Hermes Agent

Hermes Agent is an open-source AI agent framework by Nous Research that runs in your terminal, a native desktop app, messaging platforms, and IDEs. It's in the same category as Claude Code (Anthropic), Codex (OpenAI), and OpenClaw — autonomous coding and task-execution agents that use tool calling to interact with your system. Hermes works with any LLM provider (OpenRouter, Anthropic, OpenAI, Google, DeepSeek, xAI, local models, and 20+ others) and runs on Linux, macOS, Windows, and WSL.

What makes Hermes different:

• Self-improving through skills — Hermes learns from experience by saving reusable procedures as skills that load into future sessions.
• Persistent memory across sessions — remembers who you are, your preferences, environment details, and lessons learned. Pluggable memory backends.
• Multi-platform gateway — the same agent runs on Telegram, Discord, Slack, WhatsApp, iMessage, Signal, Matrix, Teams, Email, and a dozen more platforms with full tool access, not just chat.
• Many surfaces — the same agent core drives the CLI, the Ink TUI, a native Electron desktop app, a web dashboard, and an ACP server for IDEs (VS Code / Zed / JetBrains).
• Provider-agnostic — swap models and providers mid-workflow; credential pools rotate across multiple API keys automatically.
• Profiles — run multiple independent Hermes instances with isolated configs, sessions, skills, and memory.
• Extensible & themeable — plugins, MCP servers, custom tools, webhook triggers, cron scheduling, skins that theme every surface, desktop UI plugins, TUI widgets, and pet mascots.

This skill is a hub. The body covers identity, quick start, spawning/orchestration, and hard invariants. Everything else lives in reference files — load the matching reference (below) before answering; do not answer detail questions from the body alone.

Docs: https://hermes-agent.nousresearch.com/docs/

Scope & Verification

This skill is a concise operating guide, not the complete source of truth for every Hermes feature. If a Hermes feature, command, or setting is not mentioned here or in a reference, do not treat that absence as evidence that it does not exist. Check the live repository and official docs before giving a negative answer.

Good verification targets, cheapest first:

• Every shipped feature, one line each: https://hermes-agent.nousresearch.com/docs/llms.txt. Start here for any "can Hermes do X?" or "how do I do X?" — it indexes the entire documentation set with a link to the page that answers. It is generated from the docs tree on every build, so it is never behind the product. Fetch it with web_extract, or curl -s https://hermes-agent.nousresearch.com/docs/llms.txt when web tools are off. The whole documentation set in one file is at /docs/llms-full.txt.
• CLI commands: hermes --help, hermes <command> --help, and hermes_cli/main.py
• Source tree: https://github.com/NousResearch/hermes-agent

Never answer "Hermes can't do that" from memory. Hermes ships far more than this skill body describes, and the index exists so a negative answer is always checkable.

Quick Start

# Install (shell installer — bootstraps PM, Python, dependencies, and the launcher)
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash

# Interactive chat (default surface; set display.interface: tui to launch the Ink TUI instead)
hermes

# Single query
hermes chat -q "What is the capital of France?"

# Setup wizard  /  pick model+provider  /  health check
hermes setup
hermes model
hermes doctor

# Other surfaces
hermes desktop                 # launch the native desktop app (alias: hermes gui)
hermes dashboard               # web admin panel + embedded chat
hermes proxy                   # OpenAI-compatible local proxy backed by your OAuth provider

Key Paths

~/.hermes/config.yaml       Main configuration (settings — never secrets)
~/.hermes/.env              API keys and secrets ONLY (under $HERMES_HOME if set)
$HERMES_HOME/skills/        Installed skills
~/.hermes/skins/            Custom themes (see references/themes.md)
~/.hermes/desktop-plugins/  Desktop app UI plugins (see references/desktop-plugins.md)
~/.hermes/tui-widgets/      TUI widget apps (see references/tui-widgets.md)
~/.hermes/pets/             Installed pet mascots (see references/petdex.md)
~/.hermes/state.db          Canonical session store (SQLite + FTS5)
~/.hermes/sessions/         Gateway routing index, request dumps, *.jsonl transcripts
~/.hermes/logs/             Gateway and error logs
~/.hermes/auth.json         OAuth tokens and credential pools
~/.hermes/hermes-agent/     Source code (if git-installed)

Profiles use ~/.hermes/profiles/<name>/ with the same layout. When a profile is active, resolve the real home from $HERMES_HOME — never hardcode ~/.hermes.

