OpenClaw keyboard shortcuts

This page lists commands of OpenClaw 2026.9.8, the self-hosted gateway that connects chat apps to AI agents, as its documentation prints them: the terminal CLI for setup, the Gateway, channels, models, skills and updates, the slash commands typed in a chat, and the terminal UI keys. Rows are worked examples; rarer groups such as fleet, wiki and secrets are left out. Anything starting with openclaw runs in a shell on the Gateway host. Capitals mark values you replace.

341 shortcuts in 21 sections. Checked row by row against OpenClaw docs, release v2026.9.8 on . Edited by Jay.

Setup and onboarding 22

ActionShortcut
Try OpenClaw without installingOn a fresh machine it runs onboarding and keeps the Gateway in that terminal until you press Ctrl+C.npx openclaw@latest
Install on macOS or LinuxThe install script starts the guided onboarding wizard when it finishes.curl -fsSL https://openclaw.ai/install.sh | bash
Install from Windows PowerShellPowerShell form of the same installer for native Windows.iwr -useb https://openclaw.ai/install.ps1 | iex
Start OpenClawWith no subcommand it runs onboarding on a new install, otherwise opens the TUI on the Gateway or a local model.openclaw
Run guided onboardingDetects existing AI access, verifies the provider you pick, then sets up Gateway, workspace, channels and skills.openclaw onboard
Open the classic wizardFull step-by-step wizard; it cannot be combined with --non-interactive.openclaw onboard --classic
Onboard with minimal promptsClassic wizard that generates a Gateway secret instead of asking for a token or password.openclaw onboard --flow quickstart
Onboard with full promptsManual setup asks for port, bind mode and secret storage; advanced is an alias.openclaw onboard --flow manual
Onboard by importingRuns a detected migration provider, such as Hermes, against a fresh setup.openclaw onboard --flow import
Onboard without promptsFor scripted setup; --accept-risk is mandatory here and --mode defaults to local.openclaw onboard --non-interactive --accept-risk
Point setup at a remote GatewayPrefills the remote Gateway step; add --remote-token or --remote-password, never both.openclaw onboard --mode remote --remote-url wss://gateway-host:18789
Reset before onboardingDestructive: without --reset-scope it removes config, credentials and sessions; the full scope also resets the workspace.openclaw onboard --reset
Open the setup assistantOn a configured system it opens the system-agent chat; on a fresh one it falls through to onboarding.openclaw setup
Send one setup requestRuns a single request and exits; add --yes to approve a persistent config write.openclaw setup -m "status"
Create baseline config onlyWrites the config, workspace and session folders without walking through onboarding.openclaw setup --baseline
Change an existing setupInteractive prompts for model auth, gateway, channels, plugins or skills; needs a real terminal.openclaw configure
Configure selected sectionsThe filter is repeatable; sections are workspace, model, web, gateway, daemon, channels, plugins, skills and health.openclaw configure --section model --section channels
Open the Control UIOpens the browser with a short-lived, one-time owner pairing link.openclaw dashboard
Print the dashboard URLPrints the link and leaves the browser closed.openclaw dashboard --no-open
Install shell completionCaches the scripts, then adds a source line to your shell profile.openclaw completion --write-state --install
Print a completion scriptThe shell can be zsh, bash, powershell or fish; without the flag it is detected from $SHELL.openclaw completion --shell fish
Search the docs from the terminalSearches the live documentation index; --limit caps the number of results.openclaw docs QUERY

Running the Gateway 13

ActionShortcut
Run the GatewayRuns in the foreground and refuses to start unless gateway.mode=local is set in the config.openclaw gateway
Run the Gateway, explicit formSame as openclaw gateway, spelled with its subcommand.openclaw gateway run
Set the Gateway portOption of openclaw gateway; the WebSocket port usually defaults to 18789.--port PORT
Choose the bind modeOption of openclaw gateway: loopback (default), lan, tailnet, auto or custom.--bind MODE
Start without gateway.mode=localFor ad-hoc or dev runs; it bypasses the guard and neither writes nor repairs config.--allow-unconfigured
Free the port firstStops whatever is listening on that port before startup; refused for a verified Gateway when the shell is non-interactive.--force
Install the Gateway serviceCreates a LaunchAgent on macOS, a systemd user unit on Linux and WSL2, or a Scheduled Task on Windows.openclaw gateway install
Start the Gateway serviceReports still-starting with exit code 2 if the managed Gateway has not become ready by the deadline.openclaw gateway start
Stop the Gateway serviceStill works when plugin configuration needs a Doctor migration.openclaw gateway stop
Restart the Gateway serviceThe docs prefer this over sending signals by hand.openclaw gateway restart
Remove the Gateway serviceopenclaw gateway uninstall
Reveal the Gateway tokenPrints only the shared token and insists on an interactive terminal, so it cannot be piped or redirected.openclaw gateway auth-token --show
Find Gateways on the networkBrowses Bonjour for advertised Gateways; only those with discovery enabled show up.openclaw gateway discover

