hermes-agent

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

Updated Sep 9, 2026
One-click install
npx skills add https://github.com/luckybbjason1/trading --skill hermes-agent-luckybbjason1
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: hermes-agent
Source: https://github.com/luckybbjason1/trading/tree/main/.hermes/skills/autonomous-ai-agents/hermes-agent
Command: npx skills add https://github.com/luckybbjason1/trading --skill hermes-agent-luckybbjason1

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Setting up and operating the Hermes Agent framework involves many moving parts: provider credentials, toolsets, messaging gateways, MCP servers, cron jobs, and multi-agent spawning. This Skill consolidates the CLI reference, configuration options, and operational patterns so you can install, configure, troubleshoot, and extend Hermes without digging through scattered documentation. ## Core Features & Use Cases - Complete CLI and slash-command reference: Covers chat, config, auth, tools, skills, MCP servers, gateway, sessions, cron, webhooks, profiles, and credential pools with exact flags and subcommands. - Configuration and security guidance: Documents config.yaml sections, 20+ LLM providers with their auth methods, toolset toggles, secret redaction, PII redaction, and command approval modes. - Multi-agent and durable systems: Explains spawning independent Hermes processes via tmux, delegate_task subagents, cron scheduling, the skill curator, and the kanban multi-agent work queue. - Use Case: You want Hermes to monitor GitHub issues and respond on Telegram. Use this Skill to configure the webhook subscription, enable the gateway, set up the Telegram platform, and verify delivery with the documented test commands. ## Quick Start Ask the agent to install Hermes, run the setup wizard, and configure your preferred model provider using the hermes setup and hermes model 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 curl install script from the official docs, then run hermes setup to launch the interactive wizard. The wizard walks through model, terminal, gateway, tools, and agent configuration sections.

How do I change the model or provider in Hermes?

Run hermes model for an interactive provider and model picker, or pass -m with a model name like anthropic/claude-sonnet-4 to hermes chat. Hermes supports 20+ providers including OpenRouter, Anthropic, DeepSeek, and local models.

Does Hermes Agent support MCP servers?

Yes, Hermes has a built-in MCP client supporting stdio and HTTP transports. Add servers under mcp_servers in config.yaml, and their tools are auto-discovered at startup and registered with the mcp_{server}_{tool} naming prefix.

How do I run multiple Hermes agents in parallel?

Use delegate_task for quick subtasks within a session, or spawn independent processes with hermes chat -q for one-shot tasks and tmux for interactive sessions. The -w worktree flag prevents git conflicts when agents edit code.

Why is Hermes redacting secrets from my tool output?

Secret redaction is enabled by default and scans tool output for API keys and tokens before they enter conversation context. It is snapshotted at startup, so changing security.redact_secrets requires a new session to take effect.

Can Hermes Agent run on Windows?

Yes, Hermes runs natively on Windows including PowerShell, cmd, Windows Terminal, git-bash, and VS Code terminals. Some quirks exist, such as Alt+Enter being intercepted by Windows Terminal, so use Ctrl+Enter for newlines instead.