> ## Documentation Index > Fetch the complete documentation index at: https://docs.postqueen.ai/llms.txt > Use this file to discover all available pages before exploring further. # OpenClaw > Turn your chat apps into her front door with the OpenClaw agent client OpenClaw bridging WhatsApp, Telegram, Slack and Discord to the postqueen CLI on your own machine ## What OpenClaw is OpenClaw is an open-source agent client from another project, running on your own machine. Install it and the chat apps you already use become a way to reach her: WhatsApp and Telegram on your phone, Slack and Discord with your team. You message her like any other contact, and OpenClaw does the relaying. A voice note to OpenClaw: PostQueen generates the visual and schedules the posts Behind the scenes, OpenClaw drives the same `postqueen` CLI that other agents use. That matters: whatever you ask for through chat lands on the same PostQueen calendar you see at [app.postqueen.ai](https://app.postqueen.ai), where you can review, edit, or delete it. The PostQueen mobile app is on the way. You are not waiting on it, though: through OpenClaw she already answers on the phone in your pocket. ## What you need * A machine that can run OpenClaw: macOS, Linux, or Windows, with Node.js 22.22.3+, 24.15+ or 25.9+ (the OpenClaw docs default to Node 24) * An API key for a model provider such as Anthropic or OpenAI, which OpenClaw asks for during onboarding * The PostQueen skill, which teaches OpenClaw her full command set * Your `POSTQUEEN_API_KEY` * `POSTQUEEN_API_URL`, only if you self-host PostQueen ## Setup On macOS or Linux: ```bash theme={"system"} curl -fsSL https://openclaw.ai/install.sh | bash ``` On Windows, in PowerShell: ```powershell theme={"system"} iwr -useb https://openclaw.ai/install.ps1 | iex ``` Then run the onboarding wizard. It walks you through choosing a model provider, setting that provider's API key, and starting the Gateway, which is the always-on process that connects your chat apps to the agent: ```bash theme={"system"} openclaw onboard --install-daemon ``` OpenClaw is a separate project with its own documentation. Install troubleshooting and other routes such as Docker: [OpenClaw getting-started guide](https://docs.openclaw.ai/start/getting-started). ```bash theme={"system"} npx skills add GkhanKINAY/postqueen-agent ``` The skill gives OpenClaw her complete command reference and the patterns behind it, so it works from documented commands instead of guessing. If the `postqueen` CLI is not already on the machine, install it too: ```bash theme={"system"} npm install -g postqueen ``` Your key lives in the app at [app.postqueen.ai](https://app.postqueen.ai): open **Settings > Developers > Public API** and click **Reveal**. Then export it in the environment the OpenClaw Gateway runs in: ```bash theme={"system"} export POSTQUEEN_API_KEY="your-api-key" ``` Self-hosting PostQueen? Point the CLI at your backend URL, the same value as `NEXT_PUBLIC_BACKEND_URL`. Most single-domain setups serve the backend under `/api`: ```bash theme={"system"} export POSTQUEEN_API_URL="https://postqueen.example.com/api" ``` ```bash theme={"system"} postqueen integrations:list ``` A JSON list of your connected channels means she is ready. You can also run `postqueen auth:status` to confirm your credentials are valid. Now connect the app you want to reach her from. Telegram ships with the core OpenClaw install and only needs a bot token. WhatsApp, Slack, and Discord are official OpenClaw plugins: ```bash theme={"system"} openclaw plugins install @openclaw/ ``` You can also let OpenClaw do it for you: `openclaw channels add` installs the plugin on demand and starts the channel's setup flow. WhatsApp pairs by scanning a QR code, while Slack and Discord connect through a bot you add to your workspace or server. Restart the Gateway after installing a plugin. Each channel has its own walkthrough in the [OpenClaw channel docs](https://docs.openclaw.ai/channels). Once linked, send her a first message and watch the post land on your calendar. ## Talking to her 👑 Message her the way you would message a colleague. Plain text works, and so does a voice note if your assistant supports voice: speak an idea on your walk and find it waiting on the calendar as finished posts. She answers in your pocket: you ask in the OpenClaw chat for today's podcast to go to X and LinkedIn at 5pm, and she replies that two posts are scheduled and waiting on your calendar Try saying: > "Plan a month of content for our coffee shop and fill the calendar." > "Take this photo of today's special and put it on Instagram at lunchtime." > "We just hit 10k followers, write a warm thank-you post for all our channels." She writes the copy and schedules it across your connected channels, from one chat message. ## Run her on a schedule She does not have to wait for your message. The OpenClaw Gateway includes a scheduler, so you can give the agent a recurring job and let it drive the `postqueen` CLI while you sleep. A job is created with `openclaw cron add`: you pass a cron expression and a prompt, and the Gateway runs that prompt on schedule. Here is a weekday morning run that reviews yesterday and preps today: ```bash theme={"system"} openclaw cron add \ --name "Morning content run" \ --cron "0 7 * * 1-5" \ --session isolated \ --announce \ --message "Run 'postqueen integrations:list' to get my channel ids. Check yesterday's numbers with 'postqueen analytics:platform' for each channel, then draft one post for today and schedule it for noon with 'postqueen posts:create'." ``` The `--session isolated` flag runs the job in its own session, and `--announce` has the agent report the result back to your chat. OpenClaw also has a heartbeat, a periodic check-in the Gateway runs per agent; the OpenClaw docs recommend cron jobs like the one above when you want precise timing. Cron jobs are documented in the [OpenClaw scheduled tasks guide](https://docs.openclaw.ai/automation/cron-jobs), and heartbeat has its own [heartbeat page](https://docs.openclaw.ai/gateway/heartbeat). Add `-t draft` to the `posts:create` command in your prompt and the overnight run stacks up drafts instead of scheduled posts. You publish them from the calendar over coffee. ## Staying in control Drafts, edits and deletes work the same as anywhere else in PostQueen. Ask for drafts in your message and each post sits on the calendar unscheduled until you publish it. How control works: [she runs on your terms](/agents/overview#she-runs-on-your-terms). ## FAQ No. She works on her own through the dashboard, CLI, and API. OpenClaw is one of several ways to automate her, and the one to pick when you want to reach her from a chat app. Everything the CLI can do. She can list your channels and schedule posts, upload media for you, and pull analytics afterwards, all with JSON output the agent can parse. Yes. Ask for drafts in your message and each post sits on the calendar unscheduled until you publish it there. No. Agent access uses the same API key and plan limits as your regular PostQueen account, on any plan. OpenClaw itself is open source; the only outside cost is whatever model provider you run it with. ## Learn more Every way to put an agent in front of PostQueen, from coding assistants to chat apps. The `postqueen` CLI that OpenClaw drives: installation, authentication, and the full command set.