hermes-agent

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

14|5|Updated Apr 9, 2026
One-click install
npx skills add https://github.com/MLT-OSS/hermes-agent-go --skill hermes-agent-mlt-oss
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: hermes-agent
Source: https://github.com/MLT-OSS/hermes-agent-go/tree/main/skills/autonomous-ai-agents/hermes-agent
Command: npx skills add https://github.com/MLT-OSS/hermes-agent-go --skill hermes-agent-mlt-oss

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Setting up and operating the Hermes Agent framework involves many moving parts — CLI commands, config files, providers, toolsets, gateway platforms, profiles, and multi-agent spawning — and this Skill consolidates all of that operational knowledge into one reference so you can configure, troubleshoot, and extend Hermes without hunting through documentation. ## Core Features & Use Cases - Complete CLI and configuration reference: Covers every hermes subcommand (chat, setup, model, tools, skills, mcp, gateway, sessions, cron, profiles, auth), slash commands, config.yaml sections, and 18 supported LLM providers with their auth methods. - Multi-agent orchestration guidance: Explains when to use delegate_task versus spawning independent hermes processes, with concrete tmux-based patterns for interactive PTY sessions and multi-agent coordination using git worktree isolation. - Troubleshooting and contributor reference: Provides diagnostic flows for voice, tools, model, skills, and gateway issues, plus a contributor guide covering project layout, adding tools and slash commands, testing, and commit conventions. - Use Case: You want to run two Hermes agents in parallel — one building a backend API and one building a frontend — without git conflicts. This Skill gives you the exact tmux and worktree commands to spawn, message, monitor, and shut down both agents. ## Quick Start Ask the agent to show you how to install Hermes, run the setup wizard, and start your first chat session with a chosen model provider.

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 NousResearch 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 in tmux sessions for interactive mode, or use hermes chat -q for one-shot background tasks. Add the -w worktree flag when agents edit code to prevent git conflicts, and use delegate_task for quick subtasks instead.

Which LLM providers does Hermes Agent support?

Hermes supports 18 providers including OpenRouter, Anthropic, DeepSeek, Z.AI, Kimi, and MiniMax via API keys, plus Nous Portal and OpenAI Codex via OAuth login. Custom endpoints work through the model.base_url and model.api_key config settings.

Why are my Hermes tools or skills not taking effect?

Tool and skill changes require a new session to apply, so run /reset after enabling toolsets with hermes tools. Verify installation with hermes skills list and check platform enablement with hermes skills config, or load explicitly with /skill name.

When should I use delegate_task versus spawning a hermes process?

Use delegate_task for quick parallel subtasks that finish in 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.