otty / apps
All apps/OpenClaw

OpenClaw

openclaw-cli

Personal AI assistant you own and run on your own devices.

Runs as openclaw|macOS, Linux, Windows|docs.openclaw.ai
Open form in Otty otty.toml

Command form

ai-draft · 4 tasks · 17 fields

Run one headless agent turn or check OpenClaw status. Gateway, channels, plugins, onboarding and configuration commands are left out.

Opens the form; the finished command lands at your prompt, unrun
Run in Otty
otty gui openclaw-cli

openclaw agent exec

Run one agent turn
Run one agent turnExample values, fixed in this page — nothing here reaches a terminal
Basic
Prompt*
string
Working directory
directory
Model
string
TasksEach one presets the form for one job
Run a prompt
messagecwdmodel
Run a prompt file in a repo
message_filecwdjson
ParametersOnly these flags are editable in the form
Prompt
string · positional 0
Prompt file
Read the prompt from a UTF-8 file instead.
path
--message-file
Working directory
Sets both the agent workspace and the tool working directory.
path
--cwd
Config file
path
--config
Ignore ambient config
boolean
--isolated
Model
provider/model.
string
--model
Fallback models
Ordered fallbacks; requires a model.
string · repeatable
--fallback
Thinking level
string
--thinking
Lean tool surface for local models
boolean
--local-model-lean
Timeout (seconds)
Default 600; 0 disables the deadline.
integer
--timeout
JSON output
boolean
--json

openclaw status

Check status
Check statusExample values, fixed in this page — nothing here reaches a terminal
Basic
Full diagnosis
--all
Deep channel health checks
--deep
JSON output
--json
TasksEach one presets the form for one job
Full diagnosis
alldeepjson
Show provider usage
usageagent
ParametersOnly these flags are editable in the form
Full diagnosis
boolean
--all
Deep channel health checks
boolean
--deep
Provider usage
boolean
--usage
Agent id
Agent auth/profile scope for usage.
string
--agent
JSON output
boolean
--json
Timeout (ms)
integer
--timeout
SourcesEvery flag above is checked against these
docs
openclaw agent exec "Run the focused tests and fix failures" openclaw agent exec --message-file task.md --cwd ./repo [message]: positional prompt text --message-file <path>: read a UTF-8 prompt from a file; - reads stdin --cwd <dir>: set both the agent workspace and tool working directory --config <path>: run against this config file instead of the ambient c…
manual2026-10

docs.openclaw.ai

docs
openclaw status openclaw status --all openclaw status --deep openclaw status --usage --agent work --all: Full diagnosis (read-only, pasteable). --deep: Requests channel health (live checks where supported). Also enables the security audit. --usage: Prints normalized provider usage windows as X% left. --agent <id>: Selects the agent auth/profile scope for --u…
manual2026-10

docs.openclaw.ai

Before it fills your prompt, Otty checks the installed openclaw against its version. A form that does not match your version is not offered.