01
Encode
A new card surfaces. You make the hook in your own words; Hebbr refines it and saves it with the card.
Built on memory science
Built to remember.
Hebbr is a memory-science study app. The techniques that feel like learning usually are not — Hebbr uses the ones that are: encode, retrieve, teach back, and space, each walked by an AI partner.
See how it worksThe science
Built on how memory actually works.
02
Retrieve
When a card comes due, recall it cold. Hebbr grades the answer, explains what you missed, and moves on.
03
Teach-back
Explain the concept to Hebbr as if it were the student. The gaps surface while you teach.
04
Space
FSRS schedules the next touch for the moment before forgetting. You do not pick when to review.
Your AI study partner
One AI. Three roles. The loop picks.
The best way to learn something depends on where you are with it: a tutor when you are stuck, a student when you think you have it, and a peer when you want to think out loud.
Tutor
Explains what you do not get.
“Think of FSRS as a weather forecast for your memory — let me show you why that matters here.”
Elaborative interrogation
Protégé
Learns from you on purpose.
“Wait, so spaced repetition works because forgetting is good? Can you say that part again?”
The Feynman technique
Peer
Thinks alongside you as an equal.
“I keep mixing up SM-2 and FSRS — want to trade: you take the first, I will take the second?”
Socratic dialogue
From topic to deck
Three steps to a deck you can trust.
01
Describe what you want to learn
Drop a PDF, paste a URL or YouTube link, or type a topic. Hebbr proposes a deck or course plan grounded in sources, not guesses.
02
Generate cards you can trust
Claude drafts the deck, a second pass fact-checks every card, and flagged cards arrive with suggested fixes.
03
Hand it to the loop
Your deck drops into the four-phase study loop. Hebbr schedules each card and runs an AI partner through every session.
The evidence
Every phase, a principle behind it.
Spaced repetition, active recall, elaborative encoding, metacognitive calibration, generation, pre-testing, desirable difficulty, dual coding, interleaving, and the protégé effect all show up in the product loop.
Spaced repetition
FSRS predicts when a card is about to slip and schedules the next review there.
Active recall
Practice Review and Practice Exam force retrieval instead of passive recognition.
Generation effect
Teaching, guessing, and explaining require you to produce the answer yourself.
Dual coding
Visual mnemonics pair with written hooks so facts have more than one route back.
Father of neuropsychology
Donald O. Hebb
1904–1985 · McGill University
“Cells that fire together, wire together.”
About the name
Named for Donald Hebb.
In 1949, Donald Hebb described the rule behind modern neuroscience: when two neurons fire together, the connection between them strengthens. That principle — Hebbian learning — is the biological reason memory sticks.
Hebb's rule also seeded artificial intelligence, including associative-memory neural networks. The same rule that wires your memories helped shape the foundations of modern machine learning.
Built to remember.
Bring your own syllabus — or describe a goal and let Hebbr draft the whole course for you.