{"output": "usage: hermes [-h] [--version] [-z PROMPT] [-m MODEL] [--provider PROVIDER]\n [-t TOOLSETS] [--resume SESSION] [--continue [SESSION_NAME]]\n [--worktree] [--accept-hooks] [--skills SKILLS] [--yolo]\n [--pass-session-id] [--ignore-user-config] [--ignore-rules]\n [--safe-mode] [--tui] [--cli] [--dev]\n {chat,model,fallback,secrets,migrate,gateway,proxy,lsp,setup,postinstall,whatsapp,whatsapp-cloud,slack,send,login,logout,auth,status,cron,webhook,portal,kanban,hooks,doctor,security,dump,debug,backup,checkpoints,import,config,pairing,skills,bundles,plugins,curator,memory,tools,computer-use,mcp,sessions,insights,claw,version,update,uninstall,acp,profile,completion,dashboard,desktop,gui,logs,prompt-size}\n ...\n\nHermes Agent - AI assistant with tool-calling capabilities\n\npositional arguments:\n {chat,model,fallback,secrets,migrate,gateway,proxy,lsp,setup,postinstall,whatsapp,whatsapp-cloud,slack,send,login,logout,auth,status,cron,webhook,portal,kanban,hooks,doctor,security,dump,debug,backup,checkpoints,import,config,pairing,skills,bundles,plugins,curator,memory,tools,computer-use,mcp,sessions,insights,claw,version,update,uninstall,acp,profile,completion,dashboard,desktop,gui,logs,prompt-size}\n Command to run\n chat Interactive chat with the agent\n model Select default model and provider\n fallback Manage fallback providers (tried when the primary\n model fails)\n secrets Manage external secret sources (Bitwarden Secrets\n Manager)\n migrate Migrate configuration for retired models or deprecated\n settings\n gateway Messaging gateway management\n proxy Local OpenAI-compatible proxy to OAuth providers\n lsp Language Server Protocol management\n setup Interactive setup wizard\n postinstall Bootstrap non-Python deps for pip installs (node,\n browser, ripgrep, ffmpeg)\n whatsapp Set up WhatsApp integration\n whatsapp-cloud Set up WhatsApp Business Cloud API integration\n slack Slack integration helpers (manifest generation, etc.)\n send Send a message to a configured platform (scripts, cron\n jobs, CI).\n login Authenticate with an inference provider\n logout Clear authentication for an inference provider\n auth Manage pooled provider credentials\n status Show status of all components\n cron Cron job management\n webhook Manage dynamic webhook subscriptions\n portal Set up Nous Portal (login, model pick, Tool Gateway);\n see also
portal info\n kanban Multi-profile collaboration board (tasks, links,\n comments)\n hooks Inspect and manage shell-script hooks\n doctor Check configuration and dependencies\n security Supply-chain audit (OSV.dev) for venv, plugins, and\n MCP servers\n dump Dump setup summary for support/debugging\n debug Debug tools โ upload logs and system info for support\n backup Back up Hermes home directory to a zip file\n checkpoints Inspect / prune / clear ~/.hermes/checkpoints/\n import Restore a Hermes backup from a zip file\n config View and edit configuration\n pairing Manage DM pairing codes for user authorization\n skills Search, install, configure, and manage skills\n bundles Create, list, and manage skill bundles (aliases for\n multiple skills)\n plugins Manage plugins โ install, update, remove, list\n curator Background skill maintenance (curator) โ status, run,\n pause, pin\n memory Configure external memory provider\n tools Configure which tools are enabled per platform\n computer-use Manage the Computer Use (cua-driver) backend (macOS)\n mcp Manage MCP servers and run Hermes as an MCP server\n sessions Manage session history (list, rename, export, prune,\n delete)\n insights Show usage insights and analytics\n claw OpenClaw migration tools\n version Show version information\n update Update Hermes Agent to the latest version\n uninstall Uninstall Hermes Agent\n acp Run Hermes Agent as an ACP (Agent Client Protocol)\n server\n profile Manage profiles โ multiple isolated Hermes instances\n completion Print shell completion script (bash, zsh, or fish)\n dashboard Start the web UI dashboard\n desktop (gui) Build and launch the native desktop app\n logs View and filter Hermes log files\n prompt-size Show a byte breakdown of the system prompt + tool\n schemas\n\noptions:\n -h, --help show this help message and exit\n --version, -V Show version and exit\n -z PROMPT, --oneshot PROMPT\n One-shot mode: send a single prompt and print ONLY the\n final response text to stdout. No banner, no spinner,\n no tool previews, no session_id line. Tools, memory,\n rules, and AGENTS.md in the CWD are loaded as normal;\n approvals are auto-bypassed. Intended for scripts /\n pipes.