Gateway status, health and logs 23

ActionShortcut
Show Gateway service statusReports the launchd, systemd or schtasks service plus a connectivity and auth probe.openclaw gateway status
Gateway status with deep scanAlso scans system-level services for other Gateway installs.openclaw gateway status --deep
Require a healthy RPC probeFor scripts where a listening service is not enough and read-scope RPC must answer too.openclaw gateway status --require-rpc
Check Gateway healthAsks a local loopback Gateway on that port; --url targets an explicit WebSocket address instead.openclaw gateway health --port 18789
Probe every reachable GatewayChecks the configured remote and localhost even when a remote is set; the docs call it the debug-everything command.openclaw gateway probe
Probe through an SSH tunnelCLI counterpart of the macOS app's Remote over SSH mode, for a loopback-only remote Gateway.openclaw gateway probe --ssh user@gateway-host
Summarise usage costReads usage-cost summaries from session logs for the given number of days.openclaw gateway usage-cost --days 7
Call a Gateway RPC methodLow-level helper: the argument is the method name and --params passes a JSON object.openclaw gateway call status
Export a diagnostics bundleWrites a local zip meant for bug reports; --output names the file.openclaw gateway diagnostics export
Show overall statusDiagnostics for channels and sessions in one report.openclaw status
Full pasteable diagnosisRead-only; adds the security audit, plugin compatibility and memory-vector probes.openclaw status --all
Status with live channel probesRequests channel health with live probes where supported and switches on the security audit.openclaw status --deep
Show provider usage windowsPrints each provider's normalized usage window as a percentage left.openclaw status --usage
Status as JSONCommand options such as this one go behind the command name; global ones may come in front of it.openclaw status --json
Fetch a Gateway health snapshotAsks the running Gateway over WebSocket RPC; it may answer from a snapshot cached for up to 60 seconds.openclaw health
Force a live health probeProbes every channel account live and expands output to all configured accounts and agents; --debug is an alias.openclaw health --verbose
Tail Gateway logsReads the Gateway file log over RPC, so it also works against a remote Gateway.openclaw logs
Follow the log streamKeeps polling for new lines; --interval sets the polling period, 1000 ms by default.openclaw logs --follow
Cap lines and bytesDefaults are 200 lines and 250000 bytes read from the log file.openclaw logs --limit 500 --max-bytes 500000
Logs as JSON eventsEmits one JSON event per line.openclaw logs --json
Logs without stylingopenclaw logs --plain
Show log times in UTCTimestamps are rendered in your local timezone unless this flag is given.openclaw logs --utc
Follow logs of a named profileShows a global option placed in front of the command.openclaw --profile work logs --follow

Messages and agent runs 14

ActionShortcut
Send a messageNeeds --target plus one of --message, --media or --presentation; --channel is required once several channels are configured.openclaw message send --channel discord --target channel:123 --message "hi"
Send a file--media takes a local path or URL and can be repeated; --force-document avoids channel compression.openclaw message send --channel telegram --target @mychat --media ./diagram.png --force-document
Create a pollRepeat --poll-option for each choice; polls work on Discord, Matrix, Microsoft Teams, Telegram and WhatsApp.openclaw message poll --channel discord --target channel:123 --poll-question "Snack?" --poll-option Pizza --poll-option Sushi
Send to several targets--targets takes a space-separated list and --channel all reaches every configured provider.openclaw message broadcast --targets TARGET --message TEXT
Run another message actionOther actions include react, read, edit, delete, pin, search and thread create, each with its own required flags.openclaw message SUBCOMMAND
Run one agent turnGoes through the Gateway; pass at least one of --to, --session-key, --session-id or --agent.openclaw agent --agent ops --message "Summarize logs"
Run a turn and deliver the reply--to derives the session from a recipient and --deliver sends the answer back to that channel.openclaw agent --to +15555550123 --message "status update" --deliver
Read the prompt from a fileUse exactly one of --message or --message-file; files over 4 MiB or not valid UTF-8 are rejected.openclaw agent --agent ops --message-file ./task.md
Override the model for one runAccepts provider/model or a bare model id, for this run only.openclaw agent --agent ops --model openai/gpt-5.4 --message "Summarize logs"
Set the thinking level for a turnLevels are off, minimal, low, medium and high, plus any the provider adds such as xhigh or max.openclaw agent --session-id 1234 --message "Summarize inbox" --thinking medium
Run the embedded agentSkips the Gateway and needs exclusive use of the state directory, so stop a running Gateway first.openclaw agent --agent ops --message "Run locally" --local
Deliver the reply elsewhereThe two reply options override the delivery channel and target without changing session routing.openclaw agent --agent ops --message "Generate report" --deliver --reply-channel slack --reply-to "#reports"
Run a headless agent turnOne embedded turn with no Gateway connection; the docs recommend it for CI and coding automation.openclaw agent exec "Run the focused tests and fix failures"
Headless run in a directory--cwd becomes the agent workspace as well as the directory tools run in.openclaw agent exec --message-file task.md --cwd ./repo

