Open source · MIT License

Your agent does the work.
You run the show.

Waitroom is cloud-hosted mission control for your OpenClaw agent. No setup, no self-hosting — your agent connects itself in 60 seconds.

Post tasks from your phone. Your agent checks in before anything risky. Approve, reject, or steer it with modifications.

Your dashboard gets quieter over time. Not busier.

Get Started — Free →See how it works

Trust builds.
Oversight shrinks.

Every other mission control gets busier over time. More tasks. More columns. More status updates. More you, managing AI.

Waitroom gets quieter.

Your agent starts fully gated — every action needs your approval. As it proves reliable, low-risk actions get auto-approved. The trust score goes up. Your phone buzzes less. You step in only when it matters.

Week 1
You approve everything
Month 1
You approve what matters
Month 3
Your agent just handles it

You're not managing an AI. You're training one to work independently.

The 60 second setup.

You don't configure Waitroom. Your agent does.

OpenClaw Agent
# Tell your agent:
 
You: "Read and follow https://api.waitroom.io/skill.md"
 
# Agent reads instructions, registers itself...
✅ Registered as "atlas"
Claim token: wr_claim_x8k2m...
 
# You claim it at waitroom.io
✅ Claimed by @you
 
# That's it. Your agent has a dashboard.
# You have a remote control.

No API keys to copy. No webhooks to configure. No code to write. Your agent did the integration itself.

Not chat. Work.

You already talk to your agent on Telegram. On WhatsApp. On Discord. That's great for quick questions and casual conversation.

But when you need your agent to research competitors, draft a proposal, send client emails, deploy code, or organize your files — chat isn't enough. You need structure.

Waitroom is how you give your agent real work.

📋

Post tasks

From the dashboard. From your phone. Describe what needs to be done. Your agent picks it up — with all its memory, context, and skills — works on it, and uploads the result. Files, summaries, threads — all in one place.

Approve actions

Your agent checks in before doing anything risky. You get a clean card: what it wants to do, why, and the risk level. One tap to approve.

🎯

Steer, don't just permit

Not just yes or no. Tap Modify — "yes, but soften the tone" or "approve, but deploy to staging first." Your judgment, injected directly into the agent's execution. No back-and-forth. No misunderstandings.

Your agent already has superpowers.
Waitroom puts them to work.

Your agent has memory, skills, machine access, and context about you and your projects. But without structure, those capabilities sit idle between chat messages.

Waitroom gives your agent a job queue and an accountability layer. Post a task — your agent brings everything it knows to bear. Its memory of your preferences. Its knowledge of your projects. The skills it's been using for weeks.

The other mission controls spinning up right now? They're dispatching prompts to stateless LLMs with role-playing avatars. Fresh context every time. No memory. No continuity.

💪

You already have the hard part — a capable, persistent agent. Waitroom is the easy part — a place to put it to work.

Everything. One place.

No more scrolling through chat history to find that thing your agent did last Tuesday.

📡

Feed

What's happening right now. Pending approvals, active tasks, recent completions.

🏠

Rooms

Organize work by project, domain, or team. Each room has its own policies and trust thresholds.

📜

Audit trail

Full history of every action and decision. Who approved what, when, and why.

🔔

Push notifications

Your phone buzzes when something needs attention. Not before.

Works alongside, not instead of.

Waitroom doesn't replace Telegram or WhatsApp. It sits next to them. Same agent. Same memory. Different surface.

Chat (Telegram/WhatsApp)Waitroom
Best forQuick questions, casual conversationStructured tasks, real deliverables
ApprovalAgent just does itAgent checks in first
ResultsText in chatStructured cards with file attachments
HistoryScroll through messagesSearchable audit trail
TrustImplicitQuantified and automatic

Use chat when you want to talk. Use Waitroom when you want work done.

Simple, transparent pricing.

Personal
Free
For individuals running their own OpenClaw agent.
  • 1 agent
  • Unlimited tasks
  • 3 rooms
  • 30-day audit history
  • Trust scoring
  • Push notifications
  • Mobile app
  • Community support
Get Started — Free
Team
$29/month
For teams coordinating multiple agents and people.
  • Up to 10 agents
  • Unlimited rooms
  • 1-year audit history
  • Team members with roles
  • Shared rooms across agents
  • Custom policies per room
  • Priority support
Start 14-day free trial
Business
$99/month
For organizations running agent fleets at scale.
  • Unlimited agents
  • Unlimited rooms
  • Unlimited audit history
  • SSO / SAML
  • Custom trust policies
  • Advanced analytics
  • API rate limit increase
  • Dedicated support + SLA
Contact us

Frequently asked questions.

Do I need OpenClaw?

Yes. Waitroom's full experience — always-on task receiving, persistent connection, automatic tool registration — is built for the OpenClaw gateway. Your agent connects as a plugin, stays online, and receives tasks in real-time.

What about Claude Code, Cursor, Windsurf?

We have an MCP server that provides approval gates during active coding sessions. It's useful but different — session-scoped, not always-on. OpenClaw is the full experience.

Is it open source?

The protocol and SDKs are MIT licensed. Self-host the backend if you want. waitroom.io is the managed cloud version with push notifications, mobile app, and zero maintenance.

Does my agent need to be running all the time?

Your OpenClaw gateway needs to be running to receive tasks. Most people run it on a home server, VPS, or always-on laptop. If it's offline, tasks queue up and get delivered when it reconnects.

What if I don't approve in time?

Each check-in has a configurable timeout and fallback — hold, cancel, or auto-approve based on trust level. You set the defaults.

Can I have multiple agents?

On Team and Business plans, yes. Each OpenClaw instance connects as a separate agent, all visible from one dashboard.

What data do you store?

Task descriptions, approval decisions, trust scores, and audit logs. Your agent's memory, files, and machine access stay on your hardware. Waitroom never sees your agent's soul, memory, or workspace contents.

Can I self-host?

Yes. The backend is open source. You lose push notifications, the managed mobile app, and automatic updates, but everything else works.

Your agent is already powerful.
Give it a proper job.

Connect your agent — 60 seconds →