hermes-agent

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

1|Updated Feb 17, 2026
One-click install
npx skills add https://github.com/brittb-dev/zerogravityclaw --skill hermes-agent-brittb-dev
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: hermes-agent
Source: https://github.com/brittb-dev/zerogravityclaw/tree/main/src/hermes-core/skills/autonomous-ai-agents/hermes-agent
Command: npx skills add https://github.com/brittb-dev/zerogravityclaw --skill hermes-agent-brittb-dev

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Setting up and operating the Hermes Agent framework involves many CLI commands, config sections, providers, toolsets, and messaging platforms, and this Skill consolidates that operational knowledge so you can install, configure, troubleshoot, and extend Hermes without digging through source code. ## Core Features & Use Cases - CLI and configuration reference: Covers the full command surface (chat, setup, model, gateway, cron, webhooks, profiles, auth pools, MCP) plus config.yaml sections and provider credentials. - Multi-agent spawning: Provides patterns for launching independent Hermes subprocesses in one-shot or interactive tmux PTY mode and coordinating multiple agents. - In-depth references: Includes detailed guides for the native MCP client (stdio/HTTP servers, tool discovery, sampling) and webhook subscriptions (HMAC security, prompt templates, delivery targets). - Use Case: You want Hermes to triage new GitHub issues automatically. Use this Skill to enable the webhook platform, create a subscription with a prompt template, and deliver the agent's response to Telegram. ## Quick Start Ask the agent to install Hermes, run the setup wizard, and configure a model provider using the hermes CLI commands.

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 shell installer (curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash) or via pip install hermes-agent. Then run hermes setup for the interactive wizard, hermes model to pick a provider, and hermes doctor to verify dependencies.

How do I connect MCP servers to Hermes Agent?▼

Add servers under the mcp_servers key in ~/.hermes/config.yaml using either a stdio command (npx/uvx) or an HTTP url, then restart Hermes. Tools are auto-discovered at startup and registered with the mcp_{server}_{tool} naming prefix across all platforms.

Which LLM providers does Hermes Agent support?▼

Hermes Agent supports over 20 providers including OpenRouter, Anthropic, OpenAI, Google Gemini, DeepSeek, xAI, Kimi, MiniMax, and local or custom endpoints via model.base_url. Credentials are managed with hermes auth, which supports OAuth and API-key pooling with automatic rotation.

How do I spawn multiple Hermes agents in parallel?▼

Use hermes chat -q for one-shot background tasks, or tmux new-session -d with hermes for interactive PTY sessions since prompt_toolkit requires a real terminal. You can send prompts with tmux send-keys and read output with tmux capture-pane to coordinate agents.

Why are my Hermes config changes not taking effect?▼

Many settings such as toolsets, security.redact_secrets, and display options are read once at startup, so they require a fresh session via /reset or a new hermes invocation. Toggling them mid-session through environment variables will not apply to the running process.

Can Hermes Agent receive webhooks from GitHub or Stripe?▼

Yes, enable the webhook platform in config.yaml or via hermes gateway setup, then create routes with hermes webhook subscribe using prompt templates with {dot.notation} payload fields. Each subscription gets an HMAC-SHA256 secret and can deliver agent responses to Telegram, Discord, or GitHub comments.