Closes link-kind audit findings for docs/install/, docs/help/, docs/reference/, docs/start/, docs/web/ and docs/nodes/. - start/hubs: point the Model providers hub entry at the provider directory (/providers) instead of the /providers/models quickstart duplicate. - Add the missing reciprocal links the audit found: Cloudflare Containers, Kubernetes and Ansible from Docker and the Linux server page; macOS VMs from iMessage and the Linux server page; Podman from the sandbox Podman backend; Updating from Migrating; Docker from the Configuration page; Backups, Bootstrapping and Default AGENTS.md from Agent workspace; Bootstrapping from the BOOTSTRAP template; Tests from the two help testing pages; Session management deep dive from Context engine; Transcript hygiene from Session and Session pruning; SecretRef credential surface from Auth credential semantics; Device model database from the Nodes macOS section; RPC adapters from Signal and iMessage; Personal assistant setup from Getting started; Onboarding from the macOS platform page; The Lobster from Control UI settings; Release performance sweep from Dependency locking; Release policy from Release channels; Full release validation and Update and plugin tests from RELEASING. - help/index: list the Scripts page under Testing. - help/faq-first-run: add the Models FAQ to Related (was one-directional). - reference/credits: replace the two off-topic Related links with the lore and pull-request-review-flow pages. - reference/rich-output-protocol: replace the unrelated RPC adapters link with the Control UI hosted-embeds section that actually renders [embed ...]. - web/lobster: add a Related section. - glossary: 17 append-only zh-CN sources for the new list-item link labels, each inserted beside a related existing term rather than at the end of the array.
6.5 KiB
summary, read_when, title
| summary | read_when | title | ||
|---|---|---|---|---|
| Get OpenClaw installed and run your first chat in minutes. |
|
Getting started |
Install OpenClaw, run onboarding, and chat with your AI assistant in about 5 minutes. By the end you will have a running Gateway, configured auth, and a working chat session.
What you need
- Node.js 24.16+ or 26.1+ (Node 26 is the recommended runtime)
- An existing Claude Code or Codex CLI login, or a provider API key — onboarding can reuse it
Try it in one command
npx openclaw@latest
On a fresh install, choose Quick start after a one-line pointer to the security guide. That is the only onboarding prompt when usable AI access is already available: OpenClaw finds an existing Claude Code or Codex CLI login or API key, verifies it with a real completion, saves the config, and opens the web dashboard.
The Gateway runs in this terminal until you press Ctrl+C; your config stays saved. If no detected route works, onboarding opens manual provider setup. Choose Custom setup to walk through all guided options instead.
To keep the Gateway running in the background later, install the CLI below and
run openclaw gateway install. Run openclaw for the TUI or
openclaw dashboard to reopen the web UI.
Quick setup
```bash curl -fsSL https://openclaw.ai/install.sh | bash ```<Note>
Other install methods (Docker, Nix, npm): [Install](/install).
</Note>
See [Onboarding (CLI)](/start/wizard) for the full reference.
```bash
openclaw gateway install
```
This installs a LaunchAgent on macOS, a systemd user unit on Linux and
WSL2, or a Scheduled Task on native Windows (with a per-user
Startup-folder login item as the fallback if task creation is denied).
Your config stays saved across the stop and the install.
You should see the Gateway listening on port 18789.
This opens the Control UI in your browser. If it loads, everything is working.
Want to chat from your phone instead? The fastest channel to set up is
[Telegram](/channels/telegram) (just a bot token). See [Channels](/channels)
for all options.
mkdir -p "$HOME/.openclaw/control-ui-custom"
# Copy your built static files into that directory.
Then set:
{
"gateway": {
"controlUi": {
"enabled": true,
"root": "${HOME}/.openclaw/control-ui-custom"
}
}
}
Restart the gateway and reopen the dashboard:
openclaw gateway restart
openclaw dashboard
If setup does not work
One command turns the current state of your install into a diagnosis you can act on:
openclaw triage
It runs read-only health checks, writes a sanitized prompt describing what it found, and then offers to hand that prompt to a coding agent it detects on your machine — Claude Code, Codex CLI, or the built-in OpenClaw agent — so the agent starts with the diagnosis already loaded. Pick "just print the commands" if you would rather run the handoff yourself.
Nothing leaves your machine until you choose an agent, and secrets, tokens, raw chat payloads, and raw logs are excluded from the prompt.
To read the findings yourself instead, run openclaw doctor. For symptom-first routes, see Troubleshooting.
What to do next
Discord, Feishu, iMessage, Matrix, Microsoft Teams, Signal, Slack, Telegram, WhatsApp, Zalo, and more. Control who can message your agent. Models, tools, sandbox, and advanced settings. Browser, exec, web search, skills, and plugins. If you run OpenClaw as a service account or want custom paths:OPENCLAW_HOME— home directory for internal path resolutionOPENCLAW_STATE_DIR— override the state directoryOPENCLAW_CONFIG_PATH— override the config file path
Full reference: Environment variables.
Related
- Install overview
- Channels overview
- Setup
- Personal assistant setup - end-to-end guide to a dedicated number that behaves like an always-on assistant
- Triage
- Troubleshooting