Nous Hermes Commands & Prompt Reference

42 commands & parameters · 2 categories · Source: Hermes 4 model card & Hermes Agent docs

Nous Research's Hermes spans two typed surfaces: the prompt format of the open Hermes 4 models, and the slash commands of Hermes Agent, the terminal-native agent built on them. The model side is small but precise - Hermes 4 405B speaks the Llama 3.1 header-token format, reasoning mode is switched with the thinking=True chat-template flag or the official deep-thinking system prompt, internal reasoning arrives inside <think> tags, and tool calling uses the <tools>, <tool_call>, and <tool_response> tag protocol documented on the model card.

Hermes Agent's command set reads like a superset of most coding agents: session branching with /branch, git worktrees with /worktree, background runs with /background, plus operational commands for gateways, billing, and approvals. Everything here is taken from the official slash-command reference; commands marked CLI-only do not work from messaging channels.

One practical note on the model side: the reasoning system prompt is not all-or-nothing. The model card states you can add instructions before or after it to adjust thinking effort, style, and output format, and interleave it with the tool-definition system message.

All Commands

Hermes 4 Prompt Format & Tool Calling (8)

Command / SyntaxWhat it doesNotes
<|start_header_id|>role<|end_header_id|>Llama 3.1 chat header tokens used by Hermes 4 405BRoles: system, user, assistant. Each turn ends with <|eot_id|>. Smaller Hermes 4 models use ChatML instead.
<|eot_id|>End-of-turn token in the 405B prompt formatCloses each header-delimited message.
thinking=TrueChat template flag that activates reasoning modePass to the tokenizer chat template; alternatively use the deep-thinking system prompt from the model card.
<think> </think>Tags enclosing the model's internal reasoningEmitted when reasoning mode is active; strip them to get the final answer only.
You are a deep thinking AI...Official reasoning-mode system promptFull text on the model card. Additional system instructions before or after it adjust thinking effort, style, and format.
<tools> </tools>System-prompt tags wrapping the JSON tool signaturesFunction definitions go inside these tags in the system message.
<tool_call> </tool_call>Tags the model emits around a JSON function callParse the JSON inside to execute the call.
<tool_response> </tool_response>Tags wrapping the tool result you feed backReturn the function output inside these tags in a tool role message.

Hermes Agent Slash Commands (34)

