpenClaw in the cloud.

Does Hermes Agent need its own server?

It needs a computer that stays on; the Hermes docs say a small virtual server is enough. On aidrop.it your coding agent builds that always-on copy, so you do not rent or maintain a server yourself.

Search the docs