hermes-agent

Configure, extend, and orchestrate Hermes Agent instances across CLI, desktop, and messaging platforms.

Updated Aug 22, 2026
One-click install
npx skills add https://github.com/vivekgoquest/hermes-agent-stable --skill hermes-agent-vivekgoquest
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: hermes-agent
Source: https://github.com/vivekgoquest/hermes-agent-stable/tree/main/skills/autonomous-ai-agents/hermes-agent
Command: npx skills add https://github.com/vivekgoquest/hermes-agent-stable --skill hermes-agent-vivekgoquest

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Operating Hermes Agent involves a large surface area — CLI commands, provider credentials, gateway platforms, skins, plugins, cron jobs, and multi-agent spawning — and this Skill routes every question to the correct reference file or documentation page instead of answering from incomplete memory. ## Core Features & Use Cases - Guided configuration and operation: Covers installation, model/provider setup, profiles, toolsets, voice (STT/TTS), security toggles, and the full CLI command surface. - Extension authoring: Provides templates and SDK references for building desktop UI plugins, TUI widgets, custom skins, and pet mascots without modifying core code. - Multi-agent orchestration: Documents spawning independent Hermes processes via tmux, delegate_task concurrency behavior, cron scheduling, and the kanban work queue. - Use Case: A user asks why their delegate_task batch ran fewer subagents than configured; the Skill loads the concurrency diagnosis reference, checks the three real cap paths in the logs, and identifies whether the model self-limited the batch. ## Quick Start Ask the agent to help you install Hermes, configure a model provider, or troubleshoot a specific feature, and it will load the matching reference file before answering.

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?▼

Run the shell installer with curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash, then use hermes setup for the wizard, hermes model to pick a provider, and hermes doctor to verify the installation.

How do I spawn multiple Hermes agents in parallel?▼

Use delegate_task for quick subtasks within one process, or spawn fully independent processes with tmux new-session -d -s name 'hermes -w' for long interactive missions. The -w flag uses worktree mode to prevent git conflicts between agents.

Which LLM providers does Hermes Agent support?▼

Hermes supports 35+ providers including OpenRouter, Anthropic, OpenAI, Google, DeepSeek, xAI, and Nous Portal via OAuth. Credentials are managed with hermes auth, and multiple keys per provider rotate automatically in a pool.

Why did delegate_task run fewer subagents than I configured?▼

Only three code paths cap batches: a per-call reject, a per-turn truncator, both governed by delegation.max_concurrent_children. If neither log line appears, the model self-limited the batch, which is a known reasoning-model behavior, not a runtime cap.

Can I customize the Hermes desktop app interface?▼

Yes, write a plain JavaScript ESM plugin in ~/.hermes/desktop-plugins/<id>/plugin.js using the @hermes/plugin-sdk imports. The app hot-reloads the file on save, and plugins can add panes, statusbar chips, commands, themes, and full pages.

Where does Hermes store configuration and API keys?▼

Settings go in ~/.hermes/config.yaml and secrets only in ~/.hermes/.env, both under $HERMES_HOME when set. Never hand-edit config.yaml; use hermes config set KEY VAL to avoid corrupting the live gateway.