hermes-agent

Configure, operate, and extend the Hermes Agent CLI across providers, gateways, and multi-agent workflows.

Updated Jul 10, 2026
One-click install
npx skills add https://github.com/AvaTar-ArTs/.Agent-skills --skill hermes-agent-avatar-arts
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: hermes-agent
Source: https://github.com/AvaTar-ArTs/.Agent-skills/tree/main/skills/autonomous-ai-agents/hermes-agent
Command: npx skills add https://github.com/AvaTar-ArTs/.Agent-skills --skill hermes-agent-avatar-arts

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Setting up and operating the Hermes Agent framework involves many moving parts—providers, toolsets, gateways, profiles, cron jobs, and multi-agent spawning—and this Skill consolidates the commands, configuration keys, and troubleshooting knowledge needed to work with it effectively. ## Core Features & Use Cases - CLI and Configuration Reference: Covers the full hermes command surface including setup, model/provider selection, tools, skills, MCP servers, sessions, cron, webhooks, profiles, and credential pools. - Multi-Agent Orchestration: Explains how to spawn additional Hermes instances via one-shot mode, tmux-based interactive PTY sessions, worktree isolation, and delegation for parallel task execution. - Gateway and Platform Operations: Documents running Hermes across Telegram, Discord, Slack, WhatsApp, and 10+ messaging platforms, plus security toggles like secret redaction, PII redaction, and approval modes. - Use Case: A developer wants to run two isolated Hermes agents—one building a backend API and one building a frontend—and relay context between them; this Skill provides the exact tmux and worktree commands to do it. ## Quick Start Ask the agent to help you install Hermes, run the setup wizard, and configure a model provider such as OpenRouter or Anthropic.

Frequently Asked Questions about hermes-agent

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I install and set up Hermes Agent?

Install Hermes Agent with the official install script from the Nous Research GitHub repository, then run `hermes setup` to launch the interactive wizard. Use `hermes model` to pick a provider and `hermes doctor` to verify dependencies and configuration.

How do I run multiple Hermes agents in parallel?

Spawn independent Hermes processes using `hermes chat -q` for one-shot tasks or tmux sessions for interactive agents. Use the `-w` worktree flag when agents edit code to prevent git conflicts, and prefer `delegate_task` for quick subtasks.

Which LLM providers does Hermes Agent support?

Hermes supports over 20 providers including OpenRouter, Anthropic, OpenAI, DeepSeek, Google Gemini, xAI, Kimi, and local models. Configure them via `hermes model` or `hermes setup`, with API keys stored in the `.env` file or OAuth via `hermes login`.

Can Hermes Agent run on messaging platforms like Telegram or Discord?

Yes, the Hermes gateway runs the same agent on Telegram, Discord, Slack, WhatsApp, Signal, Matrix, Email, and more with full tool access. Start it with `hermes gateway run` or install it as a background service with `hermes gateway install`.

Why is Hermes prompting me before running shell commands?

Hermes defaults to `approvals.mode: manual`, which prompts before destructive commands like `rm -rf`. Change it with `hermes config set approvals.mode smart` for LLM-assisted auto-approval, or use `--yolo` per invocation to bypass prompts entirely.

When should I use delegate_task instead of spawning a Hermes process?

Use `delegate_task` for quick parallel subtasks lasting minutes with a subset of parent tools. Spawn a full Hermes process for long autonomous missions lasting hours, tasks needing full tool access, or interactive sessions via tmux.