Agents, sessions and memory 20

ActionShortcut
List configured agentsSame output as the list subcommand; an agent is an isolated workspace with its own auth and routing.openclaw agents
List agents with routing rulesPrints the full routing rules instead of per-agent counts.openclaw agents list --bindings
Add an isolated agent--bind attaches a channel account at creation and can be repeated.openclaw agents add work --workspace ~/.openclaw/workspace-work
Show routing bindingsAdd --agent to see the bindings of a single agent.openclaw agents bindings
Route a channel account to an agentThe binding is written channel:account; repeat --bind to add several at once.openclaw agents bind --agent work --bind telegram:ops
Remove a routing bindingopenclaw agents unbind --agent work --bind telegram:ops
Delete an agentopenclaw agents delete work
List stored sessionsShows persisted conversation rows, not channel liveness; openclaw sessions list is the explicit spelling.openclaw sessions
List recently active sessionsThe number is minutes since the session was last updated.openclaw sessions --active 120
List sessions of every agentAggregates all configured agent stores; --agent picks just one.openclaw sessions --all-agents
Archive a sessionGoes through the running Gateway; several keys can be given and --dry-run previews.openclaw sessions archive "agent:main:scratch-1"
Delete a sessionNeeds a running Gateway; list several keys to remove them together.openclaw sessions delete "agent:main:scratch-1"
Preview session maintenanceMaintenance otherwise waits for the next write cycle; --enforce applies it even when the configured mode is warn.openclaw sessions cleanup --dry-run
Follow session progressRenders trajectory events as compact progress lines, starting with running sessions.openclaw sessions tail --follow
Compact a stored sessionFrees context budget when a session is stuck or too large; needs a running Gateway.openclaw sessions compact "agent:main:main"
Resume a recent sessionWith no query it lists up to 50 sessions active in the last seven days and opens your pick in the TUI.openclaw resume
Resume a session by nameAn exact session key wins; otherwise the query must match one session uniquely.openclaw resume bugfix
Check memory readiness--deep probes the vector store, embedding provider and semantic search, which costs extra provider calls.openclaw memory status --deep --agent ID
Rebuild the memory index--force does a full reindex rather than an incremental one.openclaw memory index --force --agent ID
Search agent memoryThe query can also be passed with --query, which wins if both are given.openclaw memory search QUERY

Channels and pairing 18

ActionShortcut
List channel accountsShows configured accounts with installed, configured and enabled tags; --all adds channels with no account yet.openclaw channels list
Show channel runtime statusFalls back to config-only summaries when the Gateway is unreachable.openclaw channels status
Probe channels liveRuns per-account probe and audit checks on a reachable Gateway; --deep is not supported here.openclaw channels status --probe
Check channel permissionsShows what the bot is allowed to do in that specific target.openclaw channels capabilities --channel discord --target channel:123
Resolve names to IDs--kind narrows the lookup to user, group or channel; the default is auto.openclaw channels resolve --channel slack "#general" "@jane"
Show channel logsPrints the last 200 lines by default; --lines changes the count.openclaw channels logs --channel all
Add a channel accountRun bare, it opens guided setup, which requires an interactive terminal.openclaw channels add
Start guided setup for one channelA positional channel id or --channel opens that channel's guided setup directly.openclaw channels add telegram
Add a channel with a tokenFlag-driven path for scripts; credential flags belong to each channel plugin.openclaw channels add --channel telegram --token BOT-TOKEN
Add a channel from environmentChecks the variables the channel plugin declares, TELEGRAM_BOT_TOKEN for Telegram, before writing config.openclaw channels add --channel telegram --use-env
List a channel's setup flagsHelp for one channel prints its own flags rather than the shared envelope.openclaw channels add --channel telegram --help
Remove a channel accountWithout --delete it only offers to disable the account and keeps its config.openclaw channels remove --channel telegram --delete
Log in to a channelInteractive; run it in a terminal on the Gateway host.openclaw channels login --channel whatsapp
Log out of a channelUses the live Gateway when reachable so the listener stops before auth state is cleared.openclaw channels logout --channel whatsapp
List inbound dead lettersEvents that ran out of retries, with failure reasons and attempt counts; resubmit re-enqueues one by event id.openclaw channels dead-letters list --channel telegram --account default
List pending DM pairing requestsChat DMs only; device and node pairing use openclaw devices.openclaw pairing list telegram
Approve a pairing codeThe channel can be left out when only one pairing-capable channel is configured.openclaw pairing approve telegram CODE
Approve and notify the sender--notify sends a confirmation back on the same channel; --account limits it to one account.openclaw pairing approve --channel telegram --account work CODE --notify

Devices and nodes 14

ActionShortcut
Show a mobile pairing QRGenerates the QR and setup code from the current Gateway configuration.openclaw qr
Print only the setup codeSkips the QR drawing; if --json is also given, JSON output wins.openclaw qr --setup-code-only
Pair without admin accessLeaves operator.admin out of the operator token handed to the phone.openclaw qr --limited
List devices and requestsShows pending pairing requests together with paired devices.openclaw devices list
Approve a device requestNeeds the exact request ID; without one, or with --latest, it only previews the newest request.openclaw devices approve REQUESTID
Reject a device requestopenclaw devices reject REQUESTID
Remove a paired deviceopenclaw devices remove DEVICEID
Rotate a device tokenIssues a new token for that role; --scope can update its scopes at the same time.openclaw devices rotate --device DEVICEID --role operator
Revoke a device tokenopenclaw devices revoke --device DEVICEID --role node
Show node status--connected limits it to connected nodes and --last-connected to a time window such as 24h.openclaw nodes status
List paired nodesopenclaw nodes list
List pending node requestsopenclaw nodes pending
Approve a nodeopenclaw nodes approve REQUESTID
Send a notification to a nodeopenclaw nodes notify --node ID --title "Build" --body "Done"

