Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.wednesdayai.dev/llms.txt

Use this file to discover all available pages before exploring further.

​
Getting started

This page takes you from zero to a running WednesdayAI gateway with the control panel accessible. Channel setup — connecting WhatsApp, Telegram, iMessage, and others — comes after the gateway is stable.
Fastest path to a first chat: once the gateway is running, open http://127.0.0.1:18789/ in a browser on the same machine. The built-in control panel lets you chat with your AI without connecting any external channel first.

​
Requirements

  • Node.js 22 or newer — the installer script installs it automatically if missing
  • macOS, Linux, or Windows (via WSL2) — native Windows is supported but WSL2 is recommended
  • About 500 MB free disk space (including node modules)
Check your Node version: 
node --version
If it prints v22.x.x or higher you are ready. Otherwise, let the installer handle it or install via nvm / fnm first.

​
Step 1 — Install

The installer script is the recommended path. It detects your Node version, installs or upgrades it if needed, installs the openclaw CLI globally via npm, and then launches the onboarding wizard. 
curl -fsSL https://wednesdayai.dev/install.sh | bash
pnpm requires an extra step to approve packages with native build scripts:
pnpm add -g openclaw@latest
pnpm approve-builds -g    # select openclaw, sharp, node-llama-cpp when prompted
If sharp fails during install because you have libvips installed via Homebrew:
SHARP_IGNORE_GLOBAL_LIBVIPS=1 npm install -g openclaw@latest

​
Step 2 — Run the onboarding wizard

If the installer script completed successfully it already ran the wizard. If you used the manual npm install, run: 
openclaw onboard --install-daemon
The wizard walks you through:
  1. Auth provider — choose which AI provider (Claude, GPT-4, Gemini, local) to connect first. You can add more later via openclaw login.
  2. Gateway port — defaults to 18789. Change it here if that port is already in use.
  3. System service — --install-daemon installs the gateway as a background service so it starts at login. Recommended for persistent deployments.
You can rerun the wizard at any time with openclaw onboard. Individual steps are also available as subcommands — for example openclaw login to re-authenticate with a provider.

​
Step 3 — Verify the gateway

After onboarding, the gateway should be running as a service. Confirm: 
openclaw gateway status
Expected output: 
✔ Gateway running  pid=12345  port=18789  uptime=0m 12s
If the gateway is not running, start it: 
systemctl --user start openclaw-gateway
systemctl --user status openclaw-gateway

​
Step 4 — Open the control panel

openclaw dashboard
This opens http://127.0.0.1:18789/ in your default browser. If you are running the gateway on a remote server, see Remote access to reach it securely.
If the control panel loads and you can send a test message, your gateway is ready.

​
Step 5 — Run a health check

openclaw doctor
openclaw doctor validates your config file, checks that all configured channels and providers are reachable, and reports any missing credentials or unknown config keys. Fix any warnings before moving on. 
openclaw doctor --fix    # auto-repair common issues

​
What you have now

ComponentStatus
openclaw CLIInstalled globally
GatewayRunning as a background service
AuthAt least one AI provider connected
Control panelAccessible at http://localhost:18789/

​
Next steps

Gateway configuration

Tune port, TLS, rate limits, model routing, and all other gateway settings.

Connect channels

Add WhatsApp, Telegram, iMessage, Signal, Slack, Discord, and more.

Authentication

API keys, provider credentials, and OAuth tokens.

Remote access

Reach the gateway securely from outside localhost.

​
Troubleshooting

The npm global bin directory is not in your PATH. Quick fix:
echo 'export PATH="$(npm prefix -g)/bin:$PATH"' >> ~/.zshrc
source ~/.zshrc
Then verify: openclaw --version
Change the port in your config file (~/.openclaw/openclaw.json):
{
  "gateway": {
    "port": 18790
  }
}
Then restart: systemctl --user restart openclaw-gateway (Linux) or openclaw gateway start (macOS/manual).
The wizard requires an active TTY. If you are running over SSH without a PTY, add -t:
ssh -t user@host openclaw onboard
Or complete the wizard locally and then copy ~/.openclaw/openclaw.json to the server.
Unknown keys at the top level cause the gateway to refuse to start. Remove them, or run:
openclaw doctor --fix
This strips unknown keys and fills missing required defaults. Always check the diff before restarting the gateway.