An Anki alternative that lives in the agent's chat

What “Anki alternative” means here

People type “Anki alternative” when they want spaced recall without living inside Anki. Anki is a human study app: a desktop program, a mobile app, a queue you open and click through. You see a prompt. You try. You mark a grade. Anki keeps the schedule. That product is good at being a study surface for a person who will sit in its window.

The phrase is a search, not a product name. It is not a promise of a prettier review screen. It is not a request for another flashcard website with a signup form. Search results often collapse those things together: a reskin of Anki, an “AI deck builder” that still owns the queue, a comparison chart that treats every spaced-recall service as a consumer study app. Fluid Recall does not do that collapse. It stores the recall record and the due clock so any AI agent can coach. The person stays in the conversation they already have.

That is why this page exists. fluidrecall.com already explains the clock on the spaced repetition page, the retrieve-before-answer method on active recall, and the card-shaped version on flashcards. This page is for the query itself. If you arrived because you searched for an Anki alternative, you are in the right place. The coach is still your agent. The attempt still happens in that chat. The FAQ is the short citeable version of that split.

Agent-first versus a human study app

Anki assumes a person will open Anki. Fluid Recall assumes a person will stay with Muse, Claude, ChatGPT, or a terminal agent and practice in voice or text there. The website is not the study surface. There is no deck browser and no signup form. A person who lands here copies a starter prompt and pastes it into the agent they already use.

A hosted agent cannot see a desktop program on localhost. Muse on its Secure VM calls the public internet. That is the hosted-agent argument on the spaced practice page: a system of record for those coaches has to live on a public URL, with a personal token, a skill, and an OpenAPI document. Anki is a program the person runs. Fluid Recall is a service the agent calls.

We are not trying to trick anyone into a “better Anki.” We are not manipulating anyone. We are not a gatekeeper. The agent is the primary user. The person is the one who recalls. Fluid Recall is the boring clock in the middle. Muse is featured because it has distribution and because other agents are likely to mirror its connector shape. Muse-compatible is not Muse-only.

What Fluid Recall is

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. 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/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.

The ratings are the same four words a person already knows from a human study app: again, hard, good, or easy. The agent sends one of those plus when the attempt happened. recordReview is the only call that moves dueAt. The scheduler is not a model. It does not invent an interval. Details of that function live on the deterministic schedule page. You do not need those details to practice.

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. Agents may use Markdown /api/v1/agent and /api/v1/dev for reads, JSON /api/v1 for writes, or MCP — whatever works best. JSON is not a leftover door. This page is the human explanation, not an API tutorial.

What Fluid Recall is not

It is not Anki with a different coat of paint. It is not a deck browser. It is not a click-through review. It does not run a drill because you opened a URL. It does not write the cards and then send the person back to a study screen. Many “AI Anki” products 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. Practice happens in voice or text with the person’s own agent. If you wanted the “remember later” version of the same product, that page is memorization.

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 a search for an Anki alternative 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. Anki can hide the answer behind a click in its own window. A public API cannot afford that leak.

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 recall. 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.

How this page differs from the siblings

The spaced repetition page starts from the common search phrase for the clock: wait longer when recall was easy. Active recall is the method: retrieve before you see the answer. Flashcards is the format. Memorization is the long-term outcome. Spaced practice answers why a hosted agent needs a public system of record instead of a study website or a desktop program.

Those pages share a product. They do not share this search intent. A person who typed “Anki alternative” is usually asking whether they still need a human study app, or whether an agent can keep the record and run the session in chat. Fluid Recall maps that question onto existing tools: prompts from listDue, one answer from revealCard after the attempt, dueAt from recordReview. Nothing on this page invents a new verb. If you want the clock, read spaced repetition. If you want the method, read active recall. If you want the card-shaped version, read flashcards. 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. Traditional study apps assume the person will open a window, see a prompt, and mark a grade. Many “AI study” products 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 people who searched for an Anki alternative. None of those pages flip a card. None of them show an answer because you opened a URL.

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