\n -m MODEL, --model MODEL\n Model override for this invocation (e.g.\n anthropic/claude-sonnet-4.6). Applies to -z/--oneshot\n and --tui. Also settable via HERMES_INFERENCE_MODEL\n env var.\n --provider PROVIDER Provider override for this invocation (e.g.\n openrouter, anthropic). Applies to -z/--oneshot and\n --tui. The persistent provider lives in config.yaml\n under model.provider โ use
hermes setup or edit the\n file to change it.\n -t TOOLSETS, --toolsets TOOLSETS\n Comma-separated toolsets to enable for this\n invocation. Applies to -z/--oneshot and --tui.\n --resume SESSION, -r SESSION\n Resume a previous session by ID or title\n --continue [SESSION_NAME], -c [SESSION_NAME]\n Resume a session by name, or the most recent if no\n name given\n --worktree, -w Run in an isolated git worktree (for parallel agents)\n --accept-hooks Auto-approve any unseen shell hooks declared in\n config.yaml without a TTY prompt. Equivalent to\n HERMES_ACCEPT_HOOKS=1 or hooks_auto_accept: true in\n config.yaml. Use on CI / headless runs that can't\n prompt.\n --skills SKILLS, -s SKILLS\n Preload one or more skills for the session (repeat\n flag or comma-separate)\n --yolo Bypass all dangerous command approval prompts (use at\n your own risk)\n --pass-session-id Include the session ID in the agent's system prompt\n --ignore-user-config Ignore ~/.hermes/config.yaml and fall back to built-in\n defaults (credentials in .env are still loaded)\n --ignore-rules Skip auto-injection of AGENTS.md, SOUL.md,\n .cursorrules, memory, and preloaded skills\n --safe-mode Troubleshooting mode: disable ALL customizations โ\n user config, AGENTS.md/memory injection, plugins, and\n MCP servers (implies --ignore-user-config and\n --ignore-rules)\n --tui Launch the modern TUI instead of the classic REPL\n --cli Force the classic prompt_toolkit REPL (overrides\n display.interface=tui)\n --dev With --tui: run TypeScript sources via tsx (skip dist\n build)\n\nExamples:\n hermes Start interactive chat\n hermes chat -q \"Hello\" Single query mode\n hermes --tui Launch the modern TUI (or set display.interface: tui)\n hermes --cli Force the classic REPL (overrides display.interface: tui)\n hermes -c Resume the most recent session\n hermes -c \"my project\" Resume a session by name (latest in lineage)\n hermes --resume
Resume a specific session by ID\n hermes setup Run setup wizard\n hermes logout Clear stored authentication\n hermes auth add Add a pooled credential\n hermes auth list List pooled credentials\n hermes auth remove Remove pooled credential by index, id, or label\n hermes auth reset Clear exhaustion status for a provider\n hermes model Select default model\n hermes fallback [list] Show fallback provider chain\n hermes fallback add Add a fallback provider (same picker as hermes model)\n hermes fallback remove Remove a fallback provider from the chain\n hermes config View configuration\n hermes config edit Edit config in $EDITOR\n hermes config set model gpt-4 Set a config value\n hermes gateway Run messaging gateway\n hermes -s hermes-agent-dev,github-auth\n hermes -w Start in isolated git worktree\n hermes gateway install Install gateway background service\n hermes sessions list List past sessions\n hermes sessions browse Interactive session picker\n hermes sessions rename ID T Rename/title a session\n hermes logs View agent.log (last 50 lines)\n hermes logs -f Follow agent.log in real time\n hermes logs errors View errors.log\n hermes logs --since 1h Lines from the last hour\n hermes debug share Upload debug report for support\n hermes update Update to latest version\n hermes dashboard Start web UI dashboard (port 9119)\n hermes dashboard --stop Stop running dashboard processes\n hermes dashboard --status List running dashboard processes\n\nFor more help on a command:\n hermes --help", "exit_code": 0, "error": null}