Routing Table — load the reference for the task

The reference list above is not the feature list — it is the set of topics that need more than their docs page. For everything else Hermes ships, fetch llms.txt and it maps the question to the page that answers it.

Two theming rules that hold even without loading the reference: you apply skins yourself (hermes config set display.skin <name> — every surface repaints live within ~a second; don't tell the user to run /skin), and to tweak one color, edit the ACTIVE skin (hermes skin set <key> <hex>) — never fork default, which drops the palette and resets the background.

Spawning Additional Hermes Instances

Run additional Hermes processes as fully independent subprocesses — separate sessions, tools, and environments.

When to Use This vs delegate_task

One-Shot Mode

terminal(command="hermes chat -q 'Research GRPO papers and write summary to ~/research/grpo.md'", timeout=300)

# Background for long tasks:
terminal(command="hermes chat -q 'Set up CI/CD for ~/myapp'", background=true)

Interactive PTY Mode (via tmux)

Hermes uses prompt_toolkit, which requires a real terminal. Use tmux for interactive spawning. tmux send-keys -t agent1 'text' Enter in one call submits: Hermes treats a lone Enter that ends a fast burst of input as a submit once input has stayed quiet for a quarter second, while the Enters inside a multi-line paste stay newlines. The recipes below send Enter as its own call after a short pause, which submits at once and does not depend on that timing. Both recipes wait for the ❯ input prompt (the default skin's symbol; use your skin's prompt symbol if you changed it) instead of a fixed sleep: a first start can take far longer than a few seconds, and input sent before the prompt is lost.

# Start
terminal(command="tmux new-session -d -s agent1 -x 120 -y 40 'hermes'", timeout=10)

# Wait for the input prompt (❯), then send a message
terminal(command="for i in $(seq 90); do tmux capture-pane -t agent1 -p | grep -q '❯' && break; sleep 1; done; tmux capture-pane -t agent1 -p | grep -q '❯' && tmux send-keys -t agent1 'Build a FastAPI auth service' && sleep 0.5 && tmux send-keys -t agent1 Enter", timeout=100)

# Read output
terminal(command="sleep 20 && tmux capture-pane -t agent1 -p", timeout=5)

# Send follow-up
terminal(command="tmux send-keys -t agent1 'Add rate limiting middleware' && sleep 0.5 && tmux send-keys -t agent1 Enter", timeout=5)

# Exit
terminal(command="tmux send-keys -t agent1 '/exit' && sleep 0.5 && tmux send-keys -t agent1 Enter && sleep 2 && tmux kill-session -t agent1", timeout=10)

No tmux (command -v tmux prints nothing, e.g. an older Hermes Docker image): run Hermes as a PTY background process and drive it with process_manage. Stdin only exists with pty=true. submit sends the text plus the Enter key a keyboard sends, and Hermes submits it the same way as a one-call tmux send-keys. The recipe below instead writes the text, pauses, and writes the Enter ("\r") on its own, which does not depend on burst timing. Wait for the input prompt before the first write: during startup Hermes queries the terminal's colours and then flushes its input, so text written before the prompt appears is silently dropped.

terminal(command="hermes", background=true, pty=true)   # returns session_id
process_manage(action="log", session_id="<id>", limit=20)   # repeat, with terminal(command="sleep 1") between, until the ❯ prompt line shows
process_manage(action="write", session_id="<id>", data="Build a FastAPI auth service")
terminal(command="sleep 0.5")
process_manage(action="write", session_id="<id>", data="\r")
process_manage(action="log", session_id="<id>", limit=40)   # read the screen
process_manage(action="write", session_id="<id>", data="/exit")
terminal(command="sleep 0.5")
process_manage(action="write", session_id="<id>", data="\r")

