Skip to content
Rheticus

Know what you can actually do.Not what you have read about.

Rheticus keeps a record of everything you study and prove, on your own computer, and plans your next session from it. Bring any model.

Early beta. Free during the early beta, with everything unlocked.

This is the app, not a mock-up.

Real screens from the beta, with an example learner studying calculus, Spanish and system design. Pick one.

Rheticus · Today
The Today screen: a greeting, the next review with its reason, the week's study and each track's progress

What to do next, why, and how long it takes, across every subject.

The app as it runs in the beta, with an example learner's data.

Four tools. None of them remembers what you proved.

You already have the tools. They do not share anything, so the thread goes after a week or two.

  • Your chatbot

    The plan never changes when your results do.

    Keeps: A roadmap, in a transcript

  • Your notes app

    It has no idea what you were trying to master.

    Keeps: Everything you wrote down

  • Your flashcards

    They know nothing about the curriculum around them.

    Keeps: The cards you made by hand

  • Your calendar

    It cannot tell what is due or what is blocked.

    Keeps: Two hours on Thursday

One record that every part reads and writes.

So three questions go unanswered. What am I trying to be able to do? What have I actually shown I can do? What is the best use of the next hour?

Five states. Each one has to be earned.

Every lesson sits in one of five states, and only a recorded attempt can move it. Reading about something never counts as knowing it.

State 1 of 5

Not encountered

You have not worked through this concept yet.

What earns it
Nothing. Every concept starts here.
What does not
Having heard of it. Having it on a roadmap. Having a book about it.

For example: Backpropagation is on the plan, three concepts ahead.

There is no percentage and no score. Read the full rules

Try one. Answer it and watch the record.

A working miniature of a practice session, running the app's rules in your browser. Get it wrong on purpose, then retry, and see what does and does not count.

Practice, Calculus for machine learning

Calculus for machine learning, Chain rule

Demonstration item, no hints

Differentiate f(x) = (3x2 + 1)4

Choose your answer
Hints off for this item

Pick an answer and submit it. Your attempt is saved before it is checked, and only the result of the check can move the state.

It decides what comes next.

Open the app and it tells you the most useful thing to do with the time you have, across every subject, and why.

Tonight, 45 minutes

Ranked by rule, not by a model

  1. Review HTTP basics

    10 min

    Overdue by 2 days

  2. Practise Chain rule

    20 min

    Unblocks 3 concepts

  3. Learn Preterite: regular verbs

    15 min

    Spanish is behind its weekly hours

  4. Demonstrate Making requests

    20 min

    Checkpoint in 3 days

  5. Confirm 2 provisional markings

    5 min

    Short, batched

The last two did not fit tonight and move to tomorrow. The same state and the same clock always produce the same plan, and every suggestion says why it is there.

Reviews that space out

Pass a review and the next one moves further away. Miss one and it comes back in 2 days.

Reviews fall 7, 16, 35 and 75 days after a concept is demonstrated.

Blockers, named

The planner never schedules a blocked concept. It schedules whatever is blocking it.

  1. Chain rulescheduled tonight
  2. Backpropagation
  3. Training a network

One system. Every subject taught its own way.

Mathematics is not learned like a language. The record and the five states stay the same; the practice, the checking and the reviews change with the subject.

“Build and deploy a useful application in eight weeks.”

First discipline to ship

A typical 45-minute session

  1. 5 minReview a due concept
  2. 10 minIntroduction by questions
  3. 20 minImplement with tests
  4. 5 minExplain your solution
  5. 5 minSummary

Orange steps produce evidence. The rest is exposure.

You practise with
Exercises, implementations, debugging, projects
Checked by
Unit tests and output comparison, run on your machine
Demonstration looks like
Implement from a specification with every test passing
Review looks like
A small new implementation, or a bug to find

Your record outlives your model.

The app owns the learning record. Models and agents are interchangeable workers on it, so you can switch whenever a better one appears and lose nothing.

Your learning recordOne SQLite file, on your computerThe model you bring
Anthropic
OpenAI
Google Gemini
OpenRouter
Ollama
The agents you use
Claude Code
Codex
Any MCP client
Plain Markdown, any time
Answering now: AnthropicSwitch the model and the record does not change. Agents reach it through the MCP server.
  • A model's output is a proposal

    Everything a model returns is checked against a schema before the app decides what to write. A failed call cannot damage your record.

  • You see where it goes

    The active model is always on screen, and what each request cost is counted, with caps you set.

  • API keys are billed separately

    A chat subscription is not an API key. You pay your provider by usage, or nothing at all with a local model.

How models and agents connect

The method is written down.

Fifteen Kircher skills: plain SKILL.md files that every agent in the app follows, from mapping a field to making it stick. Open source is planned; for now the repository is private while we bring the skills up to the bar we set for them.

  • Plan

    Learn anything, Curriculum architect, Placement test, Learning planner

  • Learn

    Lesson teacher, Socratic tutor, Reading companion, Teach back, What-if lab

  • Practise and prove

    Assessor, Practice coach, Error detective, Project coach

  • Remember and keep

    Memory coach, Study notes

See the skills

skills/assessor/SKILL.md
---
name: assessor
description: Writes fair questions and quizzes that test
  whether someone can actually do a thing, and marks
  answers honestly against an explicit rubric with a
  stated confidence, naming the specific misconception
  behind a miss.
---

# Assessor

You find out whether someone can do a thing, and you
tell them the truth about it in a way they can act on.
Two halves: writing questions that are fair, and
marking answers that are honest.

## Writing a quiz

### 1. Set it up first

Never write a quiz before you know what it covers,
how many questions, how hard, and which kinds.

Free while it is in beta.

Everyone in the early beta gets the whole app, unlocked. After the beta: a free version with one track, and one payment for everything. You bring the model, so we never charge for tokens.

Early beta

Now

Freewhile the beta runs

The whole app, every capability unlocked, for everyone who joins the beta.

  • Unlimited tracks
  • All nine agents and the Kircher skills
  • Lessons, practice, checks, projects and reviews
  • The five states and the full evidence log
  • Today, the planner and the schedule

What you tell us decides what gets built next.

Free

₹0after the beta

The complete learning loop, on one track.

  • One track
  • Lessons, practice, checks and reviews
  • The five states and the full evidence log
  • Today and the planner
  • Notes and your own sources

Full version

One paymentprice to be announced

Pay once and keep every capability. No subscription, no renewal.

  • Unlimited tracks
  • Everything in Free
  • Every agent, skill, tool and connection the app has
  • Bought once, kept for good

The full version's price is not set yet. Compare the plans

Start keeping the record.

Free during the early beta, with everything unlocked. Join the beta and the Windows build comes to you first.