hermes-agent

Configure, extend, and operate the Hermes Agent CLI across terminal and messaging platforms.

Updated Jun 5, 2026
One-click install
npx skills add https://github.com/xu1713/openhorse --skill hermes-agent-xu1713
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: hermes-agent
Source: https://github.com/xu1713/openhorse/tree/main/openhorse/openhorse/skills/autonomous-ai-agents/hermes-agent
Command: npx skills add https://github.com/xu1713/openhorse --skill hermes-agent-xu1713

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Setting up and operating the Hermes Agent framework involves many CLI commands, config sections, providers, toolsets, and platform integrations, and this Skill consolidates that operational knowledge so you can configure, troubleshoot, and extend Hermes without digging through source code. ## Core Features & Use Cases - CLI and configuration reference: Covers every hermes command (chat, setup, config, tools, skills, mcp, gateway, cron, profiles, auth) plus config.yaml sections and provider credentials. - Multi-agent orchestration: Explains spawning additional Hermes instances via one-shot mode, tmux PTY sessions, worktree isolation, and coordination patterns versus delegate_task. - Durable background systems: Documents delegation, cron scheduling, the skill curator, and the kanban multi-agent work queue with their CLI verbs and config knobs. - Use Case: You want two agents building a backend and frontend in parallel. Use this Skill to spawn tmux-based Hermes sessions with worktree isolation, relay context between them, and monitor progress. ## Quick Start Ask the agent to show you how to install Hermes, pick a model provider, and run your first chat query using the hermes CLI.

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 by running the install script from the NousResearch GitHub repository, then run hermes setup for the interactive wizard. Use hermes model to pick a provider and hermes doctor to verify dependencies and configuration.

How do I spawn multiple Hermes agents in parallel?

Spawn parallel Hermes agents using tmux sessions with hermes -w for git worktree isolation, or use hermes chat -q for fire-and-forget one-shot tasks. For quick subtasks, prefer the delegate_task tool, which runs subagents inside the parent process with less overhead.

Which LLM providers does Hermes Agent support?

Hermes Agent supports over 20 providers including OpenRouter, Anthropic, OpenAI, DeepSeek, Google Gemini, xAI, Kimi, and local models. Set the provider with hermes model or hermes setup, and store keys in ~/.hermes/.env or via hermes auth credential pools.

When should I use delegate_task versus 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 needing full tool access, interactive PTY control, or lifetimes of hours to days.

Why are my Hermes config changes not taking effect?

Many Hermes settings, including security.redact_secrets and tool toggles, are read once at startup, so changes require a new session via /reset or a fresh hermes invocation. Tool changes never apply mid-conversation to preserve prompt caching.

Does Hermes Agent work on Windows?

Hermes Agent runs natively on Windows in PowerShell, cmd, Windows Terminal, git-bash, and VS Code terminals. Note that Alt+Enter is intercepted by Windows Terminal for fullscreen, so use Ctrl+Enter to insert newlines in the prompt.