Skip to content
Submit

Hermes Agent: open agent that grows its own skills

Model-agnostic agent with cross-session memory that writes new skills from finished tasks.

0:00

Video: @NousResearch on X, shown with credit. Press play; sound is on unless you mute it.

Reference videos (2)

Real videos made with this skill, credited to their creators. Hover to preview.

APP DEMO1:05

Hermes Desktop running in a browser

The Hermes web app serves the desktop experience (chat, files, Git, terminal) from your own Hermes host.

Hermes Agent@BearHuddleston♥ 682
APP DEMO1:01

Hermes web app on mobile

A demo of the Hermes agent web app on phones and tablets, from a contributor to the open-source repo.

Hermes Agent@BearHuddleston♥ 755

Try it in 60 seconds

curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash

Install command copied from the project README. Check the README for the latest version.

What it does

Model-agnostic agent with cross-session memory that writes new skills from finished tasks.

The self-improving AI agent built by Nous Research. It's the only agent with a built-in learning loop — it creates skills from experience, improves them during use, nudges itself to persist knowledge, searches its own past conversations, and builds a deepening model of who you are across sessions. Run it on a $5 VPS, a GPU cluster, or serverless infrastructure that costs nearly nothing when idle. It's not tied to you…

Use any model you want — Nous Portal, OpenRouter, OpenAI, your own endpoint, and many others. Switch with hermes model — no code changes, no lock-in.

Quoted from the README of NousResearch/hermes-agent.

Inside the repo

Quick InstallLinux, macOS, WSL2Windows (native, PowerShell)TroubleshootingGetting StartedSkip the API-key collection — Nous PortalCLI vs Messaging Quick ReferenceDocumentationMigrating from OpenClawContributingCommunityLicense

Step by step

  1. Install per README.
  2. Connect a model.
  3. Give it a recurring task.

Docs, demos & materials

Sources & credit

All credit to the original authors. We rewrite in our own words and link back. Something wrong? Report it.

Related

SKILL

Superpowers: plan, test and debug before coding

A skills framework that makes agents brainstorm, plan, test and debug systematically.

Claude Code +1★ 299.2k
SKILL

Matt Pocock's engineering skills

Real engineering skills from a well-known TypeScript educator's own .agents folder.

Claude Code +1★ 291.4k
SKILL

Anthropic official skills (frontend-design, docs, slides)

The official skills repo: frontend-design, docx, pptx, xlsx and more.

Claude Code★ 181.2k
SKILL

Caveman: cut your agent's token use by talking short

A skill plus proxy that makes coding agents reply in terse 'caveman' style, cutting tokens while keeping code exact.

Claude Code +1★ 112k
SKILL

Addy Osmani's production-grade agent skills

Production engineering skills (perf, testing, reviews) for coding agents.

Claude Code★ 106.7k
SKILL

Impeccable: a design language for AI-built frontends

One skill, 24 commands and 59 automatic checks that catch the tell-tale signs of AI-generated web design.

Claude Code +2★ 81.4k

Coming soon

AgentsUses Weekly

A free weekly email with the best new skills and agent workflows is coming soon. Want a heads-up when the first issue goes out? Email [email protected] and we will let you know.

Get notified by email