Serverless compute · paid in ANM

Run any Python function on a decentralized GPU fleet

Animica Studio is a Modal-style serverless platform for the post-quantum chain. Write a function, add a decorator, and run it on Animica's GPU & CPU fleet — .remote(), .map(), cron, and web endpoints — metered and settled on-chain in ANM. The same rigs that mine and train ANM now run your code.

Open Studio → Read the docs pip install animica

pip install animica

The complete client — mine, run a node, use the wallet, deploy Python contracts, run animica up (the unified miner: PoW + useful-work + GPU train/serve + Studio functions), and use the Studio SDK. The native CPU miner (animica-fastpow) is included by default. This is what most people want.

pip install "animica[all]"

Everything above plus every optional extra: Qt desktop-wallet QR codes, the full distributed Studio client (cloudpickle for closures + omni-sdk for on-chain ANM escrow), and all server/operator dependencies pinned. Use it for the kitchen sink or to run pool/API infrastructure. Quote the brackets so zsh/macOS does not glob them.

import animica.studio as studio

app = studio.App("trainer")

@app.function(image=studio.Image.debian_slim().pip_install("torch"), gpu="A100", timeout=900)
def train(seed: int) -> float:
    import torch
    return float(torch.randn(1024, seed % 8 + 1).mean())

train.remote(42)          # one call on the fleet
train.map(range(128))     # fan-out across providers

From zero to running in three steps

Install

pip install animica

Decorate

@app.function(gpu="A100") def train(seed): ...

Run

train.remote(42) • animica studio run app.py::train

Everything you expect from serverless

@app.function

Decorate any Python function and run it remotely — no servers, no YAML, no Dockerfiles required.

.remote() & .map()

Call a function once on the fleet, or fan out across thousands of inputs with one line.

GPU on demand

Pin A100/H100-class GPUs per function. Pay per second of compute, settled in ANM.

Images in Python

Declare pip/apt deps inline with Image.debian_slim().pip_install(...). Deterministic, content-addressed.

Secrets & Volumes

Inject secrets into a function and mount persistent volumes — no plaintext in your job.

Cron & web endpoints

Schedule functions on a cron, or expose them as HTTP endpoints for your app and agents.

Decentralized fleet

The same rigs that mine and train ANM run your functions — useful work, not wasted hashes.

On-chain settlement

Every run is metered and paid in ANM on a live post-quantum L1. Verifiable in the explorer.

Animica Studio vs. Modal

If you know Modal, you already know Studio — the SDK is intentionally familiar. The difference is where your functions run and how they're paid for.

Decorator-based Python SDK	Animica Studio	Modal
Serverless GPU functions	✓	✓
.remote() / .map() ergonomics	✓	✓
Cron + web endpoints	✓	✓
Pay-per-second billing	ANM (on-chain)	USD (card)
Runs on a decentralized fleet	✓ miners & GPU providers	✗ centralized cloud
Useful-work mining synergy	✓ same rig mines + serves	—
Post-quantum, verifiable settlement	✓	—
Open source	✓ Apache-2.0	partial

Built for AI agents, too

Studio is discoverable and usable by autonomous agents. An llms.txt manifest and an MCP server expose studio_run, studio_deploy, and studio_list tools so an agent can run and deploy compute on its own, paying from a wallet. Point your agent at studio.animica.org/llms.txt .

FAQ

Is Animica Studio a Modal alternative?

Yes. Animica Studio gives you the same decorator-based serverless developer experience as Modal — @app.function, .remote(), .map(), GPUs, images, secrets, cron, and web endpoints — but functions run on Animica's decentralized GPU/CPU fleet and are paid for in ANM on a live post-quantum blockchain.

How do I run a Python function on Animica Studio?

Install the SDK with `pip install animica`, decorate a function with @app.function(), and call train.remote(42) — or run it from the CLI with `animica studio run app.py::train`. In local mode it runs in a sandbox on your machine with zero infrastructure; in remote mode it dispatches to the fleet and settles in ANM.

How is compute priced?

Per second of CPU/GPU time, quoted before each run and escrowed in ANM. Payout is split to the provider, treasury, and miners by the on-chain economics. There are no monthly minimums.

Can AI agents use Animica Studio?

Yes. Studio ships an MCP server and an llms.txt manifest so AI agents can discover the platform and call studio_run / studio_deploy tools to execute and deploy functions autonomously, paying with a wallet.

Prefer the desktop studio?

The Animica Studio desktop app (local contract authoring, simulation, and node-connected workflows) is still available. Grab it from GitHub Releases or Downloads .