Zain Dana Harperlearn · study planning and course logistics

Study plans from your own material. Practice that stays yours.

Learn plans study sessions from your objectives and recorded attempts, using spaced review, retrieval practice, prerequisite checks and misconception tracking. It can also handle course logistics and stops at graded work.

See it work, step by step: an animated walkthrough with the real commands and output from the repository.

You supply the objectives, attempts and graded work. Learn schedules review, records practice and stops at anything graded.

A halftone sphere lit from one side, floating over a field of faint wavy lines.A halftone sphere lit from one side, floating over a field of faint wavy lines.
learn · v2.3.0 · published on npm · zero runtime dependencies · Node 20+

What it does

Learn is a command-line study planner for students and self-learners. You give it your objectives and record your practice attempts, and it tells you what to review next, which mistakes keep repeating and whether you are ready for the next topic.

It also runs course logistics from a workflow file. Every graded step halts and waits for you, so Learn never submits graded work on your behalf. Tutor attempts are saved as practice records, separate from anything graded.

Learn runs the recall questions and spaced review in the explainer films, in your browser.

The study loop

Spaced review Each concept comes back for review on a schedule tuned to your own recall history.
Retrieval practice The retrieval command makes cloze prompts from a draft you supply and an objective you name.
Predict, then observe Record a prediction as a pending attempt, then score it once you see the result.
Self-explanation A written explanation becomes a claim file you can check separately, for example with Crucible.
Misconceptions Wrong attempts are grouped by objective and ranked by count, with your feedback kept on each one.
Prerequisites Concepts are linked to what they depend on, so study order follows the dependencies.

learn tutor study is a planner. Given a saved session and a time, it returns what is due, the ranked misconceptions, the study order, prerequisite readiness and the mastery result.

learn tutor reverify recomputes a saved mastery result from the recorded attempts, and learn tutor prooflesson turns a Proof Surface packet into study prompts.

How it is built

Learn is a Node package with no third-party runtime dependencies. Sessions, schedules and course runs are JSON files on disk that you can open in a text editor. Optional modules prepare files for Gather, Crucible and Telos.

The MCP server offers planning tools and two local write operations: learn_tutor_plan creates a session and learn_tutor_record adds a practice attempt. Course runs stay on the CLI.

Install and run

Version 2.3.0 is published as @harperz9/learn. It installs the learn command and requires Node 20 or newer.

$ npm install -g @harperz9/learn
$ learn tutor plan mysession --topic derivatives --objectives power-rule,chain-rule
tutor plan mysession: 2 objective(s)

$ learn tutor record mysession --objective power-rule --prompt "Differentiate x^4" --answer "4x^3" --correct true
tutor record mysession: 1 practice attempt(s)

$ learn tutor study mysession --now 2026-08-28T12:00:00Z
tutor study mysession: due list, misconception count, order, readiness, and mastery status

$ learn run course.json --id course-run   # course logistics; assessment nodes halt for the learner
run course-run: halted @step 2

Use the tutor commands to plan and record your own practice. Use the workflow runner only with a course workflow you have reviewed; live browser attachment is explicit through --native.

GitHub → HarperZ9/learn  ·  ← all flagships  ·  the index