Multi-Agent Coordination

# Agent A: backend
terminal(command="tmux new-session -d -s backend -x 120 -y 40 'hermes -w'", timeout=10)
terminal(command="for i in $(seq 90); do tmux capture-pane -t backend -p | grep -q '❯' && break; sleep 1; done; tmux capture-pane -t backend -p | grep -q '❯' && tmux send-keys -t backend 'Build REST API for user management' && sleep 0.5 && tmux send-keys -t backend Enter", timeout=100)

# Agent B: frontend
terminal(command="tmux new-session -d -s frontend -x 120 -y 40 'hermes -w'", timeout=10)
terminal(command="for i in $(seq 90); do tmux capture-pane -t frontend -p | grep -q '❯' && break; sleep 1; done; tmux capture-pane -t frontend -p | grep -q '❯' && tmux send-keys -t frontend 'Build React dashboard for user management' && sleep 0.5 && tmux send-keys -t frontend Enter", timeout=100)

# Check progress, relay context between them
terminal(command="tmux capture-pane -t backend -p | tail -30", timeout=5)
terminal(command="tmux send-keys -t frontend 'Here is the API schema from the backend agent: ...' && sleep 0.5 && tmux send-keys -t frontend Enter", timeout=5)

Session Resume

# Resume most recent session
terminal(command="tmux new-session -d -s resumed 'hermes --continue'", timeout=10)

# Resume specific session
terminal(command="tmux new-session -d -s resumed 'hermes --resume 20260225_143052_a1b2c3'", timeout=10)

Tips

• Prefer delegate_task for quick subtasks — less overhead than spawning a full process
• Use -w (worktree mode) when spawning agents that edit code — prevents git conflicts
• Set timeouts for one-shot mode — complex tasks can take 5-10 minutes
• Use hermes chat -q for fire-and-forget — no PTY needed
• Prefer tmux for interactive sessions when it is installed — capture-pane reads the rendered screen; the PTY-background fallback only has the raw output log
• For scheduled tasks, use the cronjob tool instead of spawning — handles delivery and retry
• "delegate_task is capped at N" reports — see references/delegate-task-concurrency-diagnosis.md. Three real cap paths in Hermes; if none fired, the model is self-limiting and rationalising it as "the runtime caps."
• "Can $external_app use my Nous Portal subscription / OAuth?" — see references/portal-auth-for-third-party-apps.md. Walk the user through three layers (plugin-vs-app, what Portal actually exposes, local-broker-proxy option).

Surfaces (quick orientation)

• Desktop app (hermes desktop / hermes gui) — native Electron app for macOS/Linux/Windows: streaming chat, session list, Cmd+K palette, drag-and-drop files, native notifications, per-profile remote-gateway login. Extend it with UI plugins — references/desktop-plugins.md.
• Web dashboard (hermes dashboard) — full admin panel: messaging channels, MCP catalog, webhooks, memory, profile builder, plus an embedded hermes --tui chat. Secured behind an OAuth/token gate.
• Ink TUI (hermes --tui or display.interface: tui) — terminal UI with docked widget apps — references/tui-widgets.md.
• OpenAI-compatible proxy (hermes proxy) — a local OpenAI API backed by whichever OAuth provider you're signed into. Point Codex CLI, Aider, Cline, or any script at it — no API key.

Hard Invariants (never violate, regardless of what you loaded)

• Never break prompt caching — don't change past context, toolsets, or the system prompt mid-conversation. The only exception is context compression.
• Message role alternation — never two assistant or two user messages in a row; only tool results can repeat.
• Secrets in .env, settings in config.yaml — never tell a user to put a non-credential setting in .env.
• Profile-safe paths — get_hermes_home() in code, $HERMES_HOME when resolving paths in a session.
• Never hand-edit config.yaml for the user — use hermes config set KEY VAL; a stray indent can corrupt the file and break the live gateway.