Notedeck

Your materials.
Your AI tutor.
Your knowledge graph.

Notedeck ingests your books, papers, and notes — then teaches you from them, quizzes you on them, and shows you the structure between them.

Multi-format ingestion Per-KB knowledge graph Real-time AI tutor Cross-library analysis Study wiki

See it in action

From your material to mastery — a 2-minute tour

Real product footage: knowledge graph, question bank, cross-bank analysis, and the AI classroom.

Flagship · AI Tutor

An AI that teaches you
from your own materials.

Real-time slides, narrated lessons, raise-your-hand interruptions — all generated from what you've uploaded. Not a curriculum. Yours.

Generating from Atkins · ch 22 Your lecture 12 notes 2 prior lessons notedeck-tutor-v0.1
Slide 04 · Reaction kinetics · auto-generated 0.4s ago

The Arrhenius equation, in plain words.

k = A · e−Ea/RT
  • Rate depends on temperature exponentially.
  • Eₐ is the energy hill molecules must clear.
  • Higher T gives more molecules the energy to clear it.
  • This is why your reaction sped up so much when you heated it.
04 / 11
Atkins · ch 22
N
Notedeck Tutor notedeck-v0.1
Live · narrating
~ 142 tok/s
"…so the rate constant doesn't just rise linearly with temperature. It rises exponentially. The 'e' to the minus Eₐ/RT term is where the magic is. Think of it as a probability distribution: at any given temperature, only some fraction of the molecules…"
AI suggestions · based on this slide
Re-explain with a real-world analogy
Why does the activation energy matter?
Show me the derivation
Or type your own question…
Replay this slide Explain another way Go deeper here Skip ahead Save lesson notes
Advanced · Cross-library

Pull several libraries
into one view.

Once you have more than one knowledge base, Notedeck holds them side by side — finding bridges between fields, contradictions between sources, ideas one library is hiding from the other.

CFA L2 · 142 nodes
Behavioral fin. · 89 nodes
Personal notes · 36 nodes
↔ Risk perception
↔ Heuristics & bias
Vibe Learning

One memory that spans every session.

Under everything sits a holistic memory — one per knowledge domain, shared by the AI tutor, your document chats, and analysis. It extracts what landed and what tripped you up from each interaction, recalls what is relevant, and tunes explanation depth to you. Long-term, cross-channel, and personal — the way Claude Code remembers a codebase, Notedeck remembers how you learn. Generic AI chat forgets you every session; this is vibe learning.

One memory, every feature

The same per-domain memory powers the tutor, document chat, and cross-library analysis — not a fresh blank context each time.

It learns what you learned

Every session is mined for what you grasped and where you stumbled, then recalled by relevance when it matters.

Adapts to your depth

It reads your signals and meets you where you are, so the next lesson starts where you actually left off.

Study Wiki

Your scattered Q&A, organized into a living wiki.

After chatting across the tutor and your documents, the answers scatter into endless scroll-back. The Study Wiki is the human-readable face of your memory: an LLM keeps weaving your Q&A into structured, interlinked knowledge pages — grouped by domain (physics, finance, work…), built only from what you actually asked, never scraped from the source files. The systematic record a chat with ChatGPT or Claude never leaves behind.

Study wiki

Physics · Electromagnetism
Update my wiki
  • Faraday’s law of induction
    Why a changing flux drives an EMF — including the sign that tripped you up.
    from 4 questions
  • Lenz’s law & where the energy goes
    The direction of the induced current, and the work that pays for it.
    from 2 questions
  • RL circuits: the time constant
    Why current ramps instead of jumping, and what τ = L/R really means.
    from 3 questions

Compiled from your Q&A — not your source files

Only from your Q&A

Built from what you asked, never scraped from the uploaded files — it mirrors your thinking, not the source.

Organized by domain

Questions scattered across sessions become coherent, interlinked pages, one knowledge domain at a time.

A projection of your memory

It is the browsable face of the same memory that drives the tutor — one click keeps it fresh.

FAQ

FAQ

What is Notedeck?

Notedeck is an AI workbench that turns books, papers, and notes you bring in into a knowledge graph you can chat with, learn from, and quiz yourself on.

How is Notedeck different from ChatGPT?

ChatGPT answers from its training data. Notedeck answers from YOUR materials — your textbooks, papers, lecture notes — and shows you where each answer came from. It also builds a knowledge graph across all your documents so you can see how concepts connect.

How is Notedeck different from NotebookLM?

Notedeck adds an AI tutor that quizzes you, a knowledge graph that spans all your uploaded documents (not just one notebook), and explicit spaced-repetition learning workflows. NotebookLM is a great Q&A tool over a single notebook; Notedeck is a workbench for a whole personal library.

What file types can I upload?

PDF, DOCX, PPTX, EPUB, plain text, and Markdown. Images and scanned PDFs are processed with vision models for text and diagrams.

Do you train AI models on my uploaded materials?

No. Your materials are used only to answer your own questions and build your own knowledge graph. We never use them to train base models.

Is there a free tier?

Yes. The Free tier covers your first 1 GB of storage, ~ 100 documents, and unmetered chat and learning sessions on those documents.

Which languages does Notedeck support?

The product UI ships in English and Chinese today, with translations for Japanese, Korean, French, German, Spanish, Brazilian Portuguese, Turkish, Italian, and Arabic rolling out. AI answers and document understanding work in any major language regardless of UI language.

Can I export my data?

Yes. Documents are downloadable in their original format at any time. Notes, annotations, and quiz history export as JSON or Markdown.

How does pricing work?

Free tier, Pro tier (USD 20/month or 192/year) for higher storage and advanced features, and Max tier (USD 50/month or 480/year) for power users. See the Pricing page for full details.

Where is my data stored?

United States. Cross-border transfer disclosures and data processing details are in our Privacy Policy.