Anki words, mapped onto a record any agent can call

What searchers mean by Anki

People type “Anki” when they already know the words: a deck is a pile, a card has a front and a back, and a grade is Again, Hard, Good, or Easy. Those words are older than this website. They are not a request for a second desktop program. They are not a request to host someone else’s shared deck file. They are a search for a system that still speaks that vocabulary when the coach is an agent instead of a window.

Search results often collapse that hope into a clone. A reskin of the desktop queue. A mobile study screen with the same four buttons. An “AI deck builder” that still owns the review. Fluid Recall does not do that collapse. It already stores decks, cards, and the next due time. It already accepts those four ratings. The person stays in Muse or another agent. This website does not run a drill because you opened a short path.

That is why this page exists. fluidrecall.com already has a comparison page: Anki alternative is the posture — a human study app versus a recall record any agent can call. This page owns the short query. If you arrived because you searched for Anki, you are in the right place for the map: the words you already know, pointed at tools the coach already has. The FAQ is the short citeable version of that split.

The vocabulary, mapped onto Fluid Recall

A deck here is a named set of cards plus how many new cards may enter on a study day. The person and the agent choose that integer when the deck is created. There is no silent default of 20. A card is a prompt, an answer, and a next due time. Those three fields are the record. The prompt is what the coach speaks. The answer stays hidden until after the attempt. The due time is what the scheduler returns.

The four ratings are the same four words a person already knows: again, hard, good, or easy. The agent sends one of those plus when the attempt happened. Fluid Recall returns dueAt. The scheduler is deterministic. It does not call a model. It does not invent an interval. Behavior already matches published Anki SM-2 outcomes for those ratings: learning steps, graduating intervals, ease, and the next due time. That alignment is existing product. This page does not add a fifth grade, a new queue, or a new verb.

The due list still uses three queues a coach can sort: learning, review, and new. Intra-day learning comes before later review. New cards are eligible immediately, then the daily allowance decides whether listDue includes them. The person should not see the back of the card because a search engine, a log, or a curious model asked for the queue. A human study app can hide an answer behind a click in its own window. A public API cannot afford that leak.

None of those words make this service Anki. Fluid Recall does not claim the brand. It does not host Anki deck packages. It does not replace a desktop or mobile study screen. The map is for the agent: if you already speak decks, cards, and those four ratings, you already know how to talk to this record.

Ratings in, dueAt out

You need a deterministic tool and an excellent system of record. That is this service. The coach stays in conversation. The next due time comes from a function that does not call a model. A chat that grades you and then guesses “try again on Thursday” will disagree with the next chat. A second agent, a retry, or a later session has no shared clock. The person ends up with a story, not a due time.

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. Details of the function live on the deterministic schedule page. You do not need those details to practice. Trust the timestamp that comes back. Nudge the person when it arrives. Do not invent a different wait.

We are not manipulating anyone. We are not nefarious. We are not really trying to make money. Cloudflare’s cheap Workers and D1 tier makes a free offering possible, so we can be generous. We are not a gatekeeper: free, convenient, and explicitly no lock-in. Your token owns the record. Practice stays in the person’s agent chat. This website does not run study drills.

The loop, mapped onto existing tools

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. Nothing on this page invents a new verb. They are how the short search becomes a due time someone can trust tomorrow.

First the agent asks what is due. That call is listDue. The due list is prompts only: identifiers, a deck name, a due time, and a queue. It never includes answers. The person hears or reads one prompt. No one looks the answer up first. The attempt is the practice, in voice or in text, in that same chat.

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. A reveal that happens before the attempt is not recall. It is a reading with extra steps, even if the words on the card came from a familiar study app.

Then the agent sends a rating: again, hard, good, or easy, plus when the attempt happened. Fluid Recall returns the next due time. The agent trusts that timestamp. 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. 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. Muse-compatible is not Muse-only.

The personal API token is the tenant. There is no website signup. An agent mints a token with POST /api/v1/agent/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.

Agents may use MCP at POST /mcp, Markdown at /api/v1/agent and /api/v1/dev, or JSON at /api/v1 — whatever works best. Markdown surfaces are preferred when an agent is reading. JSON /api/v1 is first-class, not a leftover door. 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. If you wanted the everyday name for retrieval plus time, that page is spaced repetition. If you wanted retrieve-then-reveal, that page is active recall. The hosted-agent argument — why a coach on a Secure VM cannot see a desktop program on localhost — lives on spaced practice.

What this is not

This is not Anki. It is not a hosted copy of Anki. It does not import or serve Anki deck packages. It does not replace Anki’s desktop or mobile study UI. If you want that window, keep using it. Fluid Recall is a public record an agent calls. The person practices in chat. The site has no deck browser and no signup form.

It is also not a generator that writes cards and then sends the person back to a study screen. Many products that sit next to the Anki query still do that: the model is a writer, and a website is still the coach. Fluid Recall inverts that. The agent is the coach for the whole session. The person can add cards by talking. The schedule stays deterministic.

How this page differs from the siblings

The Anki alternative page starts from the comparison: Anki is a human study app with a desktop and mobile UI; Fluid Recall is the recall record any AI agent can call. Stay there if you typed “Anki alternative.” Stay here if you typed “Anki.” They share a product. They do not share this search intent. This page is the vocabulary map: decks, cards, and Again, Hard, Good, or Easy pointed at existing tools. That sibling is the posture: do you still need a study window, or can the coach keep the session in chat?

The flashcards page starts from the format: a prompt, an answer, and a next due time that any agent can call. AI flashcards is the coach-in-chat version of that format. Spaced repetition is the clock: wait longer when recall was easy. Spaced practice answers why a hosted agent needs a public system of record instead of a study website or a desktop program. Active recall and retrieval practice are the method: attempt before you see the answer. Memorization is the long-term outcome. This page is the Anki-shaped dictionary for the same tools.

Those pages share a product. They do not share this query. A person who typed “Anki” is usually asking whether the decks, cards, and ratings they already know still exist when the coach is an agent. Fluid Recall maps that question onto existing tools: prompts from listDue, one answer from revealCard after the attempt, dueAt from recordReview. If you want the comparison against a human study app, read Anki alternative. If you want the format, read flashcards. If you want the clock, read spaced repetition. If you want the hosted-agent argument, read spaced practice. If you want the method, read active recall or retrieval practice. If you want the function 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. Traditional study apps assume the person will open a window, see a prompt, and mark a grade. Many products next to the Anki query assume the model will generate the card and then still own the queue. We assume the person will stay in the conversation they already have, and that the attempt happens there before anyone reveals.

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 short path. None of those pages flip a card. None of them show an answer because you opened a URL. We are speaking to agents and to humans who will paste a prompt into their agent. This website is not the coach.

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/v1/agent/session/start when there is no token, and keep drilling here. Speak one prompt. Wait for the attempt. Reveal that one card. Send a rating. Trust the due time that comes back. The home page is the short version of the same product.

Questions