OpenClaw

https://docs.openclaw.ai
Admin
OpenClaw is a multi-platform AI agent gateway that bridges WhatsApp, Telegram, Discord, and iMessage...
Tokens:5,260,604
Snippets:43,995
Trust Score:5
Update:21 hours ago
Show doc for...
Tokens:
Raw
### Run classic onboarding with daemon install

Source: https://docs.openclaw.ai/help/faq-first-run/quick-start

Alternative to the two-command guided flow. Selects the classic step-by-step wizard and installs the daemon in one command, skipping the Quick start and Custom setup choice.

```bash
openclaw onboard --install-daemon
```

--------------------------------

### Install OpenClaw with guided onboarding

Source: https://docs.openclaw.ai/help/faq-first-run/quick-start

Recommended one-liner installer that starts guided onboarding automatically. After onboarding, press Ctrl+C to stop the foreground Gateway and install the background service.

```bash
curl -fsSL --proto '=https' --tlsv1.2 https://openclaw.ai/install.sh | bash
```

--------------------------------

### Run guided setup for ClickClack

Source: https://docs.openclaw.ai/channels/clickclack

Run the guided setup wizard. Select ClickClack, then enter the server URL, bot token, and workspace when prompted. Guided setup checks the server, token, and workspace after saving; a failed check does not discard the configuration.

```bash
openclaw onboard
```

--------------------------------

### OpenClaw setup command examples

Source: https://docs.openclaw.ai/web/tui

Shows three ways to invoke 'openclaw setup': interactive start, one-request run with '-m', and a config write with '--yes'. Persistent config writes require approval or '--yes'. '--json' prints startup overview as JSON.

```bash
openclaw setup                       # start interactively
openclaw setup -m "status"           # run one request and exit
openclaw setup -m "set default model openai/gpt-5.2" --yes   # apply a config write
```

--------------------------------

### Run the Feishu channel setup wizard

Source: https://docs.openclaw.ai/channels/feishu/setup

Run this command to start the Feishu channel setup wizard. It installs the @openclaw/feishu plugin if missing and guides through manual or QR setup. Requires OpenClaw 2026.5.29 or above.

```bash
openclaw channels login --channel feishu
```

--------------------------------

### Select classic setup flow with --flow

Source: https://docs.openclaw.ai/start/wizard

Use --flow quickstart or --flow manual (alias advanced) to skip the setup mode prompt and select a flow directly.

```bash
openclaw onboard --flow quickstart
```

```bash
openclaw onboard --flow manual
```

--------------------------------

### openclaw onboard command examples

Source: https://docs.openclaw.ai/cli/onboard

Shows common invocations of openclaw onboard, including TUI, classic, modern, quickstart, manual, import, skip-bootstrap, recommendations, and remote modes. Use these to run the guided setup or manage recommendations.

```bash
openclaw onboard
openclaw onboard --tui
openclaw onboard --classic
openclaw onboard --modern
openclaw onboard --flow quickstart
openclaw onboard --agent-name robby
openclaw onboard --flow manual
openclaw onboard --flow import
openclaw onboard --import-from hermes --import-source ~/.hermes
openclaw onboard --skip-bootstrap
openclaw onboard recommendations --json
openclaw onboard recommendations --agent writer --json
openclaw onboard recommendations --agent writer acknowledge
openclaw onboard recommendations acknowledge --agent writer
openclaw onboard recommendations refresh --agent writer
openclaw onboard recommendations acknowledge
openclaw onboard recommendations acknowledge --retry "<failed-id>"
openclaw onboard recommendations refresh
openclaw onboard --mode remote --remote-url wss://gateway-host:18789
```

--------------------------------

### Install and run OpenClaw with npx

Source: https://docs.openclaw.ai/start/getting-started

Run this command in a terminal to install and start OpenClaw. On a fresh install, choose 'Quick start' after the security guide pointer. The Gateway runs in the terminal until you press Ctrl+C; your config stays saved.

```bash
npx openclaw@latest
```

--------------------------------

### Set up isolated X11 session and prepare live rig

Source: https://docs.openclaw.ai/nodes/computer-use

Sets up the X11 display, starts Xvfb and openbox, creates a scratch directory, and prepares the live rig for a Linux proof. Must be run inside the `dbus-run-session` shell from the previous step.

```bash
export DISPLAY=:99 XDG_SESSION_TYPE=x11 NO_AT_BRIDGE=0
Xvfb "$DISPLAY" -screen 0 1280x800x24 -nolisten tcp &
openbox >/tmp/openclaw-cu-openbox.log 2>&1 &
scratch="$(mktemp -d /tmp/openclaw-cu-live.XXXXXX)"
scripts/dev/computer-use-macos-live-rig.sh prepare-linux \
  cu-linux-live-proof 29431 "$scratch"
```

--------------------------------

### Clone, checkout, and start Kev server

Source: https://docs.openclaw.ai/plugins/typesafe

Sets up the Kev repository, installs dependencies, downloads the Qwen3-based Kev-4B checkpoint, and starts the server on port 8009. Requires Python 3.12+ and uv. The first start downloads base model weights.

```sh
git clone https://github.com/jaredpalmer/kev.git
cd kev
git checkout 5f78968927069eaacc3b2bdb688586989b3933ac
uv sync --frozen --extra serve
uv run python - <<'PY'
from huggingface_hub import snapshot_download 
snapshot_download(
    "jaredpalmer/kev-4b",
    revision="c4bfa11b0dc07691884f2d97f1c4c4c05c92e416",
    local_dir="models/kev-4b-qwen3",
)
PY
KEV_DTYPE=bf16 uv run --extra serve python -m kev.serve \
  --run models/kev-4b-qwen3 --port 8009
```

