adbfd66056
Adds container scripts for Hermes Agent (Nous Research), a self-improving AI agent with LLM provider integration, terminal execution, web browsing, and multi-platform messaging support. Files: - ct/hermes-agent.sh - install/hermes-agent-install.sh - json/hermes-agent.json - ct/headers/hermes-agent Deviations from standard patterns (justified): 1. Uses upstream installer (curl-pipe) instead of fetch_and_deploy_gh_release: Hermes is a uv-managed Python application with complex dependency resolution, virtualenv management, and binary placement—not a single binary or tarball from GitHub Releases. 2. Dedicated 'hermes' service user (not running as root): The agent executes arbitrary terminal commands on behalf of the user. Running as root would give the AI unrestricted system access. This follows the protonmail-bridge service-user pattern for isolation. 3. Dashboard (port 9119) bound to localhost only, requiring SSH tunnel: The web UI provides admin access to an AI that can execute commands. SSH tunnel provides an authentication/authorization boundary. 4. /usr/bin/hermes shim script: The hermes CLI validates cwd permissions; running 'hermes' as root from /root fails. The shim cd's to /home/hermes and exec's as the hermes user via runuser. 5. setsid --wait wrapping of upstream installer: The upstream installer probes /dev/tty for interactive prompts even with --skip-setup; setsid detaches the controlling terminal.
53 lines
2.0 KiB
JSON
53 lines
2.0 KiB
JSON
{
|
|
"name": "Hermes Agent",
|
|
"slug": "hermes-agent",
|
|
"categories": [
|
|
20
|
|
],
|
|
"date_created": "2026-05-02",
|
|
"type": "ct",
|
|
"updateable": true,
|
|
"privileged": false,
|
|
"interface_port": 8642,
|
|
"documentation": "https://hermes-agent.nousresearch.com/docs",
|
|
"website": "https://hermes-agent.nousresearch.com",
|
|
"logo": "https://cdn.jsdelivr.net/gh/selfhst/icons@main/webp/hermes.webp",
|
|
"description": "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.",
|
|
"install_methods": [
|
|
{
|
|
"type": "default",
|
|
"script": "ct/hermes-agent.sh",
|
|
"config_path": "/home/hermes/.hermes/",
|
|
"resources": {
|
|
"cpu": 2,
|
|
"ram": 4096,
|
|
"hdd": 20,
|
|
"os": "debian",
|
|
"version": "13"
|
|
}
|
|
}
|
|
],
|
|
"default_credentials": {
|
|
"username": "hermes",
|
|
"password": null
|
|
},
|
|
"notes": [
|
|
{
|
|
"text": "Warning: Hermes can execute terminal commands. The agent runs as a dedicated 'hermes' service user for isolation.",
|
|
"type": "warning"
|
|
},
|
|
{
|
|
"text": "After container startup, SSH in as the 'hermes' user and run 'hermes setup' to configure your LLM provider (OpenRouter, Anthropic, OpenAI, Nous Portal, or custom endpoint).",
|
|
"type": "info"
|
|
},
|
|
{
|
|
"text": "OpenAI-compatible API server available at http://<container-ip>:8642/v1. API key is stored in /home/hermes/.hermes/.env.",
|
|
"type": "info"
|
|
},
|
|
{
|
|
"text": "Access the web dashboard via SSH tunnel: ssh -L 9119:localhost:9119 hermes@<container-ip>, then open http://localhost:9119",
|
|
"type": "info"
|
|
}
|
|
]
|
|
}
|