Post

Hermes Agent

Self-improving AI agent by Nous Research. Connects to 15+ LLM providers, executes terminal commands, browses the web, and learns from experience. Supports 16 messaging platforms (Telegram, Discord, Slack, WhatsApp, Signal, Matrix, and more) with persistent memory and autonomous skill creation.

Hermes Agent
In Development
This script is currently in active development and may be unstable or incomplete. Use in production environments is not recommended.

Installation

Default install:

1
bash -c "$(curl -fsSL https://raw.githubusercontent.com/community-scripts/ProxmoxVED/main/ct/hermesagent.sh)"
CPU: 2 cores RAM: 4096 MB Disk: 20 GB OS: Debian 13

Notes

Installation sources scripts outside of Community Scripts repo. Please check the source before installing.
Hermes can execute terminal commands. The agent runs as a dedicated 'hermes' service user for isolation.
After container startup, login, switch to the hermes user (su - hermes) and run 'hermes setup' to configure your model provider and gateway server.
OpenAI-compatible API server available at http://:8642/v1. API key is stored in /home/hermes/.hermes/.env.</div> </div>
Access the web dashboard via SSH tunnel: ssh -fNL 9119:localhost:9119 root@, then open http://localhost:9119</div> </div> ## Links - [Official Website](https://hermes-agent.nousresearch.com) - [Documentation](https://hermes-agent.nousresearch.com/docs) ---
Source code
Loading...