Models and inference 19

ActionShortcut
Show model statusBare form of the status subcommand: the resolved default, fallbacks and an auth overview.openclaw models
Model status for one agentUse it when diagnosing a particular agent's model selection.openclaw models status --agent AGENTID
List published modelsAnswers from the published inventory, so it does not wait for provider discovery.openclaw models list
Set the default modelWrites agents.defaults.model.primary; accepts provider/model or a configured alias.openclaw models set MODEL-OR-ALIAS
Set the image modelStores the choice in agents.defaults.imageModel.primary.openclaw models set-image MODEL-OR-ALIAS
Scan free OpenRouter modelsRanks candidates from OpenRouter's public :free catalog for fallback use; live probes need OPENROUTER_API_KEY.openclaw models scan
Refresh the hosted catalogChecks the hosted metadata catalog; restart the Gateway to use what it downloads.openclaw models refresh
List model aliasesopenclaw models aliases list
Add a model aliasAliasing an existing alias repoints it to the same model instead of chaining.openclaw models aliases add ALIAS MODEL-OR-ALIAS
List fallback modelsopenclaw models fallbacks list
Add a fallback modelAppends to agents.defaults.model.fallbacks, the global fallback list.openclaw models fallbacks add MODEL-OR-ALIAS
Clear fallback modelsopenclaw models fallbacks clear
Add model credentialsInteractive helper that starts a provider auth flow or guides a manual token paste.openclaw models auth add
Sign in to a providerRuns the provider plugin's OAuth or API-key flow for system or agent credentials.openclaw models auth login --provider ID
List auth profilesNever prints token, API-key or OAuth secret material.openclaw models auth list
Paste an API keyopenclaw models auth paste-api-key --provider openai
Connect a personal model accountStores the credential in your own profile on the selected Gateway, which may be remote.openclaw models accounts login
Run a one-off model promptHeadless inference that reuses the providers and models already configured.openclaw infer model run --prompt "Reply with exactly: smoke-ok" --json
Generate an imageOther capability families are audio, tts, video, web and embedding.openclaw infer image generate --prompt "friendly lobster illustration" --json

Configuration 9

ActionShortcut
Open the config wizardWithout a subcommand it starts the guided wizard that openclaw configure also runs.openclaw config
Print the config file pathResolved from OPENCLAW_CONFIG_PATH or the default location.openclaw config file
Read a config valueReads from a redacted snapshot, so secrets never print; --json keeps the value's type.openclaw config get agents.defaults.workspace
Set a config valueA value is read as JSON5 if it parses and kept as a plain string if not.openclaw config set agents.defaults.heartbeat.every "2h"
Set a value as strict JSONRequires standard JSON with no fallback to a string.openclaw config set gateway.port 19001 --strict-json
Remove a config valueopenclaw config unset plugins.entries.brave.config.webSearch.apiKey
Apply a JSON5 patchObjects merge recursively, arrays and scalars replace the target, and null deletes the path.openclaw config patch --file ./openclaw.patch.json5 --dry-run
Print the config JSON schemaGoes to stdout, so it can be redirected into a file for editor tooling.openclaw config schema
Validate the configSchema check that does not start the Gateway; add --json for structured errors.openclaw config validate

Skills 12

ActionShortcut
Skills command groupThe bare form queries the selected Gateway's skill inventory, as list, info and check do.openclaw skills
List skillsAsks the selected Gateway for its inventory; --eligible, --json, --verbose and --agent variants are documented.openclaw skills list
List eligible skillsopenclaw skills list --eligible
Search ClawHub for skillsQueries ClawHub directly; --limit sets how many results come back.openclaw skills search "calendar"
Install a ClawHub skillInstalls a native ClawHub skill into the active workspace skills directory, or the shared one with --global.openclaw skills install @owner/SLUG
Install a skill from GitClones an unmanaged Git skill; a ref can follow, as in git:owner/repo@main.openclaw skills install git:owner/repo
Install a local skillCopies a local directory that has SKILL.md at its root.openclaw skills install ./path/to/skill --as custom-name
Update all ClawHub skillsTargets the active workspace skills directory, or the shared one with --global.openclaw skills update --all
Show one skillResolves an exact skill name first and fails on an ambiguous selector.openclaw skills info NAME
Check skill requirementsLists missing prerequisites, even for skills the agent allowlist excludes.openclaw skills check
List skill proposalsopenclaw skills workshop list
Remove a ClawHub skillRemoval is done with the standalone ClawHub CLI, installed with npm i -g clawhub.clawhub uninstall @owner/my-skill

Plugins and hooks 19

ActionShortcut
List pluginsShows each plugin's format, openclaw or bundle; --enabled and --verbose refine the view.openclaw plugins list
Search ClawHub pluginsopenclaw plugins search "calendar"
Install a pluginA bare name installs from npm by default; an arbitrary npm source warns and asks before continuing.openclaw plugins install PACKAGE
Install from ClawHub onlyThe clawhub: prefix skips npm; the npm: prefix does the reverse.openclaw plugins install clawhub:openclaw-codex-app-server
Link a local pluginLinks the directory instead of copying it; the path must be on the Gateway host.openclaw plugins install -l PATH
Install and pin the versionApplies to npm sources: the resolved version is pinned.openclaw plugins install PACKAGE --pin
Install without enablingRecords the plugin but leaves plugins.allow, plugins.deny and its enabled state alone.openclaw plugins install PACKAGE --no-enable
Enable pluginsTakes one or more plugin ids in a single call.openclaw plugins enable codex cua-computer
Disable pluginsDisabling does not uninstall: the plugin's channels stay listed as installed.openclaw plugins disable IDS
Inspect a plugin--all covers every plugin, and info is an alias of inspect.openclaw plugins inspect ID
Update all plugins--dry-run previews the update first.openclaw plugins update --all
Uninstall pluginsopenclaw plugins uninstall IDS
Diagnose plugin problemsopenclaw plugins doctor
List a marketplace's pluginsopenclaw plugins marketplace list SOURCE
List internal hooksEquivalent to the list subcommand; hooks are handlers for command, message, session and Gateway events.openclaw hooks
List loadable hooksOnly hooks that are enabled, have their requirements met and declare at least one event.openclaw hooks list --eligible
Check hook eligibilityopenclaw hooks check
Enable a hookopenclaw hooks enable NAME
Disable a hookopenclaw hooks disable NAME