Command / SyntaxWhat it doesNotes
/new [name]Start a new session (fresh session ID + history)Alias: /reset. Optional [name] sets the initial session title — e.g.
/clearClear screen and start a new sessionType in the Hermes CLI/TUI or a connected messaging channel.
/historyShow conversation history (respectsType in the Hermes CLI/TUI or a connected messaging channel.
/saveSave the current conversationType in the Hermes CLI/TUI or a connected messaging channel.
/promptCompose your next prompt in $EDITOR (markdown) instead of the inline input — useful for long, multi-line, or...Alias: /compose.
/retryRetry the last message (resend to agent)Type in the Hermes CLI/TUI or a connected messaging channel.
/undoRemove the last user/assistant exchangeType in the Hermes CLI/TUI or a connected messaging channel.
/titleSet a title for the current session (usage: /title My Session Name)Type in the Hermes CLI/TUI or a connected messaging channel.
/rollbackList or restore filesystem checkpoints (usage: /rollback [number])Type in the Hermes CLI/TUI or a connected messaging channel.
/diff [staged|all|session] [--stat] [path...]Show git changes in the working directoryDefault: unstaged changes plus untracked files. staged shows what's staged for commit,
/snapshot [create|restore <id>|prune]Create or restore state snapshots of Hermes config/stateAlias: /snap. create [label] saves a snapshot,
/stopKill all running background processesType in the Hermes CLI/TUI or a connected messaging channel.
/steer <prompt>Inject a mid-run note that arrives at the agent after the next tool call — no interrupt, no new user turnThe text is appended to the last tool result's content once the current tool completes, giving the agent new context without breaking the current tool-calling loop. Use this to nudge...
/goal <text>Set a standing goal Hermes works toward across turns — our take on the Ralph loopAfter each turn an auxiliary judge model decides whether the goal is done; if not, Hermes auto-continues. Subcommands:
/subgoal <text>Append a user-supplied criterion to the active goal mid-loopThe continuation prompt surfaces all subgoals to the agent verbatim, and the judge factors them into its DONE/CONTINUE verdict — so the goal isn't marked done until the original goal and...
/heartbeat every <interval> <prompt>Set a recurring prompt that re-enters this session as a normal user turn whenever it's idle and the interval has...Alias: /hb. Subcommands:
/refine [focus]Run the background memory/skill self-improvement review now instead of waiting for the automatic post-turn triggerOptional focus text steers the review (e.g.
/moa <prompt>Run a single prompt through the default Mixture of Agents preset, then restore your current modelOne-shot — does not change your session model.
/switchClassic CLI: browse and resume previous sessions in an interactive pickerTUI: open the live session switcher for currently open TUI sessions. Use
/egress [status]Show Docker egress proxy status — enabled/configured/running state, credential source, token mappings, uncovered...Works in CLI, TUI, Desktop chat, and messaging gateway.
/redrawForce a full UI repaint (recovers from terminal drift after tmux resize, mouse selection artifacts, etc.)Type in the Hermes CLI/TUI or a connected messaging channel.
/statusShow session info — model, provider, profile, session ID, working directory, title, created/updated timestamps,...Type in the Hermes CLI/TUI or a connected messaging channel.
/context [all]Visual context-window breakdownAlias: /ctx. On the CLI/TUI: a 5×20 glyph block grid (each cell ≈ 1% of the model window) plus an estimated per-category table — system prompt, tool definitions, rules, skills index, MCP, subagen
/agentsShow active agents and running tasks across the current sessionAlias: /tasks.
/btwRun a prompt in a separate background sessionThe agent processes your prompt independently — your current session stays free for other work. Results appear as a panel when the task finishes. See CLI Background Sessions .
/branch [name]Branch the current session (explore a different path)Alias: /fork.
/worktree [new [name]|list]CLI onlyInspect or create isolated git worktrees mid-session (inspired by Copilot CLI's
/handoff <platform>CLI onlyHand the current session off to a messaging platform (Telegram, Discord, Slack, WhatsApp, Signal, Matrix). The gateway picks it up immediately, creates a fresh thread on platforms that...
/memory-graphOpen the learning journey timeline of learned skills + memoriesWorks in the classic CLI, as a TUI overlay, and in the desktop app (Star Map panel). Not available on messaging platforms. See Learning Journey .
/configShow current configurationType in the Hermes CLI/TUI or a connected messaging channel.
/model [model-name]Show or change the current modelSupports:
/codex-runtime [auto|codex_app_server|on|off]Toggle the optional Codex app-server runtime for OpenAI/Codex modelsType in the Hermes CLI/TUI or a connected messaging channel.
/personalitySet a predefined personalityType in the Hermes CLI/TUI or a connected messaging channel.
/verboseCycle tool progress display: off → new → all → verboseCan be enabled for messaging via config.

Frequently Asked Questions

How do I turn on reasoning mode in Hermes 4?

Pass thinking=True to the tokenizer chat template, or use the official deep-thinking system prompt from the model card. Reasoning arrives inside <think> </think> tags; strip them for the final answer.

How does Hermes 4 do function calling?

Tool signatures go inside <tools> </tools> tags in the system message. The model emits calls inside <tool_call> </tool_call> as JSON, and you return results inside <tool_response> </tool_response> in a tool role message.

Which prompt format does Hermes 4 405B use?

The Llama 3.1 header-token format: <|start_header_id|>role<|end_header_id|> with <|eot_id|> closing each turn. Smaller Hermes 4 models use ChatML.

Every entry on this page is a literal, typeable token taken from the official documentation linked above. Command sets in AI tools change quickly - the in-product command menu is always authoritative for your installed version.

Related prompt references

DeepSeek (22) · LM Studio (24) · Claude Code (111) · All AI prompt references