> Source: https://meetrix.io/store/hermes-agent/
> Markdown copy of that page. Cite the URL above, not this file.

[Store](https://meetrix.io/store/)  Hermes Agent

Open-source AI agent

# Self-hosted Hermes Agent on AWS and Google Cloud

Run Hermes Agent, the self-improving AI agent from Nous Research, from a pre-configured image in your own cloud account. It remembers past conversations, builds its own skills and answers on Telegram, Discord, Slack, WhatsApp and Signal, with the LLM provider of your choice.

 [Launch on AWS](https://aws.amazon.com/marketplace/pp/prodview-y5xgoi7s7qrh4)[ Launch on Google Cloud](https://console.cloud.google.com/marketplace/product/meetrix-public/hermes-agent-self-hosted-ai-agent)

-   Ready in 5-10 minutes
-   Any LLM provider
-   Data stays in your account

![Hermes Agent deployed on AWS by Meetrix](https://meetrix.io/assets/store/hermes-agent/hermes-agent.webp)

## What is Hermes Agent?

Hermes Agent is an MIT-licensed, self-hosted autonomous AI agent built by Nous Research. It keeps memory across sessions, learns new skills from experience and runs scheduled automations. One gateway connects it to your messaging platforms, and it works with any LLM provider rather than a single vendor's model.

-   ### Persistent memory

    Remembers past conversations using full-text search and LLM summaries.

-   ### Self-built skills

    Learns from experience and keeps the skills it builds.

-   ### One gateway, five platforms

    Telegram, Discord, Slack, WhatsApp and Signal from one deployment.

-   ### Scheduled automations

    Run recurring jobs with the built-in cron scheduler.

-   ### Plugins and MCP

    Extend the agent with plugins and Model Context Protocol servers.

-   ### Any model provider

    Nous Portal, OpenAI, OpenRouter, Anthropic, Vertex AI, Bedrock or custom endpoints.

## What's in the Meetrix Hermes Agent image

Running Hermes Agent yourself means runtimes, a gateway process, a reverse proxy, SSL and backups. The marketplace image ships with that done, plus a web dashboard.

-   Hermes Agent running in Docker
-   A web dashboard behind nginx with the admin login you choose
-   A Let's Encrypt certificate that renews itself
-   Backups and file storage in your own S3 bucket on AWS
-   A deployment template for your own AWS account or GCP project
-   Email support from Meetrix at support@meetrix.io

## How to set up a self-hosted Hermes Agent

1.  ### Launch the server

    Subscribe on AWS Marketplace or Google Cloud Marketplace, enter your domain and admin username and password, and deploy.

2.  ### Point your domain at it

    Create a DNS A record for your Hermes domain with the server's public IP, then sign in to the dashboard once SSL has issued.

3.  ### Choose a model provider

    SSH into the server and run hermes model inside the container to pick a provider and add your API key.

4.  ### Connect a channel

    Open Channels in the dashboard and pair Telegram, Discord, Slack, WhatsApp or Signal.

## Choose your cloud

### Hermes Agent on AWS

An AMI on AWS Marketplace, launched into your own AWS account with a CloudFormation stack.

Deploys with

CloudFormation

Recommended size

t3a.small

Ready in

5-10 minutes

#### Setup guides

-   [**Developer guide** Launch, SSL, model provider, channels](https://meetrix.io/blogs/hermes-agent-developer-guide/)
-   [**Hermes Agent on AWS Marketplace** Pricing, memory and alternatives](https://meetrix.io/blogs/hermes-agent-aws-marketplace/)

 [Launch on AWS](https://aws.amazon.com/marketplace/pp/prodview-y5xgoi7s7qrh4)

### Hermes Agent on Google Cloud

The same agent as a Google Cloud Marketplace image, deployed into your own GCP project.

Deploys with

Marketplace deployment form

Recommended size

Default General purpose type

Free trial

5 days, up to USD 50 licence credit

#### Setup guides

-   [**Developer guide** Configure, SSL, model provider, channels](https://meetrix.io/blogs/hermes-agent-gcp-developer-guide/)
-   [**Hermes Agent on Google Cloud Marketplace** Pricing, Vertex AI and alternatives](https://meetrix.io/blogs/hermes-agent-gcp-marketplace/)

 [Launch on Google Cloud](https://console.cloud.google.com/marketplace/product/meetrix-public/hermes-agent-self-hosted-ai-agent)

## Hermes Agent by Meetrix vs hosted agent SaaS vs a manual install

|  | Hermes Agent by Meetrix | Hosted AI agent SaaS | Self-managed install |
| --- | --- | --- | --- |
| Licence | MIT, open source | Proprietary | MIT, open source |
| Pricing model | Instance and software fee, plus your own model cost with no markup | Per-seat or usage markup on model cost | Server cost plus your own model cost |
| Platforms | Telegram, Discord, Slack, WhatsApp and Signal from one gateway | Usually one, more as paid add-ons | Whatever you wire up yourself |
| Data location | Your own AWS account or GCP project | Vendor's infrastructure | Your server |

Model tokens are billed by your provider directly, not by Meetrix. [Read about Hermes Agent on AWS →](https://meetrix.io/blogs/hermes-agent-aws-marketplace/)

## Hermes Agent FAQ

What is Hermes Agent?

A self-hosted, self-improving autonomous AI agent built by Nous Research. It keeps memory across sessions, builds its own skills, runs scheduled automations and connects to Telegram, Discord, Slack, WhatsApp and Signal through one gateway.

Do I need my own model API key?

Yes. The image does not include model access. Run hermes model after deployment and choose Nous Portal, OpenAI, OpenRouter, Anthropic, Google Vertex AI, AWS Bedrock or a custom OpenAI-compatible endpoint. The provider bills you directly.

Does it remember conversations between sessions?

Yes. Memory persists using SQLite FTS5 full-text search combined with LLM summarisation, stored on the server's own disk, so it survives a stop and restart.

How do I connect Telegram, Discord or the others?

Open the Channels section of the dashboard and follow the pairing flow for each platform. They all run through the same gateway.

What is the admin login?

The username and password you set at deployment. There is no default credential. To change them later, regenerate /etc/nginx/.htpasswd on the server and reload nginx.

Which machine size should I choose?

t3a.small on AWS, or the default General purpose type on Google Cloud. Size up for many concurrent automations or several busy channels.

Where does my data live?

On the server in your own AWS account or GCP project. Conversation history, the memory database and your API keys stay there; Meetrix has no access to the running deployment.

What if SSL does not issue automatically?

Make sure DNS has propagated to the server, then SSH in and run sudo bash /root/certificate\_generate\_standalone.sh.

## Hermes Agent guides and articles

### [Hermes Agent on AWS Marketplace: a Self-Improving AI Agent](https://meetrix.io/blogs/hermes-agent-aws-marketplace/)

Your own agent, without someone else metering every message.

### [Hermes Agent on GCP Marketplace](https://meetrix.io/blogs/hermes-agent-gcp-marketplace/)

An agent that is actually yours, billed the way Google Cloud already bills you.

### [Hermes Agent on AWS: Developer Guide](https://meetrix.io/blogs/hermes-agent-developer-guide/)

Launch the stack, issue SSL, pick a model provider and connect a channel.

## Need a hand with your AI agent?

We build and run self-hosted AI infrastructure for teams every day, from model provider setup to channel integrations. Tell us what you need.

[Contact us](https://meetrix.io/contact-us/)