Editor and MCP bridges 7

ActionShortcut
Run the ACP bridgeAn IDE connects to it over stdio and its prompts are forwarded to a Gateway session.openclaw acp
Attach ACP to a session key--session-label picks an existing session by label instead.openclaw acp --session agent:main:main
Test the ACP bridgeBuilt-in debug client that spawns the bridge and lets you type prompts without an IDE.openclaw acp client
Launch Claude Code on a sessionClaude Code gets a temporary MCP grant scoped to a single Gateway session, the main one by default.openclaw attach
Print the attach configurationWrites the temporary .mcp.json and prints the launch command without starting Claude Code.openclaw attach --print-config
Serve channels over MCPLets an external MCP client read and send channel conversations through the Gateway.openclaw mcp serve
Show saved MCP serversShows what is saved without starting any MCP server; the docs suggest it as the starting point.openclaw mcp status --verbose

Automation and system events 13

The scheduler command registers as openclaw cron with openclaw automations as an alias; every subcommand works with either spelling, and the documentation writes its examples with automations.

ActionShortcut
Manage scheduled jobsRegistered name of the scheduler command; the docs write its alias, openclaw automations, in every example.openclaw cron
Create a scheduled jobSchedule first, prompt second; create is an alias of add.openclaw automations create "0 7 * * *" "Summarize overnight updates." --name "Morning brief" --agent ops
List automation jobs--agent narrows the list to one agent's jobs.openclaw automations list
Show one jobopenclaw automations get JOB-ID
Run a job nowForce-runs and returns once the Gateway has accepted the run; --wait blocks until it reaches a final status.openclaw automations run JOB-ID
Show a job's run historyopenclaw automations runs JOB-ID --limit 50
Turn off delivery for a jobFor an isolated job; --announce with --channel and --to sets a delivery target instead.openclaw automations edit JOB-ID --no-deliver
Resume a job's scheduleRunning a disabled job by hand does not re-enable it; this does.openclaw automations enable JOB-ID
Set up Gmail Pub/SubOne-time wizard for the Gmail watch, the Pub/Sub topic and subscription, and hook delivery.openclaw webhooks gmail setup --account [email protected]
Run the Gmail watcherForeground watcher for debugging; the Gateway normally starts it on boot once hooks are enabled.openclaw webhooks gmail run --account [email protected]
Queue a system eventLands on the main session; --mode now triggers the heartbeat at once rather than at the next tick.openclaw system event --text "Check for urgent follow-ups" --mode now
Show the last heartbeatenable and disable in its place turn heartbeats back on or pause them.openclaw system heartbeat last
View presenceopenclaw system presence

Diagnostics and repair 20

ActionShortcut
Run guided health checksInteractive; note that it may migrate legacy config and state even when --fix is not given.openclaw doctor
Apply recommended repairsAlias of --repair; it still asks before each repair unless running unattended is safe.openclaw doctor --fix
Read-only lint for CIChanges nothing and sets its exit code from the findings threshold; --severity-min filters them.openclaw doctor --lint
Doctor report as JSONAdvisory and read-only: it exits successfully, so check ok and findings in the output.openclaw doctor --json
Scan for extra Gateway installsLooks through system services and reports recent Gateway supervisor restart handoffs.openclaw doctor --deep
Repair without prompts--non-interactive alone suppresses prompts, not writes; safe migrations still apply.openclaw doctor --fix --non-interactive
Generate a Gateway tokenCreates and configures a token; restart the Gateway afterwards.openclaw doctor --generate-gateway-token
Check plugins after an upgradeRuns plugin compatibility probes and exits 1 on any error-level finding.openclaw doctor --post-upgrade
Hand diagnostics to a coding agentRuns read-only checks, writes a sanitized prompt and offers it to a detected agent such as Claude Code or Codex.openclaw triage
Collect diagnostics onlyGathers the sanitized diagnostics without starting an agent; --non-interactive does the same.openclaw triage --json
Audit security settingsStays on the config and filesystem read-only path and does not load plugin runtimes.openclaw security audit
Audit with live probesAdds best-effort live Gateway probes and plugin-owned audit collectors.openclaw security audit --deep
Apply safe security fixesSwitches open group policies to allowlist and tightens permissions on state, config and credential files.openclaw security audit --fix
List sandbox runtimesOne row per runtime with its backend, age, idle time and owning session or agent.openclaw sandbox list
Recreate sandbox runtimesRemoves them so they are rebuilt with current config on next use; pass exactly one of --all, --session or --agent.openclaw sandbox recreate --all
Explain the sandbox policyReports the effective mode, scope, workspace access and tool policy, with the config keys to change.openclaw sandbox explain
Show browser statusPassive: it never launches Chrome just to collect facts.openclaw browser status
Start the managed browser--headless applies to that start only and does not change the saved profile config.openclaw browser start
Stop the browser sessionEnds the control session and drops temporary emulation overrides, even for browsers OpenClaw did not launch.openclaw browser stop
Diagnose the browser--deep adds a live snapshot probe to prove the current tab can be inspected.openclaw browser doctor --deep

