Note: This article is Adapted from the official Phala post.
Open Notebook brings that NotebookLM style research workflow, the kind where you feed in sources and let AI help you organize your thinking, into a self-hosted setup you can actually control. If you’ve used NotebookLM before, you know how useful it is to dump in a pile of documents and have something make sense of them for you. The catch has always been that your documents, your notes, and your questions all end up sitting on someone else’s servers. Open Notebook gives you that same experience without handing everything over.
What makes the Phala version worth paying attention to is where it actually runs. Your sources, your notes, your prompts, and even the app’s internal state stay inside a TEE CVM, which is just a way of saying the whole thing runs in an isolated environment that even the infrastructure provider can’t peek into while it’s active. So you get the convenience of a polished research tool, but without the usual tradeoff of exposing sensitive material to get it.
You can deploy it yourself right now at https://cloud.phala.com/templates/open-notebook, and it’s live in minutes.
You can also check the Template code: https://github.com/Phala-Network/phala-cloud/tree/main/templates/prebuilt/open-notebook
Upstream: https://github.com/lfnovo/open-notebook
For developers building on this, the setup stays familiar, you’re just running it somewhere that doesn’t ask you to trust a third party with your data. For institutions dealing with sensitive research or proprietary documents, that’s often the difference between being able to use a tool like this at all and having to sit it out entirely.
Top comments (0)