Skip to content
Now in early access — be first in line

The build system for AI generation.

Atlas is Git + Make for AI image and video. Content-addressed, so you never pay to render the same frame twice. Resumable, so a dead GPU never costs you progress. Budget-gated, so you always know the price before you spend it.

See how it works ✦ No spam. One email when it's your turn.
Open source Apache-2.0 Runs 100% local Your tokens never leave your machine Works with Replicate & any plugin
Three promises

Generation that behaves like engineering.

The three ways AI pipelines quietly burn your time and money — solved at the kernel, not bolted on.

Never re-render the same work

Every recipe is content-addressed — identical inputs hash identically. Atlas serves the cached artifact instead of paying for it twice. Caching is structural, not optional.

Never lose work to a kill

Runs are journaled and resumable. A dead RunPod, a killed process, a crashed laptop — atl resume picks up exactly where it stopped. Completed work stays done.

Know the cost first

Paid work refuses to run without a budget envelope covering it. atl plan shows the price before a single API call fires. No surprise invoices, ever.

How it works

Author intent.
Atlas handles the rest.

1

Describe the work as recipes

Text-to-image, image-to-video, compositing — a graph of content-addressed recipes, by hand or from the Python Director's DSL.

2

Set a budget, see the plan

Open an envelope, run atl plan. You get the exact task list and a P90 cost estimate before anything spends.

3

Render — cached, resumable, accountable

Atlas runs only what's missing and records every artifact's model, seed, cost and license in a provenance ledger.

4

Change one thing, re-render only what's dirty

Bump a character design; atl dirty lists exactly which shots fell behind — and what fixing them costs. The rest stay cached.

$0.00
to re-render unchanged work — it's cached
100%
local — no telemetry, tokens stay on your machine
1
binary to install — no account, no daemon
Pricing

Free to start. Fair as you grow.

The core CLI is free and open source, forever. Pay only when Atlas is doing real work for a real team.

Core
$0
The open-source CLI. Everything you need to build, cache and ship.
  • Full render engine & cache
  • Resumable, budget-gated runs
  • Replicate API bridge
  • Python Director's DSL
  • Community support
Team
$49/mo
Shared canon, self-host license and support for a studio.
  • Everything in Pro
  • Self-host commercial license
  • Up to 10 seats
  • Private plugin registry
  • SLA support
Cloud Soon
Managed Atlas: run renders on our infrastructure, no GPU wrangling.
  • Hosted, resumable renders
  • Usage-based billing
  • Team dashboards
  • In development
FAQ

Questions, answered.

Is Atlas really free?

Yes. The Core CLI is Apache-2.0 licensed and free forever. You only pay for Pro features, a commercial self-host license, or (later) managed Cloud rendering. You always pay your model provider — e.g. Replicate — directly for generation.

Does my API token or artwork ever touch your servers?

No. Atlas runs entirely on your machine. Your provider tokens are read from environment variables and never written to disk, logs, or any server, and never transmitted to us. Plugins run as sandboxed subprocesses with a filtered environment.

Which models and providers are supported?

The first release ships a Replicate bridge for text-to-image and image-to-video. The plugin protocol is open and versioned, so any provider can be added — the Pro plan bundles additional premium bridges.

When can I use it?

We're in early access now. Grab a spot above and we'll email you the moment your invite is ready — and nothing else.

Can I use Atlas commercially?

Yes. Core is Apache-2.0 (commercial use permitted). Pro and Team add commercial support and a self-host license for organizations that need one.

Stop paying twice for the same frame.

Join early access and be first to render with Atlas.

Explore the features