While Agents Keep Executing

Your agents now know
how to report back

WAKE is a simple, open standard that tells any AI agent how to surface its work to you — and how to wait for your direction before moving on.

See how it works
✓ Approve
✕ Reject
5 deliveries waiting

You have no idea what your agent did

AI agents work in the background — researching, writing, making decisions. But there's no standard way for them to tell you what they've done, ask for your input, or wait before doing something irreversible. So they either go silent, or they interrupt you constantly.

"The agent just published the draft without asking me first."
"It's been running for four hours. I have no idea what it's doing."
"I told it to pause and it just kept going."
"I found out it had a question three hours ago — it's been stuck waiting ever since."

A shared language between you and your agents

When an agent implements WAKE, it knows exactly when and how to check in with you. When you use a WAKE-compatible inbox, you see everything in one place — and your decisions get back to the agent immediately.

1

Agent completes work

Your agent finishes a task, hits a decision point, or encounters something unexpected. Instead of going silent or blasting you with a notification, it sends a structured delivery — a short headline and summary — to your WAKE inbox.

2

You review on your terms

Deliveries wait for you. You can check in every hour, or every day. The agent keeps working on other things. When you're ready, you see exactly what it did and what it needs from you.

3

You respond — once

You approve, reject, or redirect with optional instructions. That response goes straight back to the agent, which picks up exactly where it left off.

Three things you can tell an agent

approved

Go ahead

Proceed as planned. The agent continues with its original approach.

rejected

Don't do that

Stop. Don't proceed with this. The agent reads your feedback and adjusts.

redirected

Do it differently

Here's how I want you to change course. Your instructions go directly to the agent.

Open. Simple. Already works.

Any agent that can make an HTTP request can implement WAKE in minutes. Any inbox that can serve two endpoints is WAKE-compatible. No vendor lock-in, no new dependencies.

Works with any agent

Claude, ChatGPT, Cursor agents, n8n workflows, custom scripts — if it can make an HTTP request, it can implement WAKE. You share a URL or a prompt and you're done.

Secure by default

Every delivery is signed. Your API key travels in the header, never in the payload. Tampered messages are rejected before they reach you. The agent prompt handles all of this automatically.

Free and open forever

WAKE is an MIT-licensed open protocol. No company owns it. Any tool can implement it. If you switch agents, switch inboxes, or build your own — the protocol travels with you.

Your agents, wherever they run

WAKE doesn't care which AI you use or how your agents are built. If it can follow an instruction, it can implement the protocol.

Claude
Anthropic
ChatGPT
OpenAI
Cursor
Code agents
n8n
Automation
Grok
xAI
Gemini
Google
LangChain
Framework
Your agent
Any HTTP client

GardenRoom is a WAKE inbox, ready to use

WAKE is the protocol. GardenRoom is one place to receive deliveries — a hosted inbox built around the spec. You don't have to use it. But if you want something that works today, it's there.

GardenRoom.ai

A hosted inbox for your WAKE deliveries. One URL, one prompt to your agents, and everything they do comes to you in one place.

  • See every delivery from every agent in one feed
  • Approve, reject, or redirect from your phone or desktop
  • Agents are notified instantly when you respond
  • Self-hostable — run it on your own infrastructure
  • Open source, MIT licence
Visit GardenRoom.ai →

Built in the open.
Owned by no one.

WAKE is a public specification. The schema is stable, versioned, and designed to last. Anyone can build a WAKE-compatible inbox. Anyone can publish a WAKE-compatible agent. The community decides what comes next.