AI fills the screen. Sapior fills your mind.
AI can answer anything. Almost none of it survives the conversation. Sapior turns those answers into real knowledge — and proves it stuck.
You ask AI everything. You remember almost none of it.
Every explanation you've asked for, every concept that clicked at 11pm, every practice question you got right once and never saw again — gone. Not because you're bad at learning, but because nothing was keeping score.
AI memory remembers you. Sapior remembers what you know.
Switch from Claude to ChatGPT tomorrow? Nothing breaks. Your learning record belongs to you, not to any AI vendor — and unlike an AI's memory of your name and preferences, it's a live model of what you actually know and what's fading.
That's the whole point of a layer: cross-vendor by design, and yours to keep.
When you need to know X% by Y Date.
That's the entire product.
Give Sapior a goal, a target, and a date. It paces the plan, watches your actual retention — not your study hours — and tells you every day whether you're on track to hit your number. If the math says you'll fall short, you find out in week three, not the night before.
Hope is not a study plan. A retention model with a deadline is.
How it works
Sapior plugs into the AI assistant you already use. You bring the goal; Sapior runs the schedule.
Built so it actually sticks
These aren't study hacks. They're the most replicated findings in learning science, turned into how Sapior decides what you see and when. The full methods are on the methods page.
Who Sapior is for
Anyone with a learning goal that won't fit in a single session.
A map of your mind
Today, Sapior tracks every goal you study deliberately. Where it's headed: one engine, everywhere you learn. Your AI of choice, an extension in your browser, eventually the hardware you carry — all feeding the same engine, so anything important to your job, your degree, or your career gets captured, kept alive, and never quietly lost.
Everything layers into the engine and builds a living map of what you know, what you're mastering, and what's starting to fade — a fitness dashboard for your mind, with the Sapior Score at the center.
In a world where AI does more of the work, the value of a person concentrates in the one place that can't be outsourced: what's actually in their head. Sapior is building the instrument that measures it and the engine that protects it.
That's the destination. Today's product is the first honest mile: real goals, real retention, one real number — already running inside the AI you use.
Frequently asked
If something's missing, ask your AI. It can call Sapior and answer.
What is MCP and why does it matter?
Model Context Protocol is the open standard for letting an AI assistant call external tools and remember state between sessions. Sapior is an MCP server, which means any compliant AI — Claude, ChatGPT, Cursor — can use it without integration work on your end.
Does Sapior generate the actual quiz questions?
When you study through Claude or ChatGPT, the host AI generates the question text from Sapior's directives — what concept to test, at what depth, given your retention. Sapior owns the curriculum and scoring; the AI handles presentation. The web wrapper uses Sapior's own LLM end-to-end.
What happens to my study history if I switch AIs?
Nothing. Your plan and retention live in Sapior, not in your AI's chat history. Connect a different AI tomorrow and pick up exactly where you stopped.
Can I bring my own course materials?
Small inline source context — pasted notes, excerpts, study guides — is supported today. Full-textbook ingestion with chunking and indexing is on the roadmap.
Is this a credentialing service?
No. The progress estimate is a rolling prediction built on two inputs: how much of your goal you've covered, and a model of your retention for each item you've studied.
What does it cost?
Free during the discovery phase, with a usage cap. Pricing comes after we know the engine works for you.
Where are we headed?
Toward one engine, everywhere you learn. Today, Sapior tracks the goals you study deliberately. Where we're headed: a layer across everything you learn with AI — your assistant, your browser, eventually the hardware you carry — building a living map of what you know, what you're mastering, and what's starting to fade, with the Sapior Score at the center.
In a world where AI does more of the work, the value of a person concentrates in the one place that can't be outsourced: what's actually in their head. We're building the instrument that measures it and the engine that protects it. That's the destination — today's product is the first honest mile.