hermes-agent

Configure, operate, and extend the Hermes Agent CLI and multi-platform gateway.

Updated May 4, 2026
One-click install
npx skills add https://github.com/Junkfooooood/hermes-governance --skill hermes-agent-junkfooooood
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: hermes-agent
Source: https://github.com/Junkfooooood/hermes-governance/tree/main/skills/autonomous-ai-agents/hermes-agent
Command: npx skills add https://github.com/Junkfooooood/hermes-governance --skill hermes-agent-junkfooooood

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Setting up and operating the Hermes Agent framework involves many moving parts—providers, toolsets, gateway platforms, profiles, memory backends—and this Skill consolidates the commands, configuration options, and troubleshooting steps needed to work with it effectively. ## Core Features & Use Cases - CLI and Configuration Reference: Covers the full hermes command surface including setup, model selection, tools, skills, MCP servers, sessions, cron jobs, webhooks, profiles, and credential pools. - Multi-Agent Spawning: Provides patterns for launching additional Hermes instances via one-shot commands or interactive tmux sessions, including multi-agent coordination with git worktree isolation. - Troubleshooting and Security Toggles: Documents fixes for gateway, voice, memory, and platform issues, plus controls for secret redaction, PII redaction, and command approval modes. - Use Case: A developer wants to run two Hermes agents in parallel—one building a backend API and one building a frontend—using tmux sessions with worktree isolation, then relay API schema context between them. ## Quick Start Ask the agent to install Hermes and run a single query such as "hermes chat -q 'What is the capital of France?'" after completing the setup wizard.

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` to launch the interactive configuration 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, for example `tmux new-session -d -s agent1 'hermes -w'` followed by `tmux send-keys` to deliver prompts. The `-w` worktree flag isolates git state so concurrent agents editing code do not conflict.

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. Authentication uses API keys in the `.env` file or OAuth via `hermes login` for providers like Nous Portal and OpenAI Codex.

Why are my Hermes tool or config changes not taking effect?

Tool and skill changes require a new session via `/reset` because they are loaded at startup to preserve prompt caching. Config changes require restarting the CLI or running `/restart` in the gateway, and code changes require restarting the process.

How do I disable secret redaction in Hermes tool output?

Disable secret redaction by running `hermes config set security.redact_secrets false` in a terminal, then starting a new session. The setting is snapshotted at startup, so changing it mid-session has no effect, which prevents an LLM from disabling redaction on itself.

Why does the Hermes gateway stop when I log out of SSH?

The gateway service stops on SSH logout because user services are terminated with the session. Enable lingering with `sudo loginctl enable-linger $USER` so the systemd user service persists after logout.