OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Frameworks

Hermes Agent

Hermes Agent is a Python-based, MIT-licensed open-source AI agent from Nous Research. It combines a conversational interface with a learning loop that creates and improves skills from experience, persists knowledge, searches prior conversations and maintains user context across sessions. The project can run through local or remote terminal backends and exposes conversations through several messaging platforms.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Hermes Agent — OpenViST project profile in Agent Frameworks.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Hermes Agent when an assistant needs retained context, reusable skills, scheduled work or access through more than one conversation channel. Its documented terminal and deployment backends also suit users moving an agent beyond a local laptop.

Who it is for

  • Developers building self-hosted or cloud-hosted AI agents.
  • Operators who need persistent knowledge and searchable conversation history.
  • Teams connecting one assistant to multiple messaging platforms.
  • Researchers working with tool-calling trajectories and agent workflows.

Documented uses

  • Create reusable skills from complex agent interactions.
  • Search previous conversations to recover context across sessions.
  • Maintain user-specific context across multiple sessions.
  • Schedule recurring reports, backups or audits.
  • Delegate parallel workstreams to isolated subagents.
Before you choose

Requirements & limits

The repository is public and MIT-licensed. Installation instructions cover Linux, macOS, WSL2, native Windows and Android / Termux through different documented paths.

  • The learning loop is a central distinction: the project describes skill creation, skill improvement, memory nudges and conversation search.
  • The gateway supports Telegram, Discord, Slack, WhatsApp, Signal and CLI according to the repository description.
  • Deployment can use local, Docker, SSH, Singularity, Modal, Daytona or Vercel Sandbox backends.
  • Model providers can be switched through hermes model, with the repository naming Nous Portal, OpenRouter, OpenAI and user-owned endpoints among supported choices.
  • The project requires managing an agent environment and its dependencies; the installer delegates Python, Node.js, npm, ripgrep, FFmpeg and Python dependencies to its package-management process.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Hermes Agent on Linux, macOS, or WSL2

Install the Hermes command-line agent and open its interactive conversation interface.

Before you start

  • A Linux, macOS, or WSL2 environment.
  • A shell that can run the documented installer command.

Steps

  1. Run the command below.

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

  2. Reload your shell configuration with source ~/.bashrc or, for zsh, source ~/.zshrc.

  3. Run hermes to start a conversation.

Expected outcome

Hermes is installed and its interactive CLI is opened.

Guide limitations

  • This recipe covers the documented Linux, macOS, and WSL2 installer path only.
  • The sources do not specify hardware requirements or verify that installation succeeds in a particular environment.
Documentation 1 ↗Documentation 2 ↗
Source-based practical guide

Install Hermes on native Windows with PowerShell

Install Hermes on Windows and open its interactive conversation interface.

Before you start

  • A native Windows environment with PowerShell.

Steps

  1. Run iex (irm https://hermes-agent.nousresearch.com/install.ps1) in PowerShell.

  2. Run hermes to start a conversation.

Expected outcome

Hermes is installed and its interactive CLI is opened.

Guide limitations

  • This recipe covers the documented native Windows installer path; the sources also identify WSL2 as an alternative but do not detail it here.
  • The sources do not specify hardware requirements or verify that installation succeeds in a particular environment.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
2 October 2026
Original website title
NousResearch/hermes-agent · Official homepage title · retained in its source language
How we review sourcesSuggest a correction