Updates, backup and reset 23

ActionShortcut
Update OpenClawRestarts the Gateway service after a successful update unless --no-restart is given.openclaw update
Show update statusInspect availability and the last recorded run before retrying an update.openclaw update status
Switch update channelChannels are stable, extended-stable, beta and dev; the choice is saved after the core update succeeds.openclaw update --channel beta
Preview an updateShows the planned channel, target and restart flow without installing or writing config.openclaw update --dry-run
Update without restartingopenclaw update --no-restart
Skip update confirmationsAnswers prompts such as the downgrade confirmation.openclaw update --yes
Pick a channel interactivelyAsks for the update channel and whether to restart the Gateway afterwards.openclaw update wizard
Repair stale update stateFor update status stuck in progress while the Gateway is healthy; make sure no update is still running.openclaw update repair
Preview recovery cleanupLists retained migration originals once the update and your conversations are verified.openclaw update cleanup --dry-run
Create a backup archiveWrites a timestamped .tar.gz of state, config, credentials and sessions to the current directory; existing archives are never overwritten.openclaw backup create
Back up and verifyRescans the new archive the way openclaw backup verify does.openclaw backup create --verify
Back up the config file onlyExports just the active JSON config, without its $include dependencies.openclaw backup create --only-config
Verify a backup archiveChecks the manifest, rejects unsafe archive paths and confirms every declared payload exists.openclaw backup verify ARCHIVE
Restore a backupRestores into a fresh staging directory and leaves the live state directory untouched.openclaw backup restore ARCHIVE.TAR.GZ --target FRESH-DIRECTORY
Schedule backupsCreates one Gateway-owned automation with a fixed name.openclaw backup enable --repository ~/Backups/openclaw-git --every 24h --push
Reset local stateKeeps the CLI installed; scopes are config, config+creds+sessions and full.openclaw reset
Preview a resetPrints the actions and removes nothing.openclaw reset --dry-run
Reset everything unattendedfull removes the state directory and workspaces; --non-interactive requires both --scope and --yes.openclaw reset --scope full --yes --non-interactive
Remove service and local dataWith no scope flags an interactive prompt asks which components to remove; the CLI itself is not removed.openclaw uninstall
Uninstall everything--all is shorthand for --service --state --workspace --app.openclaw uninstall --all --yes
List migration providersShows the installed providers; the bundled ones cover Claude, Codex CLI and Hermes.openclaw migrate list
Preview a Hermes importopenclaw migrate hermes --dry-run
Import state from Hermesopenclaw migrate apply hermes --yes

Terminal UI keys 11

Reply delivery to a chat provider is fixed when the TUI starts: there is no /deliver command or settings toggle, so restart the TUI with --deliver to change it.

ActionShortcut
Send the messageMessages go to the Gateway, or to the embedded runtime in local mode.Enter
Insert a newlineStarts a new line in the composer; the message is not sent.Shift+EnterorCtrl+J
Abort the active runFrom the composer it aborts the run; with a question prompt open it collapses the prompt instead.Esc
Close a pickerA filter typed into the session picker is cleared first; press again to close.EscorCtrl+C
Clear input, twice to exitEmpties the composer and prints an exit hint; aborting a run is Esc.Ctrl+C
Exit the TUICtrl+D
Open the model pickerLists the agent's published models and sets the session override; unavailable ones stay visible with a reason.Ctrl+L
Open the agent pickerSwitches the TUI to a different agent.Ctrl+G
Open the session pickerLimited to 50 sessions from the past week; use /session with a key for older ones.Ctrl+P
Expand or collapse tool outputTool calls appear as cards; this switches them between collapsed and expanded views.Ctrl+O
Show or hide thinkingChanging the setting reloads the session history.Ctrl+T

Terminal UI commands 15

ActionShortcut
Open the terminal UIConnects to the Gateway; when started without --session it resumes the last selected session.openclaw tui
Run the TUI without a GatewayUses the embedded agent runtime; cannot be combined with --url, --token or --password.openclaw tui --local
Local TUI shortcutAlias of openclaw tui --local, as is openclaw terminal.openclaw chat
Connect to a specific GatewayWith --url the TUI ignores stored credentials, so pass --token or --password explicitly.openclaw tui --url ws://127.0.0.1:18789 --token TOKEN
Open a session with delivery onDelivery of replies to the chat provider is off by default and fixed for the whole TUI session.openclaw tui --session main --deliver
Switch sessionA bare key such as main is scoped to the current agent; a full agent:other:main key switches agent too./session KEY
Switch agent/agent ID
Show a Gateway summaryReports version, per-channel config summaries and the session inventory, archived sessions included; alias /gwstatus./gateway-status
Open TUI settingsPanel with the tool-output and thinking-visibility switches; it cannot change delivery./settings
Reopen a pending questionBrings back a question prompt you collapsed with Esc./question
Abort the active run/abort
Quit the TUI/quit does the same; pasted with a trailing newline it does not close the TUI./exit
Sign in to a provider locallyLocal mode only: it starts the provider sign-in without leaving the TUI./auth
Inspect Chrome extension setupRuns on the TUI host, not the Gateway; install and verify are its other subcommands./browser-setup
Run a shell command locallyPut it at the start of a line, as in !openclaw config validate; the TUI asks once per session for permission.!