--------------------------------

### Run openclaw doctor for guided fixes

Source: https://docs.openclaw.ai/cli/channels

Use this command to get guided fixes for issues detected in the OpenClaw setup.

```bash
openclaw doctor
```

--------------------------------

### Quick Start Installation Script

Source: https://docs.openclaw.ai/install/ansible

One-command setup that downloads and runs the openclaw-ansible installer. Requires root or sudo privileges and an internet connection.

```bash
curl -fsSL https://raw.githubusercontent.com/openclaw/openclaw-ansible/main/install.sh | bash
```

--------------------------------

### Add Buzz Channel

Source: https://docs.openclaw.ai/channels/buzz

Starts the guided setup for the Buzz channel. The setup flow walks through account selection, relay URL entry, bot identity generation, room selection, and configuration verification.

```bash
openclaw channels add --channel buzz
```

--------------------------------

### Onboard with daemon install and xAI OAuth

Source: https://docs.openclaw.ai/providers/xai

Run onboarding with daemon install, then pick xAI/Grok OAuth at the model/auth step. On a VPS or over SSH, select xAI OAuth directly; it uses device-code verification and does not need a localhost callback.

```bash
openclaw onboard --install-daemon
```

```bash
openclaw onboard --install-daemon --auth-choice xai-oauth
```

--------------------------------

### OpenCode example

Source: https://docs.openclaw.ai/start/wizard-cli-automation

Onboard with OpenCode using `--auth-choice opencode-zen` and the `OPENCODE_API_KEY` environment variable. Swap to `--auth-choice opencode-go --opencode-go-api-key "$OPENCODE_API_KEY"` for the Go catalog.

```bash
openclaw onboard --non-interactive --accept-risk --skip-health \
  --mode local \
  --auth-choice opencode-zen \
  --opencode-zen-api-key "$OPENCODE_API_KEY" \
  --gateway-bind loopback
```

--------------------------------

### openclaw webhooks gmail setup usage examples

Source: https://docs.openclaw.ai/cli/webhooks

Shows three usage examples: basic setup with an account, setup with project and JSON output, and setup with a custom hook URL. The command authenticates gcloud, enables APIs, creates/updates Pub/Sub resources, starts Gmail watch, and writes hooks.gmail with hooks.enabled: true. Missing dependencies can be auto-installed on macOS via Homebrew; other platforms need them pre-installed. The Gmail account must already be authorized in gog.

```bash
openclaw webhooks gmail setup --account you@example.com
```

```bash
openclaw webhooks gmail setup --account you@example.com --project my-gcp-project --json
```

```bash
openclaw webhooks gmail setup --account you@example.com --hook-url https://gateway.example.com/hooks/gmail
```

--------------------------------

### Onboard Qwen Standard (Global endpoint)

Source: https://docs.openclaw.ai/providers/qwen

Run this command to onboard the Qwen Standard (pay-as-you-go) plan using the Global endpoint. Requires a QWEN_API_KEY from home.qwencloud.com/api-keys.

```bash
openclaw onboard --auth-choice qwen-standard-api-key
```

--------------------------------

### Start the dev Gateway with pnpm

Source: https://docs.openclaw.ai/start/setup

Installs dependencies (first run only), runs setup, and starts the Gateway watch process. The watch process reloads on source, config, and bundled-plugin metadata changes, and runs openclaw doctor --fix --non-interactive once if the Gateway exits during startup.

```bash
pnpm install# First run only (or after resetting local OpenClaw config/workspace)pnpm openclaw setuppnpm gateway:watch
```

--------------------------------

### Install and login Tailscale on VPS (bash)

Source: https://docs.openclaw.ai/help/faq/remote-gateways-and-nodes

Installs Tailscale on the VPS and starts the tailscale up process. Run as root or with sudo.

```bash
curl -fsSL https://tailscale.com/install.sh | shsudo tailscale up
```

--------------------------------

### Run onboarding for MiniMax China API key

Source: https://docs.openclaw.ai/providers/minimax

Run this command to start onboarding with MiniMax China API key. This configures api.minimaxi.com as the base URL.

```bash
openclaw onboard --auth-choice minimax-cn-api
```

--------------------------------

### Run OpenCode Zen onboarding

Source: https://docs.openclaw.ai/providers/opencode

Starts the onboarding process for the OpenCode Zen catalog, which is the curated multi-model proxy. Use this command to authenticate with the Zen provider.

```bash
openclaw onboard --auth-choice opencode-zen
```

--------------------------------

### Onboard and Check Gateway Status

Source: https://docs.openclaw.ai/gateway/team-server

Run these commands as the service account that will run the Gateway. The first command installs the daemon, and the second checks the gateway status. Ensure you complete the Getting started steps first.

```bash
openclaw onboard --install-daemon
openclaw gateway status --deep
```

--------------------------------

### Installer spec YAML example

Source: https://docs.openclaw.ai/tools/skills

Example installer spec in YAML front-matter format. It defines a skill named 'gemini' that requires the 'gemini' binary and provides a Homebrew installer for 'gemini-cli'. The metadata includes an emoji and installer configuration.

```markdown
---
name: gemini
description: Use Gemini CLI for coding assistance and Google search lookups.
metadata:
  {
    "openclaw":
      {
        "emoji": "♊️",
        "requires": { "bins": ["gemini"] },
        "install":
          [
            {
              "id": "brew",
              "kind": "brew",
              "formula": "gemini-cli",
              "bins": ["gemini"],
              "label": "Install Gemini CLI (brew)",
            },
          ],
      },
  }
---
```
Tokens:
Raw