Security & trust

Is it safe to let agents near your AWS?

You should ask. Handing an app — or an AI agent — the keys to your cloud is exactly the kind of thing you should be nervous about. So here's the straight version, not a slogan: the dangerous setup you're picturing is the one AgentsPoppy exists to replace.

What you're picturing

An agent holding your keys

A script or an AI with a broad, long-lived AWS access key. Free to touch anything, in any region, with no one watching. If it goes wrong, you find out from the bill.

You're right to refuse this.

What AgentsPoppy is

A broker that stands in between

A local gatekeeper between the agent and your cloud. It hands out only narrow, short-lived, revocable access — and shows you every change as it happens.

The agent never even sees your keys.

You already trust this model — it's called OAuth

Before OAuth, an app that wanted your email asked for your password. Today, an app or AI agent that wants to help with your cloud asks for your access keys — the same disease, one layer down. AgentsPoppy is that missing authorization layer, rebuilt for infrastructure.

OAuth · 2007 Your password stays at the identity provider — apps never see it.
AgentsPoppy · now Your cloud keys stay on your machine — poppies never see them.
OAuth · 2007 Apps request scopes; you consent on one screen.
AgentsPoppy · now Poppies declare a permission manifest; you approve it, risk-rated.
OAuth · 2007 Short-lived, revocable access tokens.
AgentsPoppy · now Scoped session credentials that expire in about an hour.
OAuth · 2007 Revoke one app without touching the rest.
AgentsPoppy · now Revoke one poppy — its access dies instantly.

// where the analogy breaks

OAuth governs access to things that already exist. A poppy creates infrastructure — and OAuth has no idea what an app created, or how to undo it. AgentsPoppy does: every resource a poppy makes automatically carries the poppy's identity, and its permissions only ever cover resources carrying that identity. That's why everything a poppy builds is attributed, provable, and removable in one click. Revoking access is table stakes; being able to undo the app is the invention.

What an agent behind AgentsPoppy can — and cannot — do

Not a promise in a privacy policy. A boundary enforced by AWS itself, the same Allow/Deny model your own IAM already runs on.

Six things that are true no matter which agent you run

Each one is structural — enforced by the system, not left to good intentions.

Scoped ENFORCED

Narrowed to its own box

Each agent's credentials are limited to its own resources. Outside that box, access is denied — by AWS, not by our word.

Short-lived ENFORCED

Temporary, minted per task

Access expires in about an hour and is issued on demand. No standing admin key sits on your disk waiting to leak.

Contained ENFORCED

Can't escalate or hide

Hard guardrails deny the dangerous moves. Even a bad actor can't gain more power than you granted, or take the keys away from you.

Legible

You can actually see it

One plain-language view of every change and who made it, across every region — the thing the AWS console makes nearly impossible.

Reversible

One click, cleanly gone

Tear an agent's whole footprint back down in a click. No orphaned resources, no surprise bills next month.

Local-first & open

Nothing leaves your machine

Your keys stay local, held by a broker on your computer. Nothing travels to agentspoppy.com. The code is open — verify all of this yourself.

The questions everyone asks first

Q.“Is it secure to run agents on my computer?”

An agent is only as dangerous as what it can reach. Left alone with your AWS keys, very. Behind AgentsPoppy, its reach is a small box you defined and can revoke instantly — and it never sees your real keys; it asks the local broker for scoped, temporary access each time. AgentsPoppy takes the scary version off the table.

Q.“Isn't it safer to just keep using the AWS CLI and console?”

If you personally run every command with a tightly-scoped, temporary credential and read the logs afterward — keep doing it; AgentsPoppy doesn't replace that. But that's not the real comparison. The real one is the moment you want an app or an agent to do the work for you. The usual answer there is “give it a broad key and hope.” AgentsPoppy replaces that one moment with something scoped, watched, and reversible. It isn't a substitute for your judgment — it's a safer set of hands for the work you'd otherwise delegate blind.

Q.“Why add a new app that could endanger my AWS?”

Fair — more software is more surface, and we won't pretend otherwise. So the app has to earn its place: it only holds access on your machine (never our servers), it can't do anything to your account you didn't scope, it can't escalate or hide, and it's open for you to audit. The risk it removes — an agent loose in your cloud with a broad key — is far larger than the risk it adds.

// safe sourcing

Belt and braces: the guardrails above hold for any poppy you run — but the two paths that ask for no faith at all are to run a poppy you built yourself (below), or one whose source is public, so you or the community can read exactly what it does with the access you grant it. Prefer those over an anonymous, unverified download.

// straight talk

What we won't tell you

  • That any software is unbreakable. None is, and anyone who says so is selling something. Our job is to shrink what can go wrong and make sure you see it — not to promise nothing ever will.
  • That it replaces good AWS hygiene. Your keys, your machine, and your judgment still matter. AgentsPoppy raises the floor; it doesn't remove your responsibility.
  • That it's magic. It's a careful, auditable layer that enforces least privilege and shows you the truth. Boring is the point.

The safest path of all

The poppy you trust most is the one you built.

The guardrails above hold for any poppy you run. But you don't have to download a stranger's code at all: AgentsPoppy was built for vibe-coding your own infrastructure. Point your AI agent at the guides and it can build you a polished, compliant poppy — no cloud expertise required on your side. An afternoon to a few days, not a project.

  • 01
    Written for your AI. The build guide, the SDK, and the design kit are structured for a coding agent to follow end to end — and to keep you inside the security rules automatically.
  • 02
    One paste to start. A boilerplate starter prompt gets your agent scaffolding immediately, from a working example.
  • 03
    Yours to keep or share. Private, for your own infrastructure — or distribute and even monetise it as the poppy ecosystem opens up.

The build guide and a copy-paste starter prompt open when AgentsPoppy’s code goes public — then your agent has everything it needs.

Prefer to verify first? Don't take our word for it —

the architecture docs and full source open the moment the repo goes public — so you can check every claim on this page, line by line.