========== YENİ KOMUT | 23.09.2026 13:13:34 ==========
========== YENİ KOMUT | 23.09.2026 13:13:34 ==========
usage: hermes [-h] [--version] [-z PROMPT] [--usage-file PATH] [-m MODEL]
[--provider PROVIDER] [--reasoning LEVEL] [-t TOOLSETS]
[--resume SESSION] [--no-restore-cwd] [--in DIR]
[--continue [SESSION_NAME]] [--worktree] [--accept-hooks]
[--skills SKILLS] [--yolo] [--pass-session-id]
[--ignore-user-config] [--ignore-rules] [--safe-mode] [--tui]
[--cli] [--dev]
{chat,model,moa,fallback,worktree,browser,secrets,egress,migrate,gateway,proxy,lsp,setup,whatsapp,whatsapp-cloud,slack,send,login,logout,auth,status,pause,resume,cron,sync,webhook,peer,portal,kanban,project,hooks,doctor,verify,security,approvals,dump,debug,backup,checkpoints,import,import-agent,config,skin,console,pairing,skills,bundles,plugins,curator,pets,journey,learning,memory-graph,memory,tools,computer-use,mcp,sessions,insights,monitoring,claw,update,uninstall,acp,profile,completion,dashboard,serve,desktop,gui,logs,prompt-size}
...
Hermes Agent - AI assistant with tool-calling capabilities
positional arguments:
{chat,model,moa,fallback,worktree,browser,secrets,egress,migrate,gateway,proxy,lsp,setup,whatsapp,whatsapp-cloud,slack,send,login,logout,auth,status,pause,resume,cron,sync,webhook,peer,portal,kanban,project,hooks,doctor,verify,security,approvals,dump,debug,backup,checkpoints,import,import-agent,config,skin,console,pairing,skills,bundles,plugins,curator,pets,journey,learning,memory-graph,memory,tools,computer-use,mcp,sessions,insights,monitoring,claw,update,uninstall,acp,profile,completion,dashboard,serve,desktop,gui,logs,prompt-size}
Command to run
chat Interactive chat with the agent
model Select default model and provider
moa Configure Mixture of Agents provider/model slots
fallback Manage fallback providers (tried when the primary
model fails)
worktree Audit and reclaim accumulated git worktrees and merged
branches
browser Real-profile browsing helpers (close a browser locking
its profile)
secrets Manage external secret sources (Bitwarden, 1Password)
egress Manage the iron-proxy egress credential-injection
firewall
migrate Migrate configuration for retired models or deprecated
settings
gateway Messaging gateway management
proxy Local OpenAI-compatible proxy to OAuth providers
lsp Language Server Protocol management
setup Interactive setup wizard
whatsapp Set up WhatsApp integration
whatsapp-cloud Set up WhatsApp Business Cloud API integration
slack Slack integration helpers (manifest generation, etc.)
send Send a message to a configured platform (scripts, cron
jobs, CI).
logout Clear authentication for an inference provider
auth Manage pooled provider credentials
status Show status of all components
pause Emergency stop: pause cron/kanban dispatch and new
gateway turns
resume Lift the emergency stop set by `hermes pause`
cron Cron job management
sync Skill Sync — sync your skills across devices and with
your team
webhook Manage dynamic webhook subscriptions
peer Bot-to-bot DMs across machines (peer Hermes gateways)
portal Set up Nous Portal (login, model pick, Tool Gateway);
see also `portal info`
kanban Multi-profile collaboration board (tasks, links,
comments)
project Manage projects (named, multi-folder workspaces)
hooks Inspect and manage shell-script hooks
doctor Check configuration and dependencies
verify Detect a project's run recipe and smoke-test it
security Supply-chain audit (OSV.dev) for venv, plugins, and
MCP servers
approvals Approval-prompt tools (mine history into allowlist
proposals)
dump Dump setup summary for support/debugging
debug Debug tools — upload logs and system info for support
backup Back up Hermes home directory to a zip file
checkpoints Inspect / prune / clear ~/.hermes/checkpoints/
import Restore a Hermes backup from a zip file
import-agent Import a Claude Code or Codex CLI setup into Hermes
config View and edit configuration
skin List, switch, and tweak skins
console Open the safe Hermes command console
pairing Manage DM pairing codes for user authorization
skills Search, install, configure, and manage skills
bundles Create, list, and manage skill bundles (aliases for
multiple skills)
plugins Manage and validate plugins
curator Background skill maintenance (curator) — status, run,
pause, pin
pets Browse, install, and select petdex animated pets
journey (learning, memory-graph)
Timeline of learned skills + memories over time
memory Configure external memory provider
tools Configure which tools are enabled per platform
computer-use Manage the Computer Use (cua-driver) backend
(macOS/Windows/Linux)
mcp Manage MCP servers and run Hermes as an MCP server
sessions Manage session history (list, rename, export, prune,
delete)
insights Show usage insights and analytics
monitoring Inspect gateway monitoring (health & diagnostics
export)
claw OpenClaw migration tools
update Update Hermes Agent to the latest version
uninstall Uninstall Hermes Agent
acp Run Hermes Agent as an ACP (Agent Client Protocol)
server
profile Manage profiles — multiple isolated Hermes instances
completion Print shell completion script (bash, zsh, or fish)
dashboard Start the web UI dashboard
serve Start the Hermes backend server (headless; powers the
desktop app and remote backends)
desktop (gui) Build and launch the native desktop app
logs View and filter Hermes log files
prompt-size Show a byte breakdown of the system prompt + tool
schemas
options:
-h, --help show this help message and exit
--version, -V Show version and exit
-z PROMPT, --oneshot PROMPT
One-shot mode: send a single prompt and print ONLY the
final response text to stdout. No banner, no spinner,
no tool previews, no session_id line. Tools, memory,
rules, and AGENTS.md in the CWD are loaded as normal;
approvals are auto-bypassed. Intended for scripts /
pipes.
--usage-file PATH One-shot mode only: after the run, write a JSON usage
report (estimated cost, token counts, model,
api_calls) to PATH. The report is written even when
the run fails, so pipelines can always account for
spend. No effect outside -z/--oneshot.
-m MODEL, --model MODEL
Model override for this invocation (e.g.
anthropic/claude-sonnet-4.6). Applies to -z/--oneshot
and --tui. Also settable via HERMES_INFERENCE_MODEL
env var.
--provider PROVIDER Provider override for this invocation (e.g.
openrouter, anthropic). Applies to -z/--oneshot and
--tui. The persistent provider lives in config.yaml
under model.provider — use `hermes setup` or edit the
file to change it.
--reasoning LEVEL Reasoning effort for this invocation: none, minimal,
low, medium, high, xhigh, max, or ultra. Overrides
agent.reasoning_effort in config.yaml for this run
only; the persistent level lives there (or per-model
under agent.reasoning_overrides).
-t TOOLSETS, --toolsets TOOLSETS
Comma-separated toolsets to enable for this
invocation. Applies to -z/--oneshot and --tui.
--resume SESSION, -r SESSION
Resume a previous session by ID or title, or pass
root@213-238-170-219:/home/hermes#