NotebookLlama
An open-source NotebookLM alternative with a local browser interface, MIT license, and cloud services through LlamaCloud, OpenAI and ElevenLabs.
NotebookLlama is a self-hosted NotebookLM alternative for people who want to work with documents through an app they can host and modify. Its browser interface runs locally, while LlamaCloud provides document extraction and indexing. It requires cloud services.
The app includes document chat and a multi-page Streamlit interface. It's written in Python and released under the MIT license, so you can inspect the code and adapt it to your own document workflows. The supplied setup covers macOS, Linux and Windows, with Postgres and Jaeger running in Docker containers.
Hosting the interface yourself doesn't keep all processing on your machine. NotebookLlama requires API keys for LlamaCloud, OpenAI and ElevenLabs, so it needs internet access and accounts with those providers. It's a fit for readers who want control over the application code and hosting while accepting a cloud-backed document workflow.
LlamaCloud supports North American and European regions. The default indexing pipeline uses OpenAI's text-embedding-3-small model, and the app also allows custom embedding models. Its backend includes an MCP server, and Jaeger provides an observability dashboard.
