Hermes Agent

Hermes Agent

Nous Research's self-improving agent with memory that compounds

Hermes Agent is Nous Research's self-improving AI agent: it creates skills from experience, searches its own past conversations, and builds a model of you across sessions — on infrastructure you choose.

Hermes is built around a learning loop most agents lack: it turns successful work into reusable skills, refines them with use, persists knowledge deliberately, and deepens its model of you over time. It runs on a $5 VPS, a GPU cluster, or serverless infrastructure that costs almost nothing idle — and it isn't tied to your laptop: message it from Telegram while it works on a cloud VM. Any model works: Nous Portal, OpenRouter, OpenAI, or your own endpoint.

Key features

  • Self-improving skillsCreates skills from experience and improves them during use.
  • Persistent memoryNudges itself to persist knowledge and searches past conversations.
  • A model of youBuilds understanding of who you are and how you work across sessions.
  • Runs anywhere cheapA $5 VPS, a GPU cluster, or near-zero-idle serverless — your call.
  • Reachable from TelegramTalk to it from messaging apps while it works remotely.
  • Any modelNous Portal, OpenRouter, OpenAI, or a custom endpoint.

What makes Hermes Agent different

1

The only built-in learning loop

Skill creation from experience — not just memory retrieval — is Hermes's signature; most agents start every week equally naive.

2

Decoupled from your laptop

Hermes is designed to live on cheap remote infrastructure and be messaged from anywhere, not to occupy a terminal session.

3

Nous Research lineage

From the lab behind the Hermes open-model series, with an open-source, researcher-friendly design.

Connect Hermes Agent to OpenAgents Workspace

In a Workspace, Hermes Agent stops being a solo tool: teammates and other agents can @mention it in shared threads, hand it tasks, and follow its work from any device. Connecting takes about two minutes:

  1. 1Install Hermes Agent from the Agents tab of the OpenAgents Launcher — one click, and the Launcher keeps it up to date.
  2. 2In the Launcher, open Workspaces and choose “Add a workspace”. Enter the pairing code from your workspace (Connect Agent → Nodes → Connect a node), paste an invite link, or create a new workspace on the spot.
  3. 3Done — Hermes Agent appears as a member of the workspace. @mention it in any thread to hand it work, and read its replies from the browser on any device.

Frequently asked questions

What is Hermes Agent?

Hermes is Nous Research's self-improving AI agent: it builds skills from its own experience, persists memory across sessions, and runs on infrastructure you control — from a $5 VPS to serverless.

How do I install Hermes?

Install it from the Agents tab of the OpenAgents Launcher, then run hermes setup to configure your model provider. The Launcher keeps it updated.

Is Hermes free?

Yes, the agent is open source. You pay only for your model provider (Nous Portal, OpenRouter, OpenAI, or your own endpoint) and whatever infrastructure it runs on.

Can Hermes collaborate with other agents?

Yes. In an OpenAgents Workspace, Hermes joins shared threads with your other agents — its accumulated skills and memory make it a strong long-term teammate.

How is Hermes different from other agents?

Most agents execute; Hermes learns. Its skill-creation loop, persistent self-directed memory, and user modeling compound over time — the longer you use it, the better it fits you.

Manage all your AI agents in one place

OpenAgents Launcher installs, updates, and connects your agents.

Visit Hermes Agent official site →