Chat commands for sessions and models 21

Directives such as /think, /fast, /verbose, /reasoning, /model and /queue are removed from the message before the model reads it, and most of them persist as session settings when sent alone.

ActionShortcut
Start a fresh sessionArchives the current session first; a model name may follow./new
Reset the session in place/reset soft keeps the transcript and reruns startup./reset
Name the sessionLeave the title out to see the present name plus a suggested one./name TITLE
Compact the session contextAccepts optional instructions after the command./compact
Abort the current run/stop
Export the session to HTMLOwner-only; writes inside the workspace, and /export is the alias./export-session
Show or switch the modelArguments are a model name, default, list or status./model
Change model for this sessionConfigured defaults stay as they are; --session is the long form./model MODEL -s
Change the agent's default modelOwner or admin only; also switches the current session./model MODEL -a
Change the global default modelOwner or admin only; requests an update of agents.defaults.model./model MODEL -g
Return to the default modelClears this session's selection without writing any defaults./model default -s
List providers or modelsOptional provider, page and limit arguments narrow the list./models
Set the thinking leveldefault clears the session override; /thinking and /t are aliases./think LEVEL
Show or set fast modeTakes status, auto, on, off or default; the effect depends on the provider./fast
Turn on verbose outputAlso off and full; meant for debugging, and risky in group chats./verbose on
Show model reasoningAlso off and stream; /reason is the alias./reasoning on
Turn on elevated modeAlso off, ask and full; /elev is the alias./elevated on
Show plugin trace linesReveals only plugin-owned trace and debug lines for the current session./trace on
Set the queue modeModes are steer, followup, collect and interrupt; they decide what a message sent mid-run does./queue MODE
Steer the active runAdds guidance to the run in progress; /tell is the alias./steer MESSAGE
Sign in to a model providerOwner or admin only; shows the sign-in providers and then the connection methods./login

Chat commands for status, tools and skills 20

/help, /commands, /status and /whoami are inline shortcuts: they run at once, even inside a longer message, and only for authorized senders. Ordinary commands must be the only content of the message.

ActionShortcut
Show the help summary/help
List all commandsGenerated catalog: what appears depends on config flags, the channel, and installed plugins and skills./commands
Show available tools/tools verbose adds short descriptions; results depend on agent, channel, sender and model./tools
Show runtime statusIncludes uptime for Gateway and host, the health of plugins, and provider quota./status
Show detailed plugin healthRequires commands.plugins: true; lists load errors, quarantines and dependency issues./status plugins
Show token usage per replySets the footer under each response; other values are off, full and reset./usage tokens
Print a cost summaryLocal summary; in the TUI it covers the session, today and the last 30 days./usage cost
Show your sender id/id is the alias; like /help it runs inline for authorized senders./whoami
Explain context assemblyTakes list, detail, map or json for different views./context
Manage the session goalSub-actions cover status, starting, editing, pausing, resuming, completing, blocking and clearing a goal./goal
Ask a side questionUses the session as background but leaves future context and transcript history unchanged; /side is the alias./btw QUESTION
Run a named skillGeneric entry point that always works; input for the skill may follow the name./skill NAME
Draft a skill from the chatProduces one reviewable skill through Skill Workshop./learn
Repeat a promptOwner-only; /loop 5m check deploy status creates a fixed-cadence job, and without an interval the loop paces itself./loop INTERVAL PROMPT
List loops in this chat/loop status
Stop loops in this chatA loop name after stop limits it to matching loops./loop stop
Answer an approval promptResolves exec, plugin or OpenClaw change approvals./approve ID DECISION
List sub-agent runslog and info are the other subcommands, all for the current session./subagents list
List thread-bound agents/agents
Ask the setup helperWorks from an owner DM; in the TUI it returns you to the setup and repair chat./openclaw REQUEST

Chat commands for owners and admins 18

ActionShortcut
Restart OpenClawEnabled by default through commands.restart: true./restart
Update OpenClaw from chatOwner only; uses the configured update channel and reports completion or failure in the same chat./update
Show the config from chatOwner-only and off until commands.config: true; get, set and unset are the other subcommands./config show
Write a config value from chatValidated before the write and persists across restarts./config set channels.whatsapp.responsePrefix="[openclaw]"
Show MCP server configOwner-only; requires commands.mcp: true./mcp show
List plugins from chatRequires commands.plugins: true; install, enable and disable are owner-only writes./plugins list
Show runtime overridesRuntime-only config overrides that need commands.debug: true; set, unset and reset change them./debug show
Set the send policyOwner only; the values are on, off and inherit./send on
Manage allowlist entriesText-only; subcommands are list, add and remove./allowlist
Set group activation to mentionGroup activation mode is either mention or always./activation mention
Run a shell command on the hostRequires commands.bash: true; ! COMMAND is the alias./bash COMMAND
Check a background shell jobA session id may follow to pick one job.!poll
Stop a background shell job!stop
Turn on text to speechOther arguments include off, status, provider, limit and summary./tts on
Manage device pairingBundled plugin command with qr, status, pending, approve, cleanup and notify subcommands./pair
Check memory dreamingon and off toggle it, for the owner or a Gateway admin./dreaming status
Start a support reportOwner-only; exec approval is requested on each use./diagnostics
Detach the conversationThe agent session stays open; only this conversation is detached./session unbind

