Deployments — Layer 03

Ship agents like pods. coming

An agent should be something you ship, not something you babysit. Deployments — the third layer of the platform — will turn an agent into a deployable unit: run one, or run a fleet of them, without owning any of the plumbing underneath. It's coming. The layers beneath it are further along — one is live today.

The idea[01/02]

Deploy the agent, not the infrastructure.

The whole vision fits in three cells. Everything on this page is future tense — this is where the platform is headed, not a spec sheet.

01

Ship it like a pod

An agent becomes a deployable unit. The loop, the tools, the configuration — one thing you'll ship and start, not a process you'll babysit.

02

Run it as a fleet

One agent or fifty — the same motion. Starting the fiftieth will feel exactly like starting the first, and the fleet will be something you glance at, not something you operate.

03

None of the plumbing

The plumbing underneath will be ours to run. You'll own the agent and what it does; everything it stands on will be our job.

The ladder[02/02]

It stands on layers you can use today.

Deployments don't float. They stand on the Agent Runtime, which stands on Inference — Layer 03 of the same platform, read top to bottom.

The bottom of the ladder is live today. Start there — when the layers above arrive, they'll meet you where you already are.

Put your agent on real infrastructure

Your agent doesn't change.
Everything underneath does.

$export ANTHROPIC_BASE_URL=https://api.layerx1.in

Start free · no card · Starter from $5/mo