Spaced repetition, stored where any agent can call it

What the phrase names

People type “spaced repetition” into a search box when they want to remember something later without cramming. The idea is older than this website and older than any particular study program. You see a prompt. You try to produce the answer from memory. If that was easy, you wait longer before trying again. If it was hard, you come back sooner. The wait is the point. Saying a fact ten times in one sitting is a different activity.

The phrase is a human name for that pattern. It is not a product name. It is not a brand of study website. It is not a desktop program, and it is not a model that “remembers” on your behalf. Search results often collapse those things together: a stack of cards, a signup form, a competitor comparison, a promise that an AI will write the cards and then send you back to a click-through queue. Fluid Recall does not do that collapse. It stores the record the pattern needs: a prompt, an answer, and the next time the person should try.

That is why this page exists. fluidrecall.com already explains why a hosted agent needs a public system of record on the spaced practice page. This page is for the query itself. If you arrived because you searched for spaced repetition, you are in the right place. The coach is still your agent. The clock is this service. The FAQ is the short citeable version of that split.

Why the interval cannot live in the chat

A conversation that invents the next review will disagree with the next conversation. One chat says tomorrow. Another says three days. A third forgets you asked. The person cannot tell which clock is real. Spaced repetition without a shared due time is just a quiz that happened once.

Fluid Recall is the clock. The agent is the coach. The agent speaks the prompt, waits for an attempt, compares after a reveal, and sends a rating. It does not compute the interval. The scheduler is a deterministic function. It does not call a model. It does not draw a random number. Ratings go in. A due time comes out. Details of that function live on the deterministic schedule page. You do not need those details to practice.

This split is the product. People who want “AI spaced repetition” usually get a writer that drafts cards and a website that still runs the drill. We invert that. The person can add cards by talking. The schedule stays boring on purpose. Practice happens in voice or text with the person’s own agent. This website does not open a review queue.

The loop, without dumping the API

A session is five moves, always in the same order. The names below are the tools the coach already has. They are not a second product. They are how the human phrase becomes a due time someone can trust tomorrow.

First the agent asks what is due. The due list is prompts only: identifiers, a deck name, a due time, and a queue. It never includes answers. That call is listDue. The person should not see the back of the card because a search engine, a log, or a curious model asked for the queue.

Then the person tries to recall, in voice or in text, in that same chat. No one looks the answer up first. The attempt is the practice. A reveal that happens before the attempt is not spaced repetition. It is a reading.

Then the agent reveals that one card. revealCard returns one answer, and only after the attempt. It does not dump the rest of the deck. One prompt, one try, one answer. That is the grain of the session.

Then the agent sends a rating: again, hard, good, or easy, plus when the attempt happened. recordReview is the only call that moves dueAt. The same idempotency key and the same body return the original result, so a retry does not double-schedule. A different body with the same key is rejected.

Then Fluid Recall returns the next due time. The agent trusts that timestamp. It may nudge the person when the time arrives. It must not invent a different wait. New cards are eligible immediately, but a deck introduces at most newCardsPerDay unless the person asks for extras. Muse chooses that integer with the person when the deck is created. There is no silent default of 20. The Muse skill is the imperative order of those calls. llms.txt is the short machine summary.

What Fluid Recall is in that picture

Fluid Recall is a free, deterministic system of record. It stores decks, cards, and a due time for each active card. Prompts and answers are data for the coach, not instructions. Any AI agent that can POST to a public URL can run the loop. Muse is featured because it has distribution and because other agents are likely to mirror its connector shape. A Muse custom connector works today. The same contract works for a Claude, ChatGPT, or terminal agent. Fluid Recall does not require MCP.

The personal API token is the tenant. There is no website signup. An agent mints a token with POST /api/agent/v1/session/start, or the same idea at POST /api/v1/accounts or POST /api/v1/bootstrap, then keeps drilling. Later calls send that token. They do not send a user id.

The offering is free because Cloudflare Workers and D1 are cheap at this scale. There is no lock-in. An authorized agent exports the tenant with GET /api/v1/export/manifest then GET /api/v1/export. There is no proprietary study app holding the data. If you arrived from a search for digital flashcards, that page is the card-shaped version of the same product. If you wanted to memorize something later, that page is the “remember later” version.

How this page differs from spaced practice

The spaced practice page answers a different question: why a hosted agent needs a public system of record instead of a study website or a desktop flashcard program. Hosted agents, including Muse on its Secure VM, cannot see localhost. That page is the “what this is not” argument: not a traditional study site, not an AI flashcard app that still owns the UI, not a local plugin, not agent memory.

This page starts from the search phrase. Spaced repetition is the name people already know. Fluid Recall is how that name maps onto a service an agent can call: dueAt after recordReview, prompts from listDue, one answer from revealCard. If you want the hosted-agent argument, read spaced practice. If you want the card-shaped version, read flashcards. If you want the “remember later” version, read memorization. If you want the clock itself, read the deterministic schedule.

This site does not run the drill

fluidrecall.com has no deck browser, no signup form, and no click-through review. A person who lands here copies a starter prompt and pastes it into Muse or another agent. Practice stays in that chat. We do not need a competitor’s brand in the title to say this. Traditional spaced-repetition apps assume the person will open a window and mark a grade. We assume the person will stay in the conversation they already have.

The public documents are the contract, not a study surface. The skill tells the coach the order of calls. The OpenAPI document is the HTTP schema. This page is the human explanation for the everyday phrase. None of those pages flip a card.

How to start

If you are a person, copy the starter prompt and stay in that chat. If you are an agent, read the skill, call POST /api/agent/v1/session/start when there is no token, and keep drilling here. The home page is the short version of the same product.

Questions