Global flags 10

ActionShortcut
Use the dev profileState moves to ~/.openclaw-dev and the default Gateway port becomes 19001, with derived ports shifted.--dev
Use a named profileState lives under ~/.openclaw-NAME; a named profile replaces state and config paths inherited from another one.--profile NAME
Run inside a containerExecutes the CLI in a running Podman or Docker container; OPENCLAW_CONTAINER supplies the default name.--container NAME
Override the log levelApplies to both file and console output.--log-level LEVEL
Disable ANSI colorsSetting NO_COLOR=1 has the same effect.--no-color
Shorthand for openclaw updateRewrites to the update command, which helps in shells and launcher scripts.--update
Print the versionAll three spellings show the version number and exit.-V / --version / -v
Stop option parsingWords after it are still read as commands, as in openclaw -- config get gateway.port, but --help becomes a plain argument.--
Print JSON outputOn bounded reporting commands stdout carries exactly one JSON document; warnings stay on stderr.--json
Show a command's helpPlugin-added subcommands change independently, so the built-in help is the authoritative list.COMMAND --help

Notes

Two surfaces, one agent

OpenClaw splits its typeable controls into two surfaces that never overlap. In-session slash commands (/help, /status, /compact) and the TUI keys steer a live conversation. Everything else on this page belongs to the openclaw terminal CLI, which administers the platform: onboarding, channel accounts, model configuration, backups, and the Gateway process itself. If you are typing into a chat, you want a slash command; if you are typing into a shell on the Gateway host, you want the CLI. Inside the terminal UI, Esc aborts the active run, while Ctrl + C only clears the input and, pressed twice, exits.

Isolating state with global flags

Three of the global flags deal with isolation. --dev moves state under ~/.openclaw-dev and shifts the default Gateway port to 19001, so a development instance can run beside the normal one. --profile NAME generalizes this: state lives under ~/.openclaw-NAME with its own config path, and a named profile replaces the paths inherited from another profile, including those of a running Gateway service. --container NAME runs the whole CLI inside a running Podman or Docker container. Global options go in front of the command; options that belong to a command go after its name.

Operating the Gateway day to day

The operational loop revolves around the Gateway, the process the CLI reaches over WebSocket RPC. openclaw gateway runs it in the foreground, openclaw gateway install turns it into a background service, openclaw gateway status and openclaw status --all report on it, openclaw doctor checks and repairs it, and openclaw backup create archives state, config, credentials and sessions before anything risky. Outbound traffic goes through a single command: openclaw message covers sends and channel actions across Discord, Slack, Telegram, Signal, WhatsApp and the rest. For the in-session command set that pairs with this CLI, see the OpenClaw prompt & command reference.

Questions

What is the difference between OpenClaw slash commands and the openclaw CLI?

Slash commands like /help, /status, and /compact run inside an active chat session and steer the conversation. The openclaw CLI runs in a terminal on the Gateway host and operates the platform itself — setup, channels, models, backups, and the Gateway process. One surface drives a session, the other administers the system.

How do I run several isolated OpenClaw instances on one machine?

Use the global flags. --dev keeps all state under ~/.openclaw-dev and moves the default Gateway port to 19001, while --profile NAME keeps state under ~/.openclaw-NAME with its own config path. --container NAME goes one step further and runs the CLI inside a running Podman or Docker container.

Which openclaw commands should I reach for when something breaks?

Start with openclaw doctor, which pairs health checks with guided repairs. openclaw status --all produces a read-only, pasteable diagnosis that includes the security audit, openclaw health fetches a health snapshot from the running Gateway, and openclaw logs --follow tails the Gateway log. openclaw triage collects sanitized diagnostics and offers them to a coding agent on the same machine.

What does openclaw gateway actually run?

openclaw gateway runs the Gateway in the foreground on a WebSocket port, usually 18789, and refuses to start unless gateway.mode=local is configured. Its subcommands install, start, stop and restart it as a background service (a LaunchAgent on macOS, a systemd user unit on Linux, a Scheduled Task on Windows), and status, health, probe and discover query running gateways over WebSocket RPC.

Which key stops a running reply in the OpenClaw terminal UI?

Esc aborts the active run from the composer, and the commands /stop and /abort do the same. Ctrl + C does not stop it: it clears the input and shows an exit hint, and a second press exits the TUI.

Is openclaw cron the same command as openclaw automations?

Yes. The command registers as openclaw cron with openclaw automations as an alias, and every subcommand works with either spelling. The documentation writes its examples with automations, which is why rows such as openclaw automations list use that form.

Sources and checks

46 more source pages

Every row on this page was matched to a line in the documentation above on . A binding that could not be found there is not listed.

4 rows from the earlier version of this page were removed in that check: duplicates, and bindings the documentation does not list or lists differently.

Found a wrong or missing key? Tell us and it gets checked against the source. How we verify describes the process and its limits.