CLI

The Claw CLI by default starts the TUI when run without any arguments.

claw

But it also accepts commands as documented on this page. This allows you to interact with Claw programmatically.

claw run "Explain how closures work in JavaScript"

---

tui

Start the Claw terminal user interface.

claw [project]

Flags

Flag	Short	Description
--continue	-c	Continue the last session
--session	-s	Session ID to continue
--prompt	-p	Prompt to use
--model	-m	Model to use in the form of provider/model
--agent		Agent to use
--port		Port to listen on
--hostname		Hostname to listen on

---

Commands

The Claw CLI also has the following commands.

---

agent

Manage agents for Claw.

claw agent [command]

---

create

Create a new agent with custom configuration.

claw agent create

This command will guide you through creating a new agent with a custom system prompt and tool configuration.

---

auth

Command to manage credentials and login for providers.

claw auth [command]

---

login

Claw is powered by the provider list at Models.dev, so you can use claw auth login to configure API keys for any provider you’d like to use. This is stored in ~/.local/share/claw/auth.json.

claw auth login

When Claw starts up it loads the providers from the credentials file. And if there are any keys defined in your environments or a .env file in your project.

---

list

Lists all the authenticated providers as stored in the credentials file.

claw auth list

Or the short version.

claw auth ls

---

logout

Logs you out of a provider by clearing it from the credentials file.

claw auth logout

---

github

Manage the GitHub agent for repository automation.

claw github [command]

---

install

Install the GitHub agent in your repository.

claw github install

This sets up the necessary GitHub Actions workflow and guides you through the configuration process. Learn more.

---

run

Run the GitHub agent. This is typically used in GitHub Actions.

claw github run

Flags

Flag	Description
--event	GitHub mock event to run the agent for
--token	GitHub personal access token

---

models

List all available models from configured providers.

claw models [provider]

This command displays all models available across your configured providers in the format provider/model.

This is useful for figuring out the exact model name to use in your config.

You can optionally pass a provider ID to filter models by that provider.

claw models anthropic

Flags

Flag	Description
--refresh	Refresh the models cache from models.dev
--verbose	Use more verbose model output (includes metadata like costs)

Use the --refresh flag to update the cached model list. This is useful when new models have been added to a provider and you want to see them in Claw.

claw models --refresh

---

run

Run claw in non-interactive mode by passing a prompt directly.

claw run [message..]

This is useful for scripting, automation, or when you want a quick answer without launching the full TUI. For example.

claw run Explain the use of context in Go

You can also attach to a running claw serve instance to avoid MCP server cold boot times on every run:

# Start a headless server in one terminal
claw serve

# In another terminal, run commands that attach to it
claw run --attach http://localhost:4096 "Explain async/await in JavaScript"

Flags

Flag	Short	Description
--command		The command to run, use message for args
--continue	-c	Continue the last session
--session	-s	Session ID to continue
--share		Share the session
--model	-m	Model to use in the form of provider/model
--agent		Agent to use
--file	-f	File(s) to attach to message
--format		Format: default (formatted) or json (raw JSON events)
--title		Title for the session (uses truncated prompt if no value provided)
--attach		Attach to a running claw server (e.g., http://localhost:4096)
--port		Port for the local server (defaults to random port)

---

serve

Start a headless claw server for API access. Check out the server docs for the full HTTP interface.

claw serve

This starts an HTTP server that provides API access to claw functionality without the TUI interface.

Flags

Flag	Short	Description
--port	-p	Port to listen on
--hostname		Hostname to listen on

---

upgrade

Updates claw to the latest version or a specific version.

claw upgrade [target]

To upgrade to the latest version.

claw upgrade

To upgrade to a specific version.

claw upgrade v0.1.48

Flags

Flag	Short	Description
--method	-m	The installation method that was used; curl, npm, pnpm, bun, brew

---

Global Flags

The claw CLI takes the following global flags.

Flag	Short	Description
--help	-h	Display help
--version	-v	Print version number
--print-logs		Print logs to stderr
--log-level		Log level (DEBUG, INFO, WARN, ERROR)

---

Environment variables

Claw can be configured using environment variables.

Variable	Type	Description
CLAW_AUTO_SHARE	boolean	Automatically share sessions
CLAW_GIT_BASH_PATH	string	Path to Git Bash executable on Windows
CLAW_CONFIG	string	Path to config file
CLAW_CONFIG_DIR	string	Path to config directory
CLAW_CONFIG_CONTENT	string	Inline json config content
CLAW_DISABLE_AUTOUPDATE	boolean	Disable automatic update checks
CLAW_DISABLE_PRUNE	boolean	Disable pruning of old data
CLAW_DISABLE_TERMINAL_TITLE	boolean	Disable automatic terminal title updates
CLAW_PERMISSION	string	Inlined json permissions config
CLAW_DISABLE_DEFAULT_PLUGINS	boolean	Disable default plugins
CLAW_DISABLE_LSP_DOWNLOAD	boolean	Disable automatic LSP server downloads
CLAW_ENABLE_EXPERIMENTAL_MODELS	boolean	Enable experimental models
CLAW_DISABLE_AUTOCOMPACT	boolean	Disable automatic context compaction
CLAW_CLIENT	string	Client identifier (defaults to cli)
CLAW_ENABLE_EXA	boolean	Enable Exa web search tools

---

Experimental

These environment variables enable experimental features that may change or be removed.

Variable	Type	Description
CLAW_EXPERIMENTAL	boolean	Enable all experimental features
CLAW_EXPERIMENTAL_ICON_DISCOVERY	boolean	Enable icon discovery
CLAW_EXPERIMENTAL_DISABLE_COPY_ON_SELECT	boolean	Disable copy on select in TUI
CLAW_EXPERIMENTAL_BASH_MAX_OUTPUT_LENGTH	number	Max output length for bash commands
CLAW_EXPERIMENTAL_BASH_DEFAULT_TIMEOUT_MS	number	Default timeout for bash commands in ms
CLAW_EXPERIMENTAL_OUTPUT_TOKEN_MAX	number	Max output tokens for LLM responses
CLAW_EXPERIMENTAL_FILEWATCHER	boolean	Enable file watcher for entire dir
CLAW_EXPERIMENTAL_OXFMT	boolean	Enable oxfmt formatter