The fastest way to fork and deploy open-source AI.

Runpod Hub is a centralized catalog of preconfigured AI repositories that you can browse, deploy, and share. All repos are optimized for Runpod’s Serverless infrastructure, so you can go from discovery to a running endpoint in minutes.

No—the Hub is currently in beta. We’re actively adding features and fixing bugs. Join our Discord if you’d like to give feedback or report issues.

One-click deployment: All Hub repos come with prebuilt Docker images and Serverless handlers. You don’t have to write Dockerfiles or manage dependencies.

Configuration UI: We expose common parameters (environment variables, model paths, precision settings, etc.) so you can tweak a repo without touching code.

Built-in testing: Every repo in the Hub has automated build-and-test pipelines. You can trust that the code runs properly on Runpod before you click “Deploy.”

Save time: Instead of cloning a repo, installing dependencies, and debugging runtime issues, you can launch a vetted endpoint in minutes.

End users/Developers: Quickly find and run popular AI models (LLMs, Stable Diffusion, OCR, etc.) without setup headaches. Customize inputs via a simple form instead of editing code.

Hub creators: Showcase your open-source work to the Runpod community. Every new GitHub release triggers an automated build/test cycle in our pipeline, ensuring your repo stays up to date.

Enterprises/Teams: Adopt standardized, production-ready AI endpoints without reinventing infrastructure. Onboard developers faster by pointing them to Hub listings rather than internal deployment docs.

In the Runpod console, go to the Hub page.

Browse or search for a repo that matches your needs.

Click on the repo to view details—check hardware requirements (CPU vs. GPU, disk size) and any exposed configuration options.

Click Deploy (or choose an older version via the dropdown).

Click Create Endpoint. Within minutes, you’ll have a live Serverless endpoint you can call via API.

For a more details, check out the docs: https://docs.runpod.io/hub/overview

Prepare a working Serverless implementation in your GitHub repo. You’ll need a handler.py (or equivalent), a Dockerfile, and a README.md.

Add a .runpod/hub.json file with metadata (title, description, category, hardware settings, environment variables, presets).

Add a .runpod/tests.json file that defines one or more test cases to exercise your endpoint (each test should return HTTP 200).

Create a GitHub Release (the Hub indexes releases rather than commits).

In the RunPod console, go to the Hub and click Get Started under “Add your repo.” Enter your GitHub URL and follow the prompts.

Once submitted, our build pipeline will automatically scan, build, and test your repo. After it passes, our team will manually review it. If approved, your repo appears live in the Hub.

For a more details, check out the docs: https://docs.runpod.io/hub/publishing-guide.