Palapa!

Turn your idle device into an AI server, or tap into a global network of shared GPU power to run AI models beyond what your hardware can handle alone

Palapa is a cooperative network that turns everyday idle computing power into a shared resource for running AI models.

Millions of devices — laptops, desktops, phones, and tablets — sit idle for most of the day. Palapa lets you contribute that unused capacity to a shared network, and in return, access AI models far larger than your own device could run on its own.

HOW IT WORKS

Palapa operates in three ways, and you can use any combination that fits your device:

• AI Server — Run AI models directly on your device and serve requests from other members when you’re not using it. On Mac, Windows, and Linux, this can include large, powerful models. On iPhone, iPad, and Apple TV, it runs efficient models suited to mobile hardware using Apple’s MLX framework.

• Companion App — Manage your account, monitor your devices, and access the network from your phone without running inference locally.

• Developer Access — Point any OpenAI-compatible tool or app directly at Palapa’s API to integrate large-scale AI inference into your own projects.

WHAT YOU CAN DO

• Run AI models locally on your device and contribute spare capacity to the network • Access models larger than your device could run on its own • Choose your privacy level for every request: keep inference entirely on your own devices, route only to trusted friends, or open it to the wider network • Connect with friends and groups and message within the app • Use Palapa as a drop-in replacement for other AI API providers in your own tools and workflows

PRIVACY BY DESIGN

You control where your requests are processed. Self-only mode keeps everything on your own devices. Friends mode routes only to people you trust. Open mode reaches the full network for the widest model selection. Nodes don’t store your data beyond the life of each request.

BUILT FOR EVERYONE

Whether you’re an individual developer looking to escape per-request API costs, part of the open-source AI community, or just have a device that’s idle most of the day, Palapa gives you a way to put spare compute to work and get more out of AI in return.