LIFEHUBBER
Choose theme

AI Resources

Open Notebook

GitHub stars: 39.6K GitHub forks: 4.6K Declared license: MIT: MIT Last pushed September 27, 2026: Pushed 2d ago
Stats from GitHub

Open Notebook is a self-hosted research workspace for collecting sources, working through questions, and saving what you learn as notes.

It accepts material such as PDFs, web pages, audio, and video, with a choice of local or cloud AI providers. Use this as a first read, not a recommendation. Open the original project before trusting details like terms, limits, privacy, cost, setup, or safety.

What it is

Sources and notes kept together

A notebook holds the material you bring in alongside your own notes and AI-generated outputs. That separates the evidence you collected from the interpretation you are building.

Why it stands out

Two ways to ask about your material

Chat uses context you select for a conversation. Ask searches for relevant passages to answer a question, so you do not have to pick all the sources yourself.

Availability

A web workspace you host

The MIT repository documents Docker Compose setup, a browser interface, and a REST API. Ollama and LM Studio are among the local-model options.

Why it matters

What makes it useful

When a topic spans several documents, keeping another chat history is only part of the work. Open Notebook gives the source collection a home and lets useful outputs become notes that you can return to while developing the research.

Notable points

What stands out

Chat context is adjustable per item: leave it out, include a condensed version, or include the full content. That choice changes what the model receives; importing a document and including all of it in a conversation are different steps.

Before using

What to review

Self-hosting the workspace does not make cloud-model calls local. Provider selection determines where those requests are processed.

The security guide says an encryption key is required for storing provider credentials, and password authentication remains disabled until configured; it directs network-accessible installations to its protection and hardening steps.

The project describes its current design as single-user. Team sharing is a deployment question, not an assumed collaboration feature.

Reader fit

Who may find it relevant

Researchers, students, and independent learners comfortable running a Docker-based application or having someone maintain it. It is most relevant when organizing the material and controlling model choice are worth the setup work.

Editorial note

Why LifeHubber lists it

A saved transformation can extract the research question and limitations from each paper. Keeping those outputs as notes in the same format gives you a starting point for comparison without rewriting the prompt for every paper.

Source links

Source materials

Reader note

Before relying on this entry

LifeHubber lists entries to help readers inspect AI projects, not to endorse them or prove they are safe, suitable, accurate, maintained, or right for a specific use. We do not verify every entry in depth. Before relying on anything listed, review the original materials, terms, privacy practices, limits, and risks that matter for your situation.

What to explore next

Keep the research portable beyond one notebook.

A self-hosted workspace gives you control of the running system, but the source files, notes, model choices, and restart instructions still need a durable home of their own.

Advertisements

Advertisements

For project maintainers

Listed here? You can use the badge.

If you maintain a project with a current LifeHubber listing, you may add the optional “Listed on LifeHubber AI Resources” badge to its README, docs, or website. No introduction or permission request is needed.

See what’s moving