Love NotebookLM but hate Google? Try this open source alternative

Open Notebook is effectively a clone of NotebookLLM’s core functionality, including audio summaries, the ability to ask questions about your research sources, and more. Of course, nothing is perfect and not without a catch. Below, I’ll start with what I love about Open Notebook, its less-than-ideal aspects, and how to try it out for yourself.

The main features are almost the same as NotebookLLM. You upload resources from PDFs to YouTube videos and everything in between, and then it synthesizes that information into audio, quizzes, or you can just chat with it.

Let’s start with what really makes Open Notebook different from NotebookLLM: it’s an open source project, you have to configure it yourself. This comes with some downsides, which we’ll get to in a bit. It also means that your data is truly secure in a way that NotebookLLM is not. You even have more flexibility and customization options than Google offers.

You can run Open Notebook natively using a model like Ollama, or use it as a GPT, Gemini Pro, Opus, etc. you can connect to your favorite cloud-based AI models including It’s also fairly easy to switch between models, so you don’t have to lock in just one option here either.

Even better, there’s no limit to the number of notebooks you create, as well as how many resources you use. Meanwhile, the free version of NotebookLM limits you to 100 notebooks with no more than 50 resources each. That said, using Open Notebook will still burn token limits if you’re using a cloud-based model, so it’s worth keeping that in mind.

As much as I like Open Notebook, it’s important to talk about its downsides upfront.

First, it’s not a plug-and-play experience by any stretch of the imagination. Even though I’m a pretty seasoned computer geek with decades of experience, manually installing Open Notebook on my Chromebook was a pain to say the least. It took me two tries and several hours to set it up this way. Thanks to the Docker Desktop app, this was easier on Windows, being set up in half an hour or so, but it still required a bit of DIY knowledge and troubleshooting to get things right.

Let’s also talk about his audio summary podcasts. While I appreciate that you can actually have four speaking voices instead of the two-voice option with NotebookLLM, the audio cuts are shorter by default. Instead of the 8-15 minute limit you’d get with NotebookLM, audio degradation is usually closer to a few minutes.

You can customize this and increase the length to 30 minutes or more, but even so, I found the quality of the podcast not to be as sharp. I’ve used a few different models and even then I feel that NotebookLM crashes a bit more strongly.

You’ll also need the service running through a host computer or your own cloud setup before using it on other devices, such as Android. However, since there is no native software, you will have to use a web browser.

As I said before, installing Open Notebook can be a bit tricky but the easiest way is to install Docker Desktop, This allows you to run containerized applications directly without using much of a command line interface.

After launching the app, you may want to obtain an API key from your chosen provider. The exact process for this will vary.

Although there is an official getting started guide for this process, it is important to note that it is actually outdated in several areas. For those planning to install the cloud model, the following steps walk you through the basic initial setup.

Start by creating a configuration file. You’ll want to open something like Notepad and paste the following:

services:
surrealdb:
image: surrealdb/surrealdb:v2
command: start – user root – pass password – shutdown 0.0.0.0:8000 rocksdb:/mydata/mydatabase.db
ports:
– “8000:8000”
Volumes:
– ./surreal_data:/mydata
# Removed sanity check because the v2 image is too minimal to run wget/curl
restart: always

open_notebook:
image: lfnovo/open_notebook:v1-latest
pull_policy: always
ports:
– “8502:8502” # Web UI
– “5055:5055” # API
environment:
– OPEN_NOTEBOOK_ENCRYPTION_KEY=replace me with secret string
– SURREAL_URL=ws://surrealdb:8000/rpc
– SURREAL_USER=root
– SURREAL_PASSWORD=password
– SURREAL_NAMESPACE=open_notebook
– SURREAL_DATABASE=open_notebook
Volumes:
– ./notebook_data:/app/data
depends on:
– surrealdb
restart: always

Once you’ve created the file, you’ll want to edit it change-me-to-hidden-line and replace it with the phrase of your choice. You will then save the file as docker-compose.yml under a new folder called Open the notebook.

Next, you’ll want to launch Docker Desktop. Once ready, open File Explorer and navigate to the Open Notebook folder where you placed the configuration file. Right-click anywhere in the window and select Open it in Terminal.

A terminal window will open and you will be prompted to enter: docker compile -d

After about 15 seconds, the services will start and you will be able to access Open Notebook in your browser. http://localhost:8502 to the address bar. The Open Notebook UI should open, but you’re not done yet.

you will want to go Manage > Models, Find your preferred AI company in the list and click on it Add configuration button. A new box will open asking you to enter a name for your configuration and API Key. After adding both, click on it Add configuration button.

You will notice a Test at this point click the button next to your new configuration. Click this button to test the connection. You should also specify which model you want to use for chat, placement, and transformations. The last of these options includes reflections, table of contents, audio summaries, etc. refers to the process used to create

Once all this is done, you should be down to business. Then you can go New tab and create a new Notebook. From here, just add resources and try out all its Transformation capabilities. However, you still need to configure your Podcast settings and a few other things. I won’t go into all these details for brevity, but you can find more here Open the Notebook startup guide.

So is Open Notebook better than NotebookLM? Honestly, the answer depends on your needs and how much you’re willing to play with the settings to get it to your liking. Open Notebook may certainly be worth the effort for those who like the idea of ​​NotebookLM but don’t like having their data on Google’s servers. The same is true for those who like the tool but prefer a model that is not based on Gemini technology.

For everyone else, NotebookLM remains a fairly good performer that’s easy to get started with and can be made even better with a NotebookLM Pro or Plus upgrade. But if you don’t mind some tweaks, Open Notebook is totally worth a shot.