Меню
/help - Show available commands
/new - Start a new session (fresh session ID + history)
/stop - Kill all running background processes
/status - Show session, model, token, and context info
/resume - Resume a previously-named session
/sessions - Browse and resume previous sessions
/model - Switch model (persists by default)
/debug - Upload debug report (system info + logs) and get shareable links
/restart - Gracefully restart the gateway after draining active runs
/update - Update Hermes Agent to the latest version
/commands - Browse all commands and skills (paginated)
/approve - Approve a pending dangerous command
/deny - Deny a pending dangerous command (optionally with a reason)
/queue - Queue a prompt for the next turn (doesn't interrupt)
/steer - Inject a message after the next tool call without interrupting
/background - Run a prompt in the background
/reasoning - Manage reasoning effort and display
/usage - Show token usage and rate limits for the current session
/platform - Pause, resume, or list a failing gateway platform
/profile - Show active profile name and home directory
/whoami - Show your slash command access (admin / user)
/start - Acknowledge platform start pings without a reply
/topic - Enable or inspect Telegram DM topic sessions
/retry - Retry the last message (resend to agent)
/undo - Back up N user turns and re-prompt (default 1)
/title - Set a title for the current session
/branch - Branch the current session (explore a different path)
/compress - Compress conversation context (add 'here [N]' to keep recent N turns; --preview shows what would happen)
/rollback - List or restore filesystem checkpoints
/agents - Show active agents and running tasks
/goal - Set a standing goal Hermes works on across turns until achieved
/moa - Run one prompt through the default Mixture of Agents preset, then restore your model
/subgoal - Add or manage extra criteria on the active goal
/sethome - Set this chat as the home channel
/codex_runtime - Toggle codex app-server runtime for OpenAI/Codex models
/personality - Set a predefined personality
/footer - Toggle gateway runtime-metadata footer on final replies
/yolo - Toggle YOLO mode (skip all dangerous command approvals)
/fast - Toggle fast mode — OpenAI Priority Processing / Anthropic Fast Mode (Normal/Fast)
/voice - Toggle voice mode
/memory - Review pending memory writes / toggle the approval gate
/bundles - List skill bundles (aliases /<name> for multiple skills)
/learn - Learn a reusable skill from anything you describe (dirs, URLs, this chat, notes)
/suggestions - Review suggested automations (accept/dismiss)
/blueprint - Set up an automation from a blueprint template
/curator - Background skill maintenance (status, run, pin, archive, list-archived)
/kanban - Multi-profile collaboration board (tasks, links, comments)
/reload_mcp - Reload MCP servers from config
/reload_skills - Re-scan ~/.hermes/skills/ for newly installed or removed skills
/credits - Show Nous credit balance and top up
/insights - Show usage insights and analytics
/version - Show Hermes Agent version
/airtable - Airtable REST API via curl. Records C...
/architecture_diagram - Dark-themed SVG architecture/cloud/in...
/arxiv - Search arXiv papers by keyword, autho...
/ascii_art - ASCII art: pyfiglet, cowsay, boxes, i...
/ascii_video - ASCII video: convert video/audio to c...
/atol2aif - Develop and debug the atol2aif Prolog...
/atol2aif_dev - Develop and debug the atol2aif Prolog...
/audiocraft_audio_generation - AudioCraft: MusicGen text-to-music, A...