Skip to main content

​
Installation

npm install -g profclaw

​
Verify Installation

profclaw --version
profclaw doctor

​
Quick Setup

1

Initialize

profclaw init
Creates the default configuration files in the current directory.
2

Run the onboarding wizard

profclaw onboard
Detects your environment, selects the right deployment mode, and configures your first AI provider.
3

Start the server

profclaw serve
Starts the HTTP API server on port 3000 (configurable with -p).

​
Global Flags

These flags are available on every command.
​
--help
boolean
Show help text for the command.
​
--version
boolean
Print the installed profClaw version and exit.
​
--json
boolean
Output raw JSON instead of formatted tables. Available on most subcommands. Useful for scripting and piping to jq.

​
Environment Variables

The CLI reads these variables for its own configuration (separate from the server).
VariableDefaultDescription
PROFCLAW_API_URLhttp://localhost:3000URL of the profClaw server
PROFCLAW_API_TOKEN-Bearer token for API authentication
PROFCLAW_MODEminiDeployment mode (pico, mini, pro)
PORT3000Server port (used by serve and daemon)
Set API credentials permanently: 
profclaw config set apiUrl http://my-server:3000
profclaw config login --token eyJ...
Or via environment: 
export PROFCLAW_API_URL=http://my-server:3000
export PROFCLAW_API_TOKEN=eyJ...

​
Command Groups

GroupDescription
init / onboardFirst-run setup
serve / daemonRun the server
chatInteractive AI chat
agent / taskAgent and task management
configConfiguration management
authUser and invite management
skill / pluginExtend functionality
tools / mcpTool and MCP management
memory / summaryKnowledge and history
cost / statusMonitoring
security / auditSecurity management
doctor / logsDiagnostics
deviceDevice pairing
backup / resetData management
update / versionLifecycle

​
Shell Completion

Generate shell completion scripts to enable tab completion. 
profclaw completion bash >> ~/.bashrc
source ~/.bashrc