Skip to main content

Quickstart

Install Hermes and start your first conversation in under 2 minutes

CLI Usage

Learn the interactive terminal interface, slash commands, and keybindings

Messaging Gateway

Connect Hermes to Telegram, Discord, Slack, WhatsApp, Signal, and more

Skills System

Procedural memory that grows with every complex task you complete

What is Hermes Agent?

Hermes is a self-improving AI agent built by Nous Research. Unlike conventional agents that reset after every session, Hermes builds up a persistent model of you and your work — creating skills from experience, improving them during use, and searching its own past conversations to recall relevant context. You can run it on a $5 VPS, a GPU cluster, or serverless infrastructure that costs nearly nothing when idle. It’s not tied to your laptop — talk to it from Telegram while it works on a cloud VM.

Key capabilities

Closed learning loop

Autonomous skill creation after complex tasks. Skills self-improve during use. FTS5 session search with LLM summarization for cross-session recall.

Any model, no lock-in

Use Nous Portal, OpenRouter (200+ models), OpenAI, Anthropic, or your own endpoint. Switch with hermes model — no code changes.

Lives where you do

Telegram, Discord, Slack, WhatsApp, Signal, and CLI — all from a single gateway process. Voice memo transcription included.

Runs anywhere

Six terminal backends: local, Docker, SSH, Daytona, Singularity, and Modal. Serverless persistence means your environment hibernates when idle.

40+ built-in tools

Terminal, file ops, web search, browser automation, code execution, image generation, TTS, and more — all configurable per platform.

MCP integration

Connect any MCP server to extend Hermes with external tools, APIs, and data sources.

Quick install

curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash
Works on Linux, macOS, and WSL2. The installer handles Python, Node.js, dependencies, and the hermes command. No prerequisites except git. After installation:
source ~/.bashrc   # reload shell (or: source ~/.zshrc)
hermes             # start chatting!
Windows native is not supported. Install WSL2 first, then run the command above.

Common entry points

What you want to doCommand
Start a conversationhermes
Choose your LLMhermes model
Enable/disable toolshermes tools
Set up messaging platformshermes gateway setup
Run the setup wizardhermes setup
Diagnose issueshermes doctor
Update to latest versionhermes update

Built by Nous Research

Hermes Agent is open source under the MIT license and built by Nous Research, the team behind the Hermes model family and cutting-edge AI research.

Build docs